JP2008301476A - Image processing apparatus, image forming apparatus, image reading apparatus, image processing system, and image processing method, image processing program and recording medium therefor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing apparatus capable of determining a similarity between input image data and a reference image and restricting contents of a process on the input image data in accordance with the result of the determination. <P>SOLUTION: An image processing apparatus includes: a data obtaining section for obtaining input image data; a memory 8 in which reference image data or features of a reference image are stored; and a similarity determination process section 34 for performing a determination process in which it is determined whether the input image data are image data corresponding to the reference image or not. The similarity determination process section 34 changes process contents of the determination process in accordance with related information of the input image data. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an image processing apparatus, an image forming apparatus, an image reading apparatus, an image processing system, and an image processing method that determine the degree of similarity between input image data and registered image data registered in advance, and perform control according to the determination result The present invention relates to an image processing program and its recording medium.

  Conventionally, input image data obtained by reading a document image with a scanner is compared with a registered image registered in advance to determine the similarity between the two, and processing on the input image data based on the determination result (for example, Technology for controlling copying, transmission, editing, etc. is used.

  As a method for determining the similarity, for example, a keyword is extracted from an image using an OCR (Optical Character Reader) or the like and matching is performed based on the keyword, or the target image is limited to a form image having a ruled line, and matching is performed based on the characteristic of the ruled line. And the like (see Patent Document 1), the determination method based on the input image data and the color distribution of the registered image (see Patent Document 2), and the like. In Patent Document 3, a plurality of feature points are extracted from a digital image, a set of local feature points is determined for each extracted feature point, and a subset of feature points is selected from each determined set Then, as an amount to characterize each selected subset, invariants for geometric transformation are obtained based on a plurality of combinations of feature points in the subset, and feature amounts are calculated by combining the obtained invariants. A technique for searching for a document / image corresponding to the digital image by voting the calculated feature value on the document / image in the database is disclosed.

  Further, as a technique for controlling processing on input image data in accordance with the similarity determination result, for example, based on a pattern detected from input image data in order to cope with counterfeit bills and securities by a color image forming apparatus. It is determined whether the input image data is image data of banknotes, securities, etc. (registered image). If the input image data is image data of a registered image, the image forming apparatus that has made a copy from the output image can be specified. There are known techniques for adding a specific pattern to an output image, painting a copy image, and prohibiting a copy operation.

  Further, in Patent Document 4, it is determined whether or not the input image data is a registered image (specific image), and if it is determined that the input image data is a registered image, the apparatus administrator reports that the input image data is a registered image. And a technique for preventing normal copy output of registered images is disclosed. Japanese Patent Application Laid-Open No. 2004-151867 describes that a registered image is determined when the device administrator recognizes that the input image data is not a registered image after the device administrator is notified that the image is a registered image. It is described that the judgment level is changed.

Further, in Patent Document 5, it is determined whether or not input image data is image data of a document (registered image) such as a banknote, and when it is determined that the input image data is image data of a registered image, normal image formation is not performed. In addition to restricting the image forming function, status information indicating that the registered image was about to be printed and its detailed status (date and time, number of copies to be printed, scale, image to be printed, recognition processing log, illegal A technique for reporting a recognized partial image or the like to another apparatus is disclosed. In addition, it is described that when a log of recognition processing and a partial image recognized as illegal are transmitted as situation information, the information is encrypted and transmitted.
JP-A-8-255236 (released on October 1, 1996) JP 5-110815 A (published April 30, 1993) International Publication No. 2006/092957 pamphlet (published on September 8, 2006) JP 11-284847 A (published on October 15, 1999) JP 2002-232707 A (released on August 16, 2002) JP 2004-88663 A (published March 18, 2004)

  By the way, in an image processing apparatus that determines whether or not the input image data is image data of a registered image (similarity between the input image and the registered image), an erroneous determination is made depending on conditions at the time of reading due to limitations on image reading accuracy. Can happen.

  Therefore, in order to improve security, it is conceivable to set the similarity threshold low when it is determined that the input image data is a registered image. However, in this case, the image data is not actually registered image data. Nevertheless, the frequency of determining that the image data is a registered image increases. As a result, for example, the processing content of input image data that should not be restricted is restricted, or notification to the administrator due to misjudgment frequently occurs, increasing the burden on the administrator. As a result, the convenience of the user or administrator is reduced.

  On the other hand, if the threshold value is set high, the frequency of determining that the image data is not registered image data although it is input image data related to the registered image is increased, resulting in a problem that security is deteriorated.

  For this reason, the threshold value needs to be set in consideration of whether security or convenience is important.

  However, whether security or convenience should be emphasized depends on, for example, incidental conditions of the input image data (for example, user, date, day of the week or time (time zone), processing mode, processing data amount, image of a specific hue) It may differ depending on whether or not data is included.

  For example, for users who satisfy a predetermined condition (for example, users belonging to a specific department in a company, users registered in advance, etc.), importance is placed on convenience, whereas for users who do not satisfy the predetermined condition By placing importance on security, there are cases where it is desired to prevent an unspecified number of users from being able to process an image that may be a registered image, and to prevent unauthorized use and leakage of the registered image.

  In addition, on the predetermined day, day of the week, or time (for example, a normal working day, a normal working hour in a company, a preset day, a day of the week, a time, etc.), the above-mentioned predetermined day, day of the week is emphasized. Alternatively, by focusing on security other than the time (for example, holidays, nighttime, etc.), the day, day of the week, or time when processing for an image that may be a registered image can be limited, There is a case where it is desired to prevent leakage.

  Further, while giving importance to security for a predetermined processing mode (for example, transmission to a network, copying, printing, etc.), the registered image is emphasized for convenience for processing other than the predetermined processing mode. In some cases, it is desirable to limit the processing modes that can be executed on an image that may be, and to prevent unauthorized use or leakage of registered images.

  In addition, data less than a predetermined amount (for example, a predetermined number of originals, a predetermined number of customer information, etc.) is regarded as a convenience, while data exceeding a predetermined amount is regarded as a registered image by emphasizing security. In some cases, it is desired to limit the amount of data that can be processed for a peculiar image and prevent a large amount of registered images from leaking.

  For example, a secret document or the like is often stamped with characters such as “secret”, “top secret”, and “confidential” written in a predetermined color such as red or blue. For this reason, when input image data includes an image of a predetermined color, security may be emphasized, and when an image of a predetermined color is not included, convenience may be emphasized.

  However, in the techniques of each of the above patent documents, the determination of the similarity between the input image and the registered image is always performed based on the same standard (the same threshold value), and determination processing according to the incidental conditions of the input image data can be performed. Can not.

  The present invention has been made in view of the above problems, and an object of the present invention is to determine whether input image data is image data of a registered image and perform processing according to the determination result. The determination process is performed according to the incidental conditions of the input image data.

  In order to solve the above problems, an image processing apparatus according to the present invention stores an input data acquisition unit that acquires input image data, a feature amount extraction unit that extracts a feature amount of input image data, and a feature amount of a registered image Input at least one of the registered image acquisition unit that acquires the feature amount of the registered image from the storage unit and the external device connected to be communicable with the feature amount of the input image data and the feature amount of the registered image An image processing apparatus including a similarity determination unit that performs a determination process as to whether or not the image data is image data corresponding to a registered image, wherein the similarity determination unit is responsive to incidental information of the input image data. The processing content of the determination process is changed. The data acquisition unit may acquire the input image data by reading a document image, or may acquire the input image data by communication from another device communicably connected to the image processing device. The input image data may be obtained by reading out image data recorded on various recording media, and the input image data is obtained by superimposing information input by the user on a predetermined format. May be.

  According to the above configuration, the input data acquisition unit that acquires the input image data, the feature amount extraction unit that extracts the feature amount of the input image data, the storage unit that stores the feature amount of the registered image, and the communicable connection are connected. An image in which the input image data corresponds to the registered image by comparing the feature amount of the input image data and the feature amount of the registered image with at least one of the registered image acquisition units that acquire the feature amount of the registered image from the external device A similarity determination unit that performs a process of determining whether or not the data is data. And this similarity determination part changes the processing content of a determination process according to the incidental information of input image data. Therefore, according to said structure, the determination process according to the incidental information of input image data can be performed.

  A processing input unit that receives a processing request for the input image data; and the supplementary information includes user information for specifying a user who has input the processing request, information indicating a date, day of the week, or time when the processing request is input. One or more of information indicating the size or number of pages of input image data, information indicating the content of a processing request, and information indicating whether or not an image of a predetermined hue is included in the input image data May be included. Note that the processing input unit may receive a processing request in a state added to the input image data (for example, a state added as header information), and by a user operation input separately from the input image data. A processing request input or a processing request input by communication may be accepted.

  According to the above configuration, the user who inputs the processing request, the date, day or time when the processing request is input, the size or number of pages of the input image data, the content of the processing request, and an image of a predetermined hue in the input image data It is possible to perform determination processing according to information indicating whether or not these are included, or a combination of these conditions.

  A similarity calculation unit that calculates a similarity between the input image data and the registered image; and a coefficient storage unit that stores a coefficient determined according to the content of the incidental information. Then, a corrected similarity calculated by correcting the similarity calculated by the similarity calculating unit based on the coefficient corresponding to the incidental information of the input image data is calculated, and the corrected similarity is compared with a preset threshold value. It is good also as a structure which performs the said determination process by doing. Note that the content of the incidental information corresponding to each coefficient is not particularly limited. For example, the user who requests processing for input image data, the date, day of the week, or day when processing for input image data is requested. The time, the size or number of pages of the input image data, the processing content for the input image data, and the like can be used. In this case, the coefficient is set for each user, each date, day of the week, or time, each size or number of pages, and each processing content.

  According to said structure, the correction similarity which correct | amended the similarity according to the content of incidental information is calculated, and a determination process is performed by comparing this correction similarity and a threshold value. Accordingly, since the determination process can be performed based on the corrected similarity obtained by correcting the similarity according to the incidental information, the similarity can be determined based on the determination criterion corresponding to the incidental information.

  The similarity determination unit calculates the corrected similarity for each page when the input image data includes image data of a plurality of pages, and calculates an added similarity obtained by adding the corrected similarities of a plurality of pages. The determination processing may be performed by comparing the added similarity with a preset first threshold value.

  According to the above configuration, the frequency of erroneous determination can be reduced by performing the determination process based on the added similarity obtained by adding the corrected similarities of a plurality of pages. That is, even if the image data is read from the same document, since the reading accuracy varies depending on the conditions for reading the image, the calculated similarity value varies. For this reason, there is always a possibility that an erroneous determination occurs in the determination process. On the other hand, according to the above configuration, since the determination process is performed based on the added similarity obtained by adding the corrected similarities of a plurality of pages, the influence of the variation in the similarity caused by the reading error of each page is reduced. In addition, the frequency of erroneous determination can be reduced.

  The similarity determination unit divides the input image data into a plurality of blocks, calculates the correction similarity for each block, calculates an addition similarity obtained by adding the correction similarities of the plurality of blocks, The determination process may be performed by comparing the added similarity with a preset second threshold value.

  According to the above configuration, by performing the determination process based on the added similarity obtained by adding the corrected similarities of a plurality of blocks, it is possible to reduce the frequency at which erroneous determination occurs.

  Also, a suitability input unit that accepts an input regarding the suitability of the determination result, and a coefficient that changes the coefficient used in the determination process when the suitability input unit receives an input indicating that the determination result is incorrect It is good also as a structure provided with the change part.

  According to the above configuration, when the suitability input unit receives an input indicating that the determination result is incorrect, the coefficient changing unit changes the coefficient used in the determination process. Thereby, the accuracy of the determination process can be improved.

  Also, an evaluation value storage unit for storing an evaluation value set for each group further classifying each item according to the content of each item included in the incidental information, and a reference evaluation value set for each item An evaluation value calculation unit that calculates an evaluation value for each item of the input image data based on the contents of each item in the incidental information of the input image data and the evaluation value stored in the evaluation value storage unit; The similarity determination unit calculates a difference for each item between the evaluation value for each item calculated by the evaluation value calculation unit and the reference evaluation value for each item, and calculates the difference between the items. The added value may be compared with a preset third threshold value, and the determination process may be performed based on the comparison result.

  According to said structure, the determination process according to the content of each item contained in the incidental information of input image data can be performed.

  According to the above configuration, when the suitability input unit receives an input indicating that the determination result is incorrect, the reference evaluation value change unit changes the reference evaluation value used in the determination process. Thereby, the accuracy of the determination process can be improved.

  In addition, a condition that stores at least one of the condition of the incidental information when the determination process is performed on the input image data and the condition of the incidental information when the determination process is not performed on the input image data A storage unit, wherein the similarity determination unit needs to perform the determination process on the input image data based on the incidental information of the input image data and the conditions stored in the condition storage unit. It is good also as a structure which judges.

  According to the above configuration, the similarity determination unit determines whether it is necessary to perform determination processing on the input image data based on the incidental information of the input image data and the conditions stored in the condition storage unit. To do. Therefore, for example, in the condition storage unit, the above-mentioned condition when performing certain processing on the input image data regardless of the determination result of the similarity between the input image data and the registered image, and the input image data according to the determination result By storing the above-described conditions for changing the processing for the input image data, processing corresponding to each case can be performed on the input image data.

  The similarity determination unit includes a similarity calculation unit that calculates the similarity between the input image data and the registered image, and a weighting coefficient storage unit that records a weighting coefficient set for each registered image. By comparing the value calculated by the similarity calculation unit with the weighting coefficient corresponding to the registered image and a preset threshold value, or the similarity calculated by the similarity calculation unit The determination processing may be performed by comparing the degree and a value obtained by multiplying a preset threshold by the weighting coefficient corresponding to the registered image.

  According to the above configuration, the determination process is performed by multiplying the weighting coefficient set for each registered image by the similarity between the input image data and the registered image or a preset threshold value. Accordingly, by setting the weighting coefficient according to the importance level of the registered image, the determination process can be performed using the similarity determination standard according to the importance level of the registered image.

  In addition, when the input image data is determined to be image data corresponding to the registered image by the determination process, a configuration is provided that includes a restriction processing unit that restricts processing according to the processing request for the input image data. It is good.

  According to said structure, while performing the determination process according to the incidental information of input image data, the process according to the said process request | requirement with respect to input image data can be restrict | limited according to the determination result.

  In addition, when the input image data is determined to be image data corresponding to the registered image by the determination process, a notification processing unit that performs notification to a preset notification destination may be provided.

  According to the above configuration, when the determination process according to the incidental information of the input image data is performed and it is determined that the input image data corresponding to the registered image has been input, a notification to that effect is notified to the preset notification destination. it can.

  In addition, when it is determined by the determination process that the input image data is image data corresponding to the registered image, the input image data or the registered image corresponding to the input image data is stored in a preset storage destination. It is good also as a structure to preserve | save.

  According to the above configuration, by storing the input image data determined to correspond to the registered image in a preset storage destination, the suitability of the determination process for the input image data can be confirmed later. .

  A storage unit that stores the feature amount of the registered image; and a registration unit that stores the feature amount of the registered image in the storage unit, wherein the feature amount extraction unit extracts the feature amount of the registered image, and The unit may store the feature amount of the registered image extracted by the feature amount extraction unit in the storage unit.

  According to said structure, the feature-value of the registration image memorize | stored in a memory | storage part can be added / updated.

  The feature amount extraction unit includes: a registered image acquisition unit that acquires a feature amount of a registered image from an external device that is communicably connected; and a registered image output unit that transmits a feature amount of the registered image to the external device. May extract the feature amount of the registered image, and the registered image output unit may transmit the feature amount of the registered image extracted by the feature amount extraction unit to the external device.

  According to the above configuration, the feature amount of the registered image acquired by the registered image acquisition unit is transmitted to the external device, the feature amount of the registered image is stored in the external device, or the feature of the registered image stored in the external device is stored. You can add and update quantities.

  An image forming apparatus according to the present invention is an image forming apparatus that forms an image according to input image data, and includes any one of the image processing apparatuses described above.

  According to said structure, the determination process according to the incidental information of input image data can be performed, and an image formation process can be restrict | limited according to this determination process result.

  An image reading apparatus of the present invention is an image reading apparatus that acquires input image data by reading a document, and includes any one of the image processing apparatuses described above.

  According to the above configuration, the determination process according to the incidental information of the input image data is performed, and the process for the input image data (for example, the output process of the input image data, the correction and the conversion for the input image data) is performed according to the determination process result. , Editing, compositing, processing, etc.).

  In order to solve the above problems, an image processing system of the present invention is an image processing system including an image processing device and a server device that is communicably connected to the image processing device. An input data acquisition unit that acquires data; a feature amount extraction unit that extracts a feature amount of input image data; a storage unit that stores a feature amount of a registered image; a feature amount of input image data; and a feature amount of a registered image; A similarity determination unit that performs a determination process to determine whether the input image data is image data corresponding to the registered image by comparing the input image data with the image processing apparatus and the server apparatus. The section is characterized in that the content of the determination process is changed according to the incidental information of the input image data. The image processing device is not particularly limited as long as it is a device that performs predetermined processing on image data. For example, a copier (copying machine), a printer, a facsimile, a display device, a communication device, and the like. Examples thereof include an apparatus, an image editing apparatus that processes, edits, combines, and corrects image data, or a combination of two or more of these.

  According to said structure, the input data acquisition part which acquires input image data, the feature-value extraction part which extracts the feature-value of input image data, the memory | storage part which memorize | stored the feature-value of the registration image, Input image data A similarity determination unit that compares the feature amount with the feature amount of the registered image and determines whether or not the input image data is image data corresponding to the registered image. And this similarity determination part changes the processing content of a determination process according to the incidental information of input image data. Therefore, according to said structure, the determination process according to the incidental information of input image data can be performed.

  Further, the feature amount extraction unit is provided in the image processing device, the similarity determination unit is provided in the server device, and the image processing device is a feature amount of input image data extracted by the feature amount extraction unit. Is output to the server device, and the server device may be configured to perform the determination process based on the feature amount acquired from the image processing device.

  According to the above configuration, it is possible to perform the determination process in the server device by extracting the feature amount of the input image data in the image processing device and outputting the extracted feature amount to the server device. Therefore, there is no need to transmit image data from the image processing apparatus to the server apparatus, and the amount of data transmitted from the image processing apparatus to the server apparatus can be reduced.

  The image processing apparatus includes a log generation unit that generates log information related to the input image data. The image processing apparatus outputs the log information to the server apparatus. When the determination unit determines that the input image data is image data corresponding to the registered image, the log information may be stored in a log storage unit provided in the server device.

  According to the above configuration, it is possible to check the document image determined to be the image data corresponding to the registered image with reference to the log information stored in the log storage unit. Therefore, the suitability of the determination result can be easily confirmed.

  The image processing apparatus includes an image compression unit that compresses input image data to generate compressed image data. The image processing apparatus outputs the compressed image data to the server apparatus, and the server apparatus When the similarity determination unit determines that the input image data is image data corresponding to the registered image, the compressed image data may be stored in an image storage unit provided in a server device.

  According to the above configuration, it is possible to confirm the document image determined to be the image data corresponding to the registered image with reference to the compressed image data stored in the image storage unit. Therefore, the suitability of the determination result can be easily confirmed.

  The image processing apparatus further includes an area separation unit that separates the input image data into a character area including a character and / or a line drawing and an area other than the character area. The character region and the region other than the character region may be compressed by different compression methods.

  According to the above-described configuration, for example, the original image can be confirmed appropriately by using a compression method for the character area that is more readable than the compression method for the area other than the character area.

  The image processing apparatus includes a character identification unit that identifies character information included in the input image data. The image processing apparatus outputs the character information to the server apparatus. When the similarity determining unit determines that the input image data is image data corresponding to the registered image, the character information may be stored in a character information storage unit provided in the server device.

  According to the above configuration, it is possible to confirm the document image determined to be the image data corresponding to the registered image with reference to the character information stored in the character information storage unit. Therefore, the suitability of the determination result can be easily confirmed.

  Further, the image processing apparatus or the server apparatus, when the similarity determination unit determines that the input image data is image data corresponding to the registered image, a notification for notifying a preset notification destination It is good also as a structure provided with the process part.

  According to the above configuration, a determination process corresponding to the incidental information of the input image data is performed, and when the input image data is determined to be image data corresponding to the registered image, a notification that is set in advance You can notify first.

  The image processing device or the server device may log the input image data and the input image data when the similarity determination unit determines that the input image data is image data corresponding to the registered image. At least one of the information may be stored in a preset storage destination.

  According to the above configuration, the input image data and the input image are determined when it is determined that the input image data is image data corresponding to the registered image while performing determination processing according to the incidental information of the input image data. By storing at least one of the log information regarding the data in a preset storage destination, it is possible to confirm later whether or not the determination processing for the input image data is appropriate.

  The second feature amount extraction unit that extracts the feature amount of the registered image and the registration unit that stores the feature amount of the registered image extracted by the second feature amount extraction unit in the storage unit may be provided. Good. Alternatively, the image processing apparatus includes a registration unit that stores the feature amount of the registered image in the storage unit, the feature amount extraction unit extracts the feature amount of the registration image, and the registration unit extracts the registered image extracted by the feature amount extraction unit. The feature amount may be stored in the storage unit.

  According to said structure, the feature-value of the registration image memorize | stored in a memory | storage part can be added / updated.

  In order to solve the above problems, an image processing method of the present invention includes an input data acquisition step for acquiring input image data, a feature amount extraction step for extracting feature amounts of input image data, and a feature amount of a registered image. A registration data acquisition step for acquiring, and a similarity determination step for comparing the feature amount of the input image data and the feature amount of the registered image to determine whether or not the input image data is image data corresponding to the registered image The content of the determination processing in the similarity determination step is changed according to the incidental information of the input image data.

  The above method includes an input data acquisition step for acquiring input image data, a feature amount extraction step for extracting feature amounts of the input image data, a registration data acquisition step for acquiring feature amounts of the registered image, A similarity determination step of comparing the feature amount with the feature amount of the registered image and determining whether or not the input image data is image data corresponding to the registered image. In this similarity determination step, the processing content of the determination process is changed according to the incidental information of the input image data. Therefore, according to the above method, it is possible to perform the determination process according to the incidental information of the input image data.

  The image processing apparatus may be realized by a computer. In this case, an image processing program for causing the image processing apparatus to be realized by the computer by causing the computer to operate as the respective units, and the program are recorded. Computer-readable recording media are also included in the scope of the present invention.

  As described above, the image processing apparatus, the image forming apparatus, the image reading apparatus, the image processing system, and the image processing method of the present invention change the processing content of the determination process according to the incidental information of the input image data.

  Therefore, the determination process according to the incidental information of the input image data can be performed.

Embodiment 1
An embodiment of the present invention will be described. In the present embodiment, an example in the case where the present invention is applied to a digital color multifunction peripheral (MFP) will be described.

(1-1. Configuration of Digital Color Multifunction Machine 1)
FIG. 2 is a block diagram showing a schematic configuration of a digital color multifunction peripheral (image processing apparatus, image forming apparatus, image reading apparatus) 1 according to the present embodiment. The digital color multifunction peripheral 1 has a copy function, a printer function, a facsimile transmission function, a scanner function, a scan to e-mail function, and the like.

  As shown in FIG. 2, the digital color MFP 1 includes a color image input device 2, a color image processing device 3, a color image output device 4, a communication device 5, and an operation panel 6.

  The color image input device (image reading device) 2 is composed of a scanner unit (not shown) having a device that converts optical information into an electrical signal, such as a CCD (Charge Coupled Device), for example, and a reflected light image from a document. Are output to the color image processing apparatus 3 as analog signals of RGB (R: red, G: green, B: blue).

  The color image processing apparatus 3 includes an A / D conversion unit 11, a shading correction unit 12, a document matching processing unit 13, an input tone correction unit 14, a region separation processing unit 15, a color correction unit 16, and a black generation and under color removal unit 17. A spatial filter processing unit 18, an output tone correction unit 19, and a tone reproduction processing unit 20. An analog signal output from the color image input device 2 to the color image processing device 3 is converted into an A / D conversion unit 11, a shading correction unit 12, a document matching processing unit 13, and an input tone correction unit in the color image processing device 3. 14, the region separation processing unit 15, the color correction unit 16, the black generation and under color removal unit 17, the spatial filter processing unit 18, the output gradation correction unit 19, and the gradation reproduction processing unit 20 are sent in this order, and CMYK digital color The signal is output to the color image output device 4 as a signal.

  The A / D (analog / digital) converter 11 converts RGB analog signals into digital signals.

  The shading correction unit 12 performs a process for removing various distortions generated in the illumination system, the imaging system, and the imaging system of the color image input apparatus 2 on the digital RGB signal sent from the A / D conversion unit 11. Is. Further, the shading correction unit 12 performs a process of converting color balance adjustment and a signal such as a density signal that can be easily handled by the image processing system employed in the color image processing apparatus 3.

  The document collation processing unit 13 determines the similarity (with / without similarity) between the input image data and the registered image. Further, the document matching processing unit 13 outputs the input RGB signal as it is to the input tone correction unit 14 at the subsequent stage. Details of the document collation processing unit 13 will be described later.

  The input tone correction unit 14 performs image quality adjustment processing such as removal of background color (background color density component: background density) and contrast on the RGB signal from which various distortions have been removed by the shading correction unit.

  The region separation processing unit 15 separates each pixel in the input image into one of a character region, a halftone dot region, and a photo region from the RGB signal. Based on the separation result, the region separation processing unit 15 generates a region identification signal indicating which region the pixel belongs to, the color correction unit 16, the black generation and under color removal unit 17, the spatial filter processing unit 18, and the gradation reproduction. The output signal is output to the processing unit 20, and the input signal output from the input tone correction unit 14 is output to the subsequent color correction unit 16 as it is.

  The color correction unit 16 performs a process of removing color turbidity based on spectral characteristics of CMY (C: cyan, M: magenta, Y: yellow) color materials including unnecessary absorption components in order to realize faithful color reproduction. Is.

  The black generation and under color removal unit 17 generates black (K) signals from the CMY three-color signals after color correction, and subtracts the K signals obtained by black generation from the original CMY signals to generate new CMY signals. The process to generate is performed. As a result, the CMY three-color signal is converted into a CMYK four-color signal.

  The spatial filter processing unit 18 performs spatial filter processing using a digital filter on the image data of the CMYK signal input from the black generation and under color removal unit 17 to correct the spatial frequency characteristics. As a result, blurring of the output image and deterioration of graininess can be reduced. Similar to the spatial filter processing unit 18, the gradation reproduction processing unit 20 also performs predetermined processing on the image data of the CMYK signal based on the region identification signal.

  For example, the region separated into characters by the region separation processing unit 15 has a high frequency enhancement amount in the sharp enhancement processing in the spatial filter processing by the spatial filter processing unit 18 in order to improve the reproducibility of black characters or color characters. Increased. At the same time, the tone reproduction processing unit 20 selects binarization or multi-value processing on a high-resolution screen suitable for high-frequency reproduction.

  Further, with respect to the region separated into halftone dot regions by the region separation processing unit 15, the spatial filter processing unit 18 performs low-pass filter processing for removing the input halftone component. The output tone correction unit 19 performs an output tone correction process for converting a signal such as a density signal into a halftone dot area ratio that is a characteristic value of the color image output device 4. Then, gradation reproduction processing (halftone generation) is performed so that the image is finally separated into pixels and each gradation is reproduced. For the region separated into photographs by the region separation processing unit 15, binarization or multi-value processing is performed on the screen with an emphasis on gradation reproducibility.

  The image data subjected to the above-described processes is temporarily stored in a storage device (not shown), read out at a predetermined timing, and input to the color image output device 4.

  The color image output device 4 outputs the image data input from the color image processing device 3 onto a recording material (for example, paper). The configuration of the color image output device 4 is not particularly limited, and for example, a color image output device using an electrophotographic method or an inkjet method can be used.

  The communication device 5 is composed of a modem or a network card, for example. The communication device 5 performs data communication with other devices (for example, personal computers, server devices, other digital multi-function devices, etc.) connected to the network via a network card, a LAN cable, or the like.

  When the image data is transmitted, the communication device 5 performs the transmission procedure with the other party and secures a state in which the image data can be transmitted. Then, the communication device 5 compresses the image data (image data read by the scanner) in a predetermined format. ) Is read from the memory, and necessary processing such as changing the compression format is performed, and then sequentially transmitted to the other party via the communication line.

  Further, when receiving the image data, the communication device 5 performs a communication procedure and receives the image data transmitted from the other party and inputs it to the color image processing device 3. The received image data is subjected to predetermined processing such as expansion processing, rotation processing, resolution conversion processing, output gradation correction, gradation reproduction processing, and the like by the color image processing apparatus 3 and is output by the color image output apparatus 4. The received image data may be stored in a storage device (not shown), and the color image processing device 3 may read it out as necessary to perform the predetermined processing.

The operation panel 6 includes, for example, a display unit such as a liquid crystal display and setting buttons (none of which are shown), and information corresponding to an instruction from a main control unit (not shown) of the digital color multifunction peripheral 1 is described above. While displaying on a display part, the information input from a user via the said setting button is transmitted to the said main control part. The user inputs a processing request (for example, processing mode (copying, printing, transmission, editing, etc.), number of copies (number of copies, number of copies), destination of input image data, etc.) for the input image data via the operation panel 6. can do. The main control unit includes, for example, a CPU (Central Processing Unit) and the like, and is based on programs and various data stored in a ROM (not shown) and the like, information input from the operation panel 6, and the like. To control the operation.

(1-2. Configuration of Document Collation Processing Unit)
Next, details of the document matching processing unit 13 will be described. The document matching processing unit 13 according to the present embodiment extracts a plurality of feature points from input image data, determines a set of local feature points for each extracted feature point, and features points from the determined sets. As a quantity that characterizes each selected subset, an invariant for geometric transformation is obtained based on a plurality of combinations of feature points in the subset, and the obtained invariants are combined. By calculating a hash value and voting for a registered image corresponding to the calculated hash value, a search for a registered image similar to the input image data and a determination process of similarity to the registered image (judgment of similarity / no similarity) I do.

  FIG. 1 is a block diagram illustrating a schematic configuration of the document matching processing unit 13. As shown in this figure, the document collation processing unit 13 includes a feature point calculation unit 31, a feature amount calculation unit 32, a voting processing unit 33, a similarity determination processing unit 34, and a registration processing unit 37. The operation of each unit of the document collation processing unit 13 is controlled by the control unit 7 provided in the color image processing apparatus 3. The control unit 7 may be provided in a main control unit for controlling the operation of each unit of the digital color multifunction peripheral 1, and is provided separately from the main control unit, and collaborates with the main control unit for document verification. It may control the operation of the processing unit 13. Further, the color image processing apparatus 3 is provided with a memory 8 for storing various data used for processing of each unit of the document matching processing unit 13, processing results, and the like, and the control unit 7 is stored in the memory 8. The processing is performed by appropriately referring to these pieces of information.

  The feature point calculation unit 31 extracts a connected part of a character string or a ruled line, and calculates the center of gravity of the connected part as a feature point.

  FIG. 3 is a block diagram illustrating a schematic configuration of the feature point calculation unit 31. As shown in this figure, the feature point calculation unit 31 includes a signal conversion processing unit (achromatic processing unit) 41, a resolution conversion unit 42, an MTF processing unit 43, a binarization processing unit 44, and a centroid calculation unit 45. ing.

  When the image data (RGB signal) input from the shading correction unit 12 is a color image, the signal conversion processing unit 41 achromatizes the image data and converts it into a lightness signal or a luminance signal.

  For example, the signal conversion processing unit 41 converts the RGB signal into the luminance signal Y by the following equation (1).

Yi = 0.30Ri + 0.59Gi + 0.11Bi (1)
Here, Y is a luminance signal of each pixel, R, G, and B are each color component in the RGB signal of each pixel, and the subscript i is a value assigned to each pixel (i is an integer of 1 or more). It is.

Alternatively, the RGB signal may be converted into a CIE 1976 L ^* a ^* b ^* signal (CIE: Commission International de l'Eclairage, L ^* : brightness, a ^* , b ^* : chromaticity).

  The resolution conversion unit 42 performs a scaling process on the input image data. For example, when the input image data is optically scaled by the color image input device 2, the resolution conversion unit 42 scales the input image data again so that the predetermined resolution is obtained. Further, the resolution conversion unit 42 may perform resolution conversion for lowering the resolution than the resolution read at the same magnification in the color image input device 2 in order to reduce the processing amount in each processing unit in the subsequent stage. (For example, image data read at 600 dpi (dot per inch) is converted to 300 dpi).

  An MTF (modulation transfer function) processing unit 43 is used to absorb (adjust) that the spatial frequency characteristics of the color image input device 2 are different for each model. In the image signal output by the CCD, MTF degradation occurs due to optical parts such as lenses and mirrors, aperture aperture of the light receiving surface of the CCD, transfer efficiency and afterimage, integration effects due to physical scanning, and scanning unevenness. ing. Due to the deterioration of the MTF, the read image is blurred. The MTF processing unit 43 performs a process of repairing the blur caused by the deterioration of the MTF by performing an appropriate filter process (enhancement process). Further, it is also used to suppress high-frequency components that are not necessary for the feature point extraction processing in the latter-stage gravity center calculation unit 45. That is, enhancement and smoothing processing is performed using a mixing filter (not shown). FIG. 4 shows an example of the filter coefficient in this mixed filter.

  The binarization processing unit 44 binarizes the image data by comparing the achromatic image data (brightness value (brightness signal) or brightness value (brightness signal)) with a preset threshold value. .

  The center-of-gravity calculation unit 45 performs labeling (labeling processing) on each pixel based on the image data binarized by the binarization processing unit 44 (for example, represented by “1” and “0”). I do. Then, a connected area where pixels with the same label are connected is specified, and the center of gravity of the specified connected area is extracted as a feature point. Further, the extracted feature points are output to the feature amount calculation unit 32. FIG. 5 is an explanatory diagram showing an example of the connected area extracted from the input image data and the center of gravity of the connected area, and shows the connected area and the center of gravity corresponding to the character string “A”. FIG. 6 is an explanatory diagram showing an example of each center of gravity (feature point) of a plurality of connected regions extracted from a character string included in input image data. The feature points can be represented by coordinate values (x coordinate, y coordinate) in the binary image.

  The feature amount calculation unit 32 includes a feature point extraction unit 32a, an invariant calculation unit 32b, and a hash value calculation unit 32c. The feature point calculated by the feature point calculation unit 31 is used to rotate and parallelize a document image. A feature amount (hash value and / or invariant) that is an invariable amount with respect to geometric deformation such as movement, enlargement, reduction, and parallel movement is calculated.

  As shown in FIG. 7, the feature point extraction unit 32a sets one feature point as a target feature point, and sets a predetermined number of feature points in the vicinity of the target feature point in order from the closest distance from the target feature point (here 4 points) are extracted as peripheral feature points. In the example of FIG. 7, when the feature point a is the feature point of interest, four feature points b, c, d, and e are extracted as the peripheral feature points, and when the feature point b is the feature point of interest. Four points of feature points a, c, e, and f are extracted as peripheral feature points.

  Further, the feature point extraction unit 32a extracts a combination of three points that can be selected from the four peripheral feature points extracted as described above. For example, as shown in FIGS. 8A to 8C, when the feature point a shown in FIG. 7 is the target feature point, three of the peripheral feature points b, c, d, and e Combinations, that is, combinations of peripheral feature points b, c, d, peripheral feature points b, c, e, and peripheral feature points b, d, e are extracted.

  Next, the invariant calculation unit 32b calculates an invariant (one of feature quantities) H′ij with respect to geometric deformation for each extracted combination. Here, i is a number indicating the feature point of interest (i is an integer equal to or greater than 1), and j is a number indicating a combination of three peripheral feature points (j is an integer equal to or greater than 1). In the present embodiment, the ratio of two of the lengths of the line segments connecting the peripheral feature points is set as the invariant Hij. The length of the line segment may be calculated based on the coordinate value of each peripheral feature point. For example, in the example of FIG. 8A, if the length of the line segment connecting the feature point c and the feature point d is A11 and the length of the line segment connecting the feature point c and the feature point b is B11, The variable H11 is H11 = A11 / B11. In the example of FIG. 8B, if the length of the line segment connecting the feature point c and the feature point b is A12 and the length of the line segment connecting the feature point b and the feature point e is B12, The variable H12 is H12 = A12 / B12. In the example of FIG. 8C, if the length of the line segment connecting the feature point d and the feature point b is A13 and the length of the line segment connecting the feature point b and the feature point e is B13, The variable H13 is H13 = A13 / B13. In this way, invariants H11, H12, and H13 are calculated in the examples of FIGS. 8 (a) to 8 (c). In the above example, the line segment connecting the peripheral feature point located on the left side in the horizontal direction and the peripheral feature point located in the center in the horizontal direction is Aij, and the peripheral feature point located in the center in the horizontal direction is located on the right side in the horizontal direction. The line segment connecting the peripheral feature points is Bij. However, the present invention is not limited to this, and the line segment used for calculating the invariant Hij may be selected by an arbitrary method.

Next, the hash value calculation unit 32c
(H′i1 × 10 ² + H′i2 × 10 ¹ + H′i3 × 10 ⁰ ) / D (2)
Is calculated as a hash value (one of feature quantities) Hi and stored in the memory 8. Note that D is a constant set in advance according to how much the range of values that the remainder can take is set.

  Note that the method of calculating the invariant H′ij is not particularly limited. For example, the cross ratio of five points near the feature point of interest, and five points extracted from the neighboring n points (n is an integer of n ≧ 5). Noteworthy feature points such as the cross ratio, the arrangement of m points extracted from n points in the vicinity (m is an integer of m <n and m ≧ 5) and the value calculated based on the cross ratio of 5 points extracted from m points It is good also as said invariant H'ij. The cross ratio is a value obtained from four points on a straight line or five points on a plane, and is known as an invariant with respect to projective deformation which is a kind of geometric transformation.

  Also, the formula for calculating the hash value Hi is not limited to the above formula (2), and other hash functions (for example, any one of the hash functions described in Patent Document 3) may be used. Good.

  Further, each part of the feature quantity calculation unit 32, after completing the extraction of the peripheral feature points for one target feature point and the calculation of the hash value Hi, changes the target feature point to another feature point, A hash value is calculated, and hash values for all feature points are calculated.

  In the example of FIG. 7, when the extraction of the peripheral feature point and the hash value when the feature point a is the target feature point is finished, the extraction of the peripheral feature point and the hash value when the feature point b is the target feature point is completed. I do. In the example of FIG. 7, when the feature point b is set as the feature point of interest, four feature points a, c, e, and f are extracted as the peripheral feature points. Then, as shown in FIGS. 9A to 9C, a combination of three points selected from these peripheral feature points a, c, e, and f (peripheral feature points a, e, f, and peripheral points) Feature points c, e, f, peripheral feature points a, c, f) are extracted, and a hash value Hi is calculated for each combination and stored in the memory 8. Then, this process is repeated for each feature point, and a hash value when each feature point is a feature point of interest is obtained and stored in the memory 8.

  Note that the invariant calculation method when the feature point a is the feature point of interest is not limited to the above method. For example, as shown in FIGS. 28A to 28D, when the feature point a shown in FIG. 7 is the feature point of interest, three of the peripheral feature points b, c, d, and e are selected. Combinations, that is, peripheral feature points b, c, d, peripheral feature points b, c, e, peripheral feature points b, d, e, peripheral feature points c, d, e are extracted, and each extracted combination , An invariant (one of feature quantities) Hij with respect to geometric deformation may be calculated.

Further, when the feature point b shown in FIG. 7 is set as the feature point of interest, as shown in FIGS. 29 (a) to 29 (d), four peripheral feature points of feature points a, c, e, and f are used. A combination of three points (peripheral feature points a, e, f, peripheral feature points a, c, e, peripheral feature points a, f, c, peripheral feature points e, f, c) from You may make it calculate the invariant Hij with respect to geometric deformation about each combination. In this case, the remainder of (Hi1 × 10 ³ + Hi2 × 10 ² + Hi ³ × 10 ¹ + Hi4 × 10 ⁰ ) / D may be calculated as a hash value and stored in the memory 8.

  In the above example, the line segment connecting the peripheral feature point closest to the target feature point and the second closest peripheral feature point is Aij, and the peripheral feature point closest to the target feature point and the third closest peripheral feature point are The line segment connecting the two is connected to Bij. However, the present invention is not limited to this, and the line segment used for calculating the invariant Hij may be selected by an arbitrary method such as selecting based on the length of the line segment connecting the neighboring feature points. That's fine.

  Note that, when performing registration processing for registering input image data as a registered image, the feature amount calculation unit 32 performs registration processing for hash values (feature amounts) for each feature point of the input image data calculated as described above. Send to part 37.

  The registration processing unit 37 sequentially registers a hash value for each feature point calculated by the feature amount calculation unit 32 and an index (document ID) representing a document (input image data) in a hash table provided in the memory 8. (See FIG. 10A). If the hash value is already registered, the document ID is registered in association with the hash value. Document IDs are sequentially assigned numbers without duplication. When the number of documents registered in the hash table exceeds a predetermined value (for example, 80% of the number of documents that can be registered), the old document ID may be searched and sequentially deleted. The deleted document ID may be used again as the document ID of new input image data. Further, when the calculated hash values are the same value (H1 = H5 in the example of FIG. 10B), these may be combined and registered in the hash table.

  In addition, when performing a determination process (similarity determination process) on whether or not the input image data is image data of a registered image that has already been registered, the feature amount calculation unit 32 calculates the input image calculated as described above. A hash value for each feature point of the data is sent to the voting processing unit 33.

  The voting processing unit 33 compares the hash value of each feature point calculated from the input image data with the hash value registered in the hash table, and votes for registered images having the same hash value. In other words, for each registered image, the number of times the same hash value as the hash value of the registered image is calculated from the input image data is counted, and the count value is stored in the memory 8. FIG. 11 is a graph showing an example of the number of votes for registered images ID1, ID2, and ID3.

  The similarity determination processing unit 34 reads the voting result (the index of each registered image and the number of votes for each registered image; similarity) of the voting processing unit 33 from the memory 8 and obtains the maximum number of votes and the maximum number of votes obtained. Extract image index. Then, the extracted maximum number of votes is compared with a predetermined threshold value to determine similarity (whether or not the input image data is image data of a registered image), and a determination signal indicating the determination result is transmitted to the control unit 7. Send to. That is, if the maximum number of votes is greater than or equal to a predetermined threshold, it is determined that there is similarity (the input image data is image data of a registered image), and if it is less than the threshold, there is no similarity. (The input image data is not image data of a registered image).

  Alternatively, the similarity determination processing unit 34 calculates the similarity by dividing and normalizing the number of votes obtained for each registered image by the total number of votes (the total number of feature points extracted from the input image data). The similarity may be determined by comparing with a predetermined threshold value (for example, 80% of the total number of votes).

  In addition, the similarity determination processing unit 34 normalizes the number of votes obtained for each registered image by dividing by the number of registered hash values (maximum registered number) for the registered image having the largest number of registered hash values. The degree of similarity may be determined by calculating the degree and comparing the degree of similarity with a predetermined threshold (for example, 80% of the total number of votes). That is, if the calculated similarity is equal to or greater than the threshold, it is determined that “similarity exists”, and if it is less than the threshold, it is determined that “no similarity”. In this case, the total number of hash values extracted from the input image data may be larger than the maximum registered number (particularly when at least a part of the original and / or registered image has a handwritten part). The calculated value of similarity may exceed 100%.

  Further, the threshold for determining similarity may be constant for each registered image, or may be set for each registered image according to the importance of each registered image. The importance of the registered image depends on the registered image, for example, the importance is maximized for banknotes, securities, confidential documents, confidential documents, etc., and the importance is lower for banknotes, etc. May be set step by step. In this case, a weighting coefficient corresponding to the importance of the registered image is stored in the memory 8 in association with the index of the registered image, and the similarity determination processing unit 34 corresponds to the registered image that has obtained the maximum number of votes. The similarity may be determined using a threshold value.

  Further, when determining similarity, the threshold may be fixed, while similarity may be determined by multiplying the number of votes for each registered image (the number of votes obtained for each registered image) by the weighting coefficient of each registered image. . In this case, a weighting coefficient corresponding to the importance of each registered image is stored in the memory 8 in association with the index of each registered image, and the similarity determination processing unit 34 determines the number of registered images for each registered image. The number of corrected votes multiplied by the weighting coefficient is calculated, and the similarity may be determined based on the number of corrected votes. For example, the maximum corrected number of votes may be compared with a threshold value, the maximum corrected number of votes normalized with the total number of votes may be compared with the threshold value, and the maximum corrected number of votes normalized with the maximum number of registrations May be compared to a threshold. In this case, for example, the weighting factor may be set to a value larger than 1, and to a larger value as the importance of the registered image becomes higher.

  In this embodiment, one hash value is calculated for one feature point (attention feature point). However, the present invention is not limited to this, and a plurality of one feature point (attention feature point) may be calculated. A hash value may be calculated. For example, 6 points are extracted as the peripheral feature points of the feature point of interest, and for each of the 6 combinations obtained by extracting 5 points from these 6 points, 3 points are extracted from 5 points to obtain an invariant and a hash value is calculated. You may use the method to do. In this case, six hash values are calculated for one feature point.

The control unit 7 adds the incidental information of the input image data (for example, the user ID of the user who has input the input image data or the processing request for the input image data, the date, day of the week, the time when the input image data or the processing request is input, the input image Number of data pages (number of pages) or data volume,
Contents of the processing request (for example, processing mode (copying, printing, transmission, editing, etc.), number of processed sheets (number of copies, number of printed sheets, destination of input image data, etc.), input image data includes an image of a predetermined hue Whether or not the input image data is the image data of the registered image is determined based on whether the input image data is the image data of the registered image. That is, the control unit 7 determines whether or not the input image data is the monitoring target image based on the incidental information of the input image data, and performs the above determination process when determining that the input image data is the monitoring target image. If it is determined that the image is not a monitoring target image, the determination process is not performed.

  In the present embodiment, there is information regarding the combination of incidental information when it is necessary to determine whether the input image data is image data of a registered image and / or the combination of incidental information when it is not necessary to determine. , Stored in advance in an administrator folder of the memory 8 (a folder that can be browsed and written only by an administrator (for example, a specific user such as a security administrator in a company or a store)). And the incidental information of the input image data are compared to determine whether or not the determination process for the input image data is necessary.

  The incidental information of the input image data may be input to the color image processing apparatus 3 (or the digital color multifunction peripheral 1) in a state added to the input image data (for example, a state added as header information), for example. In addition to the input image data, it may be input to the color image processing apparatus 3 (or the digital color multifunction peripheral 1). For example, it may be input via the operation panel 6, may be input by reading a recording medium such as a personal card inserted in a reading means such as a card reader, or may be input from an external device by communication Good. Further, based on the input image data, the control unit 7 or the main control unit may calculate based on the condition, timing, etc. when the input image data is input.

  Further, based on the input image data, it may be determined whether or not an image including a specific hue is included in the input image data, and the determination result may be used as supplementary information. As a method for determining whether or not an image including a specific hue is included in the input image data, for example, a method described in Patent Document 6 can be used.

  In this method, first, a reference density (Base_Intensity) of RGB signals is calculated based on the following equation. Note that R, G, and B in the following expression represent the R value, G value, and B value of the RGB signal.

Base_Intensity = (R + G + B) / 3
Next, the value of the reference density obtained by the above formula is compared with the value of each color component (R, G, B) of the image data, and the value of each component (R, G, B) and the value of the reference density are compared. And the value of each color component (R, G, B) is binarized based on the following equation. That is, based on the following formula, the value of each color component (R, G, B) is converted to the value of (HR, HG, HB).

HR = {1 (R> Base_Intensity), 0 (R ≦ Base_Intensity)}
HG = {1 (G> Base_Intensity), 0 (G ≦ Base_Intensity)}
HB = {1 (B> Base_Intensity), 0 (B ≦ Base_Intensity)}
Then, a process of associating the converted values (HR, HG, HB) with the hue is performed. That is, if (HR, HG, HB) = (1, 0, 0), the hue of the RGB signal is red, and if (HR, HG, HB) = (0, 1, 0), the hue of the RGB signal is changed. If green, (HR, HG, HB) = (0, 0, 1), the hue of the RGB signal is determined to be blue. Note that when it is determined to be red including magenta colors, red when (HR, HG, HB) = (1, 0, 0) or (HR, HG, HB) = (1, 0, 1). May be determined.

  And when the pixel contained in the hue of a predetermined hue (for example, red) is extracted by the determination process, and the number of pixels of the predetermined hue is in a predetermined range (for example, a range of 7000 pixels to 100,000 pixels), It is determined that image data having a predetermined hue is included.

  The control unit 7 may be provided inside the color image processing apparatus 3 or may be provided outside the color image processing apparatus 3. The control unit 7 may be provided in the main control unit of the digital color multifunction peripheral 1.

(1-3. Processing in the digital color multifunction peripheral 1)
Next, processing in the digital color multifunction peripheral 1 will be described with reference to the flowchart shown in FIG.

  First, when receiving an instruction input (processing request) from the user via the operation panel 6 or the communication device 5, the control unit 7 initializes the score value SCR and the counter value CNT stored in the memory 8 (SCR = 0, CNT = 0) (S1). The counter value CNT is a numerical value indicating the number of originals (number of pages of the input image data), and the score value SCR is a numerical value indicating the number of originals determined to be similar.

  Next, the control unit 7 acquires input image data (S2). For example, input image data may be acquired by reading a document image with the color image input device 2, or input image data may be acquired from an external device by the communication device 5, and is provided in the digital color multifunction peripheral 1. Input image data may be read and acquired from various recording media via a card reader (not shown) or the like.

  Next, the control unit 7 determines whether it is necessary to perform a determination process for determining whether the image is a monitoring target image, that is, whether the input image data is image data of a registered image (S3). Specifically, conditions for performing a certain process on the input image data regardless of the determination result of the similarity between the input image data and the registered image (the incidental information of the input image data, a predetermined value in the input image data) Whether or not a hue image is included or a combination thereof) and conditions for changing the processing on the input image data according to the determination result are stored in the memory (condition storage unit) 8 in advance. The control unit 7 determines whether or not it is necessary to perform the determination process by comparing the condition extracted from the input image data or the accompanying information with the condition stored in the memory 8.

  When determining in S3 that it is not necessary to perform the restriction process, the control unit 7 proceeds to the process of S10. On the other hand, if it is determined in S3 that the restriction process needs to be performed, the control unit 7 controls each part of the document matching processing unit 13 to perform the feature point calculation process (S4), the feature amount calculation process (S5), and the voting process. (S6) A similarity determination process (S7) is performed.

  As a result of the similarity determination process, if it is determined that there is similarity, the score value SCR and the counter value are added (SCR = SCR + 1, CNT = CNT + 1) (S8), and the process proceeds to S11.

  On the other hand, if it is determined that there is no similarity as a result of the similarity determination process, the counter value is added without adding the score value SCR (CNT = CNT + 1) (S9), and the process proceeds to S10.

  Next, the control unit 7 determines whether or not the processing of S2 to S9 has been performed on all originals (input image data) (S10). If an unprocessed document remains, the control unit 7 performs the processing from S2 on the next document.

  On the other hand, when determining that all the originals have been acquired, the control unit 7 calculates the ratio of the score value SCR to the counter value CNT, that is, the average value (SCR / CNT) of the score values with respect to the number of originals (S11). Then, it is determined whether or not the value of SCR / CNT is larger than a preset threshold value TH1 (whether SCR / CNT> TH1) (S12).

  As described above, by using the average value of the score values with respect to the number of documents, that is, by accumulating and evaluating the similarities of a plurality of documents, the similarity calculation result caused by the document reading conditions, reading accuracy, etc. Fluctuating factors can be absorbed. For example, even if the similarity is calculated for the input image data of the same document, the similarity varies depending on the conditions under which the document is read, etc., but by accumulating the similarities and evaluating these factors, these variations are absorbed. The degree can be accurately evaluated. In addition, even when different document images are successively processed instead of the same document image, the similarity can be appropriately evaluated.

  When determining that SCR / CNT ≦ TH1 in S12, the control unit 7 determines that the input image data is not related to the registered image, and processes the input image data (according to the processing mode instructed by the instruction input). (Processing) is permitted (a signal for permitting processing is sent to the main control unit), and the processing is terminated (S13).

  On the other hand, if it is determined that SCR / CNT> TH1, the control unit 7 determines that the input image data relates to the registered image, and prohibits or restricts processing of the input image data (prohibits or restricts processing). A signal is sent to the main control unit) (S14), and a notification signal indicating that processing for the registered image is requested is output from the similarity determination processing unit 34 to the communication device 5 (S15), and the processing is terminated.

  In the above description, the average value (SCR / CNT) of the score value with respect to the number of originals is calculated after the processing for all the originals is completed, and is compared with the threshold value TH1. However, the present invention is not limited to this. The average value of the score values may be calculated for each predetermined number of sheets (for example, every 5 sheets or every 10 sheets) and compared with the threshold value TH1. Alternatively, the determination timing may be set by calculating the score value according to the number of processed sheets (for example, when processing of half the number of processed sheets is completed and processing for all originals is completed) Etc.).

  In S15, the communication device 5 notifies a preset transmission destination (for example, a server device) that processing for a registered image is requested. At this time, the communication device 5 inputs a log (operation recording information; for example, a document ID of the input image, a processing request) when it is determined that the communication device 5 is similar to the information indicating that processing for the registered image is requested. The user ID of the selected user, the date, day or time when the processing request was input, the content of the processing request, etc.), the input image data (or compressed image data obtained by compressing the input image data or image data reduced in resolution), The registered image index or the like may be notified to the server device (job log system), and the server device may store the information as necessary.

  Instead of input image data (or compressed image data obtained by compressing input image data or image data reduced in resolution), a registered image corresponding to the input image (or compressed image data obtained by compressing this registered image or reduced resolution) Image data) may be notified. In this case, the document ID of the input image and the registered image (or compressed image data obtained by compressing the registered image or image data reduced in resolution) may be notified, and the registered image (or the registered image is compressed). Only compressed image data or image data with reduced resolution) may be notified. In this way, by notifying the registered image data instead of the input image data, for example, even if the user's personal information is included in the input image data, this personal information can be used illegally. Can be prevented.

  Further, the notification to the transmission destination may be performed directly from the communication device 5 provided in the digital color multifunction peripheral 1 to the transmission destination, or another apparatus connected to the digital color multifunction peripheral 1 via a network (see FIG. (Not shown).

  In S15, the control unit 7 stores the various information in the administrator folder of the storage unit provided in the memory 8 or a device connected via the network, and the administrator accesses the administrator folder as necessary. By doing so, you may make it take out such information. Also, after storing this information in the administrator folder, the data stored in the administrator folder is deleted in order from the oldest data when a certain period of time has passed or the administrator folder is full. You may do it.

  In the present embodiment, the processing for the input image data is prohibited or restricted only when it is determined in S12 that SCR / CNT> TH1, but this is not limiting. For example, SCR / CNT> TH1. In addition to the case where it is determined that there is a document, the processing is prohibited or restricted when the number of documents exceeds a predetermined number (for example, 50) (or when the number of pages of input image data or the amount of data exceeds a predetermined amount). You may make it do. Thereby, for example, a large amount of personal information can be prevented from being leaked.

  As described above, in the digital color multifunction peripheral 1 according to the present embodiment, information for determining whether or not it is necessary to determine whether or not the input image data is that of the registered image (the input image data is registered). A combination of incidental information when it is necessary to determine whether the image data is image data or information regarding a combination of incidental information when it is not necessary to determine whether the image data is image data is stored in the administrator folder of the memory 8 in advance. The control unit 7 determines whether or not the determination process for the input image data is necessary based on this information and the incidental information of the input image data.

  Thereby, it is possible to determine whether or not the determination process is necessary according to the incidental information of the input image data, and to perform the determination process only when necessary. Therefore, for example, even if the input image data is for a registered image, if there is no need to restrict or prohibit the processing contents or notify a predetermined notification destination, the input is performed without performing the determination process. If the image processing is permitted and the input image data is for the registered image, it is necessary to restrict or prohibit the processing content or notify the specified notification destination. Depending on the result, the processing on the input image data can be restricted or prohibited.

  In the present embodiment, the control unit 7 determines whether or not the similarity determination process is necessary, and the determination process is performed only when it is determined to be necessary. However, the present invention is not limited to this. For example, when similarity determination processing is performed on all input image data and the similarity determination processing unit 34 determines that the input image is image data of a registered image, additional information on the input image data and input Based on the combination of incidental information when it is necessary to determine whether the image data is image data of a registered image, or information regarding the combination of incidental information when it is not necessary to determine The necessity of restriction or prohibition and / or the necessity of notification to a predetermined notification destination may be determined.

[Embodiment 2]
Another embodiment of the present invention will be described. For convenience of explanation, members having the same functions as those in the first embodiment are denoted by the same reference numerals, and description thereof is omitted.

(2-1. Configuration of Document Collation Processing Unit)
FIG. 13 is a block diagram illustrating a schematic configuration of the digital color multifunction peripheral 1 according to the present embodiment. As shown in this figure, the document matching processing unit 13 includes a feature point calculation unit 31, a feature amount calculation unit 32, a voting processing unit 33, a score calculation unit 35, a cumulative score comparison unit 36, and a registration processing unit 37. . The feature point calculation unit 31, the feature amount calculation unit 32, the voting processing unit 33, and the registration processing unit 37 can be the same as those in the first embodiment.

  The score calculation unit 35 calculates the similarity MCH (i) and the score value (corrected similarity) SCR (i) based on the voting result received from the voting processing unit 33 and sends it to the cumulative score comparison unit 36. Specifically, the score calculation unit 35 determines the number of votes of the registered image that has obtained the maximum number of votes for the i-th page (or block) in the input image data (i is an integer of 1 or more). The value normalized by dividing by the total number of feature points extracted from the image data is defined as the similarity MCH (i). The number of registered images obtained for the maximum number of votes for the i-th page (or block) in the input image data is divided by the number of registered images having the largest number of registered hash values (maximum number of registrations). The normalized value may be MCH (i).

  The score calculation unit 35 calculates a score value SCR (i) for the i-th page (or block) in the input image data from the following equation (3).

SCR (i) = MCH (i) × (α (m) + β (n) + γ (p) + δ (q)) / 4 (3)
Here, α (m) is a coefficient preset for each user, β (n) is a coefficient preset for each time zone, and γ (p) is a coefficient preset for each processing mode. Δ (q) is a coefficient indicating whether or not an image of a specific hue is included. m, n, and p are values assigned for each user, time zone, and processing mode, and are integers of 1 or more. Q is a value given depending on whether or not an image of a specific hue is included. Note that q may be a binary value indicating whether or not an image of a specific hue is included, and is a value set according to the number of pixels having a specific hue (for example, the number of pixels is It may be a value set so as to increase as the number increases. These coefficients are registered in advance in the administrator folder of the apparatus that is communicably connected via the memory 8 or the network, and the score calculation unit 35 refers to these coefficients stored in the administrator folder. A score value SCR (i) is calculated. FIG. 14 shows an example of these coefficients stored in the memory 8.

  The cumulative score comparison unit 36 sequentially adds (accumulates) the score values (corrected similarity) SCR (i) calculated by the score calculation unit 35 for each page (or each block) of the input image data, thereby obtaining a cumulative score (additional similarity). Degree) ASCR (i) is calculated. The cumulative score comparison unit 36 performs a cumulative score comparison process that compares the cumulative score ASCR (i) with the threshold value TH2 stored in the administrator folder, and sends a determination signal indicating the comparison result to the control unit 7. send. Note that the threshold value TH2 may be changed depending on whether the score value is calculated for each page or for each block. That is, when calculating a score value for each page, the first threshold value may be used, and when calculating a score value for each block, a second threshold value different from the first threshold value may be used. .

  Based on the determination signal from the cumulative score comparison unit 36, the control unit 7 determines whether the input image data is related to the registered image. Specifically, the control unit 7 determines that the input image data is related to the registered image when ASCR (i)> TH2, and has an input image when ASCR (i) ≦ TH2. The data is not related to the registered image (no similarity). If the control unit 7 determines that there is similarity, the control unit 7 restricts or prohibits processing on the input image data, and notifies a predetermined notification destination that processing on the registered image is requested. In addition, when the control unit 7 determines that there is no similarity, the control unit 7 permits processing on the input image data.

  The control unit 7 may be provided inside the color image processing apparatus 3 or may be provided outside the color image processing apparatus 3. The control unit 7 may be provided in the main control unit of the digital color multifunction peripheral 1.

(2-2. Processing in the digital color multifunction peripheral 1)
Next, similarity determination processing in the digital color multifunction peripheral 1 according to the present embodiment will be described with reference to a flowchart shown in FIG.

  First, when receiving an instruction input from the user via the operation panel 6 or the communication device 5, the control unit 7 initializes the score value SCR stored in the memory 8 (SCR (1) = 0) (S21). ).

  Next, the control unit 7 acquires input image data (S22). For example, input image data may be acquired by reading a document image with the color image input device 2, or input image data may be acquired from an external device by the communication device 5, and is provided in the digital color multifunction peripheral 1. Input image data may be read and acquired from various recording media via a card reader (not shown) or the like.

  Next, the control unit 7 controls each part of the document matching processing unit 13 to perform feature point calculation processing (S23), feature amount calculation processing (S24), voting processing (S25), score calculation processing (S26), and cumulative score. Calculation processing (S27) is performed.

  Next, the control unit 7 determines whether or not the cumulative score ASCR exceeds the threshold value TH2, that is, whether or not ASCR (i)> TH2 (S28).

  If it is determined that ASCR (i)> TH2, the control unit 7 determines that the input image data relates to the registered image, and performs subsequent processing on the input image data (processing according to the processing mode). Is sent to the main control unit of the digital color multifunction peripheral 1 (S29), and a notification signal indicating that processing for the registered image is requested is output from the cumulative score comparison unit 36 to the communication device 5 ( S31). The communication device 5 notifies a preset notification destination (for example, an administrator) that processing for a registered image is requested. At this time, together with information indicating that processing for the registered image is requested, the ID of the digital color multifunction device 1, the installation location and department of the digital color multifunction device 1, the index of the registered image, the document ID of the input image data, the processing Processed until the time when the request was input, date, day of the week, user ID of the user who input the request, details of the request (processing mode, number of processed items, etc.), accumulated score ASCR (i) exceeds the threshold TH2. Various information such as the document ID of the document may be notified. FIG. 16 shows an example of information notified to the administrator together with information indicating that processing for a registered image is requested.

  The notification to the notification destination may be made directly from the communication device 5 provided in the digital color multifunction peripheral 1 to the transmission destination, or a server (not shown) connected to the digital color multifunction peripheral 1 via a network. ).

  For example, the control unit 7 is not limited to the configuration for notifying the transmission destination, but the control unit 7 can store the above various information in the administrator folder of another device connected to the digital color multifunction peripheral 1 via the memory 8 or the network. The information may be stored and the information may be taken out by the administrator accessing the administrator folder as necessary.

  On the other hand, if it is determined in S28 that ASCR (i) ≦ TH2, the control unit 7 determines that the input image data is not related to the registered image, and processes the i-th page (or block) in the input image data. Is sent to the main control unit of the digital color multifunction peripheral 1 (S32). Upon receiving this signal, the main control unit of the digital color multifunction peripheral 1 causes the i-th page (or block) in the input image data to execute processing according to the processing content instructed by the instruction input. When it is determined that ASCR (i)> TH2, the control unit 7 sends a signal to that effect to the main control unit, and when it is determined that ASCR (i) ≦ TH2, the main control unit The signal may not be sent.

  FIG. 17 is a graph showing an example of the number of documents (number of pages of input image data) and an accumulated score. In the case of the input image data A, processing is permitted for up to the fourth document, and processing is prohibited for the fifth document. In the case of input image data B, processing is permitted for up to the fifth original.

  After the process of S31, the control unit 7 determines whether all the pages (or blocks) in the input image data have been processed (S32). If an unprocessed page (or block) remains, the control unit 7 performs the processing from S3 on on the next i + 1-th page (or block) (S33). On the other hand, if it is determined in S32 that all pages (or blocks) have been processed, the process ends.

  As described above, the digital color multifunction peripheral 1 according to the present embodiment includes the coefficient α (m) set for each user, the coefficient β (n) set for each time zone, and the coefficient set for each processing mode. A coefficient δ (q) set according to whether γ (p) or an image of a specific hue is included is stored in the memory 8 in advance. Then, the score calculation unit 35 uses the similarity MCH (i) of the registered images that have obtained the maximum number of votes in the voting process in the voting processing unit 33, and the coefficients α (m), β (n), γ (p). , Δ (q) and a score value SCR (i) are calculated. Then, based on the score value SCR (i), the similarity between the input image data and the registered image is determined.

  As a result, a security level (coefficient) is set in accordance with each user, each time zone, each processing mode, and whether or not an image of a specific hue is included, and processing for input image data is instructed. The similarity can be determined according to whether the user, the time zone, the processing mode, and an image of a specific hue are included. Therefore, it is possible to perform determination processing by setting whether security or workability is to be emphasized depending on whether each user, each time zone, each processing mode, and whether an image of a specific hue is included. it can.

  Further, in the present embodiment, it is determined whether or not the processing content needs to be limited by comparing the accumulated score ASCR (i) obtained by sequentially accumulating the score values for each page (or each block) of the input image data with the threshold value TH2. To do.

  In this way, by determining whether or not the processing content needs to be restricted using the accumulated score, it is possible to absorb a variation factor in the similarity calculation result caused by the document reading conditions, reading accuracy, and the like. For example, even if the similarity is calculated for the input image data of the same document, the similarity varies depending on the conditions under which the document is read, etc., but by accumulating the similarities and evaluating these factors, these variations are absorbed. The degree can be accurately evaluated. In addition, even when different document images are successively processed instead of the same document image, the similarity can be appropriately evaluated.

  Note that the cumulative score ASCR (i) and the threshold value TH2 are not limited to each other, and the score value SCR (i) for each page (or each block) of the input image data and the threshold value TH3 stored in the memory 8 in advance. May be performed for each page (or each block) of the input image data.

  In this embodiment, when the accumulated score ASCR (i) exceeds the threshold value TH2, the processing for the input image data is restricted and the notification signal is output. However, the present invention is not limited to this.

  For example, instead of issuing a notification signal when the cumulative score ASCR exceeds the threshold value TH2, a flag F indicating whether or not the cumulative score ASCR exceeds the threshold value TH2 (when TH1 exceeds TH1, "1", when TH2 or less "0") is stored in the memory 8, and when the processing for all input image data is completed, it is determined whether or not the flag is "F = 1", and an input is made according to the determination result. It may be determined whether or not processing of image data is prohibited or restricted, and / or whether or not notification to the administrator is necessary. FIG. 18 is a flowchart showing the flow of processing in this case.

  First, when receiving an instruction input from the user via the operation panel 6 or the communication device 5, the control unit 7 initializes the score value SCR and the flag F stored in the memory 8 (SCR (1) = 0, F = 0) (S41).

  Next, the control unit 7 acquires input image data (S42), controls each part of the document collation processing unit 13, and performs feature point calculation processing (S43), feature amount calculation processing (S44), and voting processing (S45). Then, a score calculation process (S46) and a cumulative score calculation process (S47) are performed. Further, the control unit 7 determines whether or not the cumulative score ASCR exceeds the threshold value TH2, that is, whether or not ASCR (i)> TH2 (S48).

  When determining that ASCR (i)> TH2, the control unit 7 stores the flag F in the memory 8 with F = 1 (S49), and proceeds to the process of S50.

  On the other hand, when determining that ASCR (i) ≦ TH2, the control unit 7 proceeds to the process of S50 without changing the flag F (F = 0).

  In the present embodiment, until the determination process for all pages in the input image data is completed, the determination on whether to permit (inhibit or restrict) the process on the input image data (processing according to the processing mode) is suspended. To do. However, the present invention is not limited to this, and the processing (processing according to the processing mode) for the i-th page (or block) in the input image data may be permitted after the processing of S48.

  Next, the control unit 7 determines whether or not the processing of S42 to S49 has been performed on all pages (or blocks) in the input image data (S50). When an unprocessed page (or block) remains, the control unit 7 performs the processing from S42 on the next i + 1th page (or block) (S51).

  On the other hand, when it is determined in S50 that all pages (or blocks) have been processed, the control unit 7 determines whether or not the flag F stored in the memory 8 is F = 1 (S52). If the flag F is not 1 (when F = 0), the control unit 7 sends a signal permitting processing (processing according to the processing mode) to the input image data to the main control unit (S53). Exit.

  On the other hand, when the flag F = 1, the control unit 7 sends a signal for prohibiting or restricting the processing (processing according to the processing mode) to the input image data to the main control unit (S54), and the processing for the registered image is performed. A notification signal indicating that the request has been made is output from the accumulated score comparison unit 36 to the communication device 5 (S55), and the process is terminated.

  The communication device 5 notifies a preset notification destination (for example, an administrator) that processing for a registered image is requested. At this time, together with information indicating that processing for the registered image is requested, the ID of the digital color multifunction device 1, the installation location and department of the digital color multifunction device 1, the ID of the registered image, the document ID, the input image data, the processing The user ID of the user who input the request, the date, day of the week, and time when the processing request is input, the content of the processing request (number of processing, processing mode, etc.), and the accumulated score ASCR (i) is processed until it exceeds the threshold value TH2. Various information such as the document ID of the document may be notified. Instead of notifying the input image original ID and input image data, the input image original ID and the registered image corresponding to the input image may be notified, or only the registered image corresponding to the input image is notified. You may make it do. The notification to the notification destination may be made directly from the communication device 5 provided in the digital color multifunction peripheral 1 to the notification destination, or a server (not shown) connected to the digital color multifunction peripheral 1 via a network. ).

  For example, the control unit 7 stores the above-described various information in the administrator folder of the apparatus connected to the memory 8 or the digital color multifunction peripheral 1 via the network. The administrator may retrieve the information by accessing the administrator folder as necessary.

  The processing may also be stopped when the number of originals exceeds a predetermined number (for example, 50) (when the number of pages or the amount of data of input image data exceeds a predetermined amount).

  Further, the values of the coefficients α (m), β (n), γ (p), δ (q) stored in the administrator folder of the memory 8 are arbitrarily set by the administrator accessing the administrator folder. It may be possible to add or change.

  Further, for example, when the cumulative score ASCR (i) exceeds the threshold value TH2, the control unit 7 determines the ID of the digital color multifunction peripheral 1, the installation location and department of the digital color multifunction peripheral 1, the ID of the registered image, and the document. ID, input image data, user ID of user who input processing request, date, day of week, time when processing request is input, processing request contents (number of processing, processing mode, etc.), cumulative score ASCR (i) is threshold TH2. It is possible to store various information such as the manuscript of the manuscript that has been processed up to above in the administrator folder of the memory 8.

  As a result, the administrator can confirm the suitability of this determination for the input image data determined to be data related to the registered image as a result of the cumulative score ASCR (i) exceeding the threshold value TH2. If this determination is incorrect, it is possible to take measures such as changing the coefficients α (m), β (n), γ (p), δ (q) or the threshold value TH2.

  If the administrator determines that the above determination is incorrect, the control unit 7 uses the coefficients α (m), β (n), γ (p), δ ( q) may be changed. For example, when the administrator accesses the various types of information stored in the administrator folder, the control unit 7 instructs the administrator to input an indication that there is an error on the display unit of the device used for the access. Is displayed. Then, when this button is selected, the control unit 7 determines that the above determination is an error, and any one or more of coefficients α (m), β (n), γ (p), and δ (q). May be changed (for example, 1% lower). At this time, only the coefficient instructed by the administrator may be changed.

Further, a combination of the coefficients when the administrator determines that the determination is an error may be stored, and a coefficient change rate may be set according to the number of times the administrator determines that the determination is an error. For example, when s (s is an integer of 1 or more) is determined to be an error, and K is a constant (for example, 2), the change rate may be set to K ⁿ %. That is, any one or more of the coefficients α (m), β (n), γ (p), and δ (q) may be multiplied by K ⁿ / 100.

  Further, in the present embodiment, the case where the score value SCR is calculated using the coefficients α, β, γ, and δ according to the user, the time zone, and the processing mode among the incidental information of the input image data has been described. It is not limited to. For example, instead of some or all of these coefficients, or in addition to these coefficients, the score is obtained by using coefficients for the number of pages or the amount of input image data, the destination of input image data, or a combination thereof. The value SCR may be calculated.

  In each of the above embodiments, the document matching processing unit 13 calculates the center of gravity of the connected portion of each pixel in the input image data as a feature point, and determines the similarity based on the positional relationship between the feature points. Although the case has been described, the method of determining the similarity is not limited to this.

  For example, the similarity may be determined using the method described in Patent Document 1. In this method, a ruled line image is first raster-scanned by contour extraction processing to detect its tracking start point, and then a closed curve formed by a graphic boundary from the tracking start point in a clockwise or counterclockwise direction is tracked. . The contour information extracted by such closed curve tracking is stored as a coordinate point sequence. After that, based on the extracted outline data, feature points such as intersections and corner points of the image are detected, and a frame is extracted from the combination of point sequences. Then, a circumscribed figure of the input frame information is calculated.

Next, center coordinate data of each frame data is calculated. For example, when the frame coordinates are (x0, y0), (x1, y1), (x2, y2), (x3, y3) from the lower left corner, the intersection of the diagonal lines is (cx, cy). Next, the difference between the position of the upper left coordinate on the registered fixed format and the position of the upper left coordinate on the input image is set to dx, dy, and the center position of the frame of the registered fixed format or the frame of the ruled line image is corrected. Next, the frame data is associated with each other. For example, tcx and tcy are the center coordinates of the frame data on the registered fixed format, and the distance D when the frame data on the ruled line image is icx and icy is D = (icx−tcx) ² + (icy−). tcy) ² . The similarity is voted when there is a frame corresponding to the frame on the registered format (D <dth, dth is a threshold of distance), and the number of frames is divided by n when all the frames have been voted on the registered format. That is, the similarity is obtained by similarity = number of corresponding frames / number of frames on the registered form.

  Further, the similarity may be determined using a collation method using a color distribution described in Patent Document 2. In this method, the image data in the RGB space for the registered image is stored in the determination ROM, the number of pixels in the area recognized to match the registered image in the input image data is counted, and the input image that matches the registered image is counted. A volume Tjd in the RGB space of the data is calculated. Then, when the number of pixels in the area recognized as a registered image is equal to or greater than a constant k, the similarity R is calculated by the following equation (4), assuming that there is a possibility of a registered document (for example, a bill document). Note that “Torg” is the volume of registered image data.

R = Tjd / Torg (4)
When the similarity R is not less than the color matching rate βm in the color space, it is determined that the registered image is included. By repeating this process for each registered specific image, a process for determining similarity to each registered image is performed.

  Alternatively, the similarity of the input image data to the registered image may be determined by extracting the keyword from the input image data by OCR or the like and performing matching with the keyword included in the registered image. In addition, feature quantities other than the above-described methods are detected from input image data, the similarity is calculated by comparing with the feature quantity of the registered image, and the similarity is calculated by comparing the calculated similarity with a predetermined threshold value. The presence or absence of sex may be determined.

  In each of the above embodiments, the case where the present invention is applied to the digital color multifunction peripheral 1 has been described. However, the application target of the present invention is not limited to this. For example, the present invention may be applied to a monochrome multifunction device. Further, the present invention is not limited to a multifunction machine, and may be applied to, for example, a single facsimile communication apparatus, a copying machine, an image reading apparatus, or the like.

FIG. 19 is a block diagram showing a configuration example when the present invention is applied to a flatbed scanner (image reading apparatus, image processing apparatus) 1 ′. As shown in FIG. 19, the color image processing apparatus 3 ′ / D conversion unit 11, shading correction unit 12, document collation processing unit 13, control unit 7 (not shown in FIG. 19), and memory 8 (not shown in FIG. 19). An input device 2 is connected to constitute an image reading device 1 ′ as a whole. The functions of the A / D conversion unit 11, the shading correction unit 12, the document collation processing unit 13, the control unit 7, and the memory 8 in the color image input device (image reading unit) 2 are substantially the same as those of the digital color multifunction peripheral 1 described above. Since it is the same, description is abbreviate | omitted here.

[Embodiment 3]
Still another embodiment of the present invention will be described. For convenience of explanation, members having the same functions as those in the above-described embodiment are denoted by the same reference numerals and description thereof is omitted.

  FIG. 30 is a block diagram illustrating a schematic configuration of the document matching processing unit 13 provided in the digital color multifunction peripheral 1 according to the present embodiment. The document collation processing unit 13 is provided in the digital color multifunction peripheral 1 in place of the document collation processing unit 13 in the first or second embodiment.

  As shown in FIG. 30, the document collation processing unit 13 includes a feature point calculation unit 31, a feature amount calculation unit 32, a voting processing unit 33, a similarity determination processing unit 34, a score calculation unit 35c, a score comparison unit 36c, and a registration. A processing unit 37 is provided. As the feature point calculation unit 31, the feature amount calculation unit 32, the voting processing unit 33, the similarity determination processing unit 34, and the registration processing unit 37, the same ones as in the first and second embodiments can be used.

  The score calculation unit 35 includes each item of the incidental information of the input image data (for example, the user ID of the user who has input the processing request for the input image data, the date, day of the week, the time when the processing request is input, the input image Number of pages of data (number of sheets) or amount of data, details of processing request (for example, processing mode (copying, printing, transmission, editing, etc.), number of processing sheets (number of copies, number of printed sheets), destination of input image data, input image data The evaluation value for each of these items is calculated according to the content of a predetermined hue included therein.

  Specifically, the memory (evaluation value storage unit) 8 has an evaluation value x (i) set for each item of the incidental information of the input image data and a reference evaluation set for each item. The value xref (i) is stored. Then, the score calculation unit 35 extracts the incidental information of the input image data, and calculates an evaluation value for each item based on the contents of each item of the extracted incidental information and the correspondence relationship stored in the memory 8. To do.

  FIG. 31 is an explanatory diagram showing an example of incidental information, evaluation values, and reference evaluation values of input image data stored in the memory 8. In the example shown in this figure, each item of user, time zone, and processing mode is set as incidental information of the input image data, and an evaluation value x (i) corresponding to the content of these items is set in advance. Has been. For example, users are classified into groups A to D, and evaluation values a1 to a4 are set for each loop. The evaluation values a1 to a4 are set in the range of 1 to 10, for example. In addition, a reference evaluation value xref (i) is set for each item. Note that the reference evaluation value can be accessed only by an administrator folder (only a person who has been previously granted access authority) provided in an external device that is communicably connected to the memory 8 or the digital color multifunction peripheral 1 via a network. Folder).

  The reference evaluation value for each item is set, for example, for each user group using the digital color multifunction peripheral 1 (for example, a user group corresponding to the user's department or the installation location of the digital color multifunction peripheral 1). Also good. In this embodiment, as will be described later, the value of the reference evaluation value is corrected in accordance with the past processing performance (for example, the statistical average value of the evaluation values for the above items for each user group). Yes. For this reason, the reference evaluation value is set to a default value in the initial state, but this default value may also be set for each user group.

  Then, the score calculation unit 35 compares the evaluation value calculated for each item of the incidental information of the input image data with the reference evaluation value for each item, and calculates the score value SCRst according to the comparison result. In the present embodiment, the score value SCRst is calculated based on the following formula (5).

Note that the method of calculating the score value SCRst is not limited to this. For example, the evaluation value x (i
) And the reference evaluation value xref (i) may be the sum of absolute values of the difference as the score value SCRst.

  FIG. 32A shows an example of the evaluation value of each item calculated based on the incidental information of the input image data, and FIG. 32B shows an example of the reference evaluation value set for each item. Yes.

  The score comparison unit 36c compares the score value SCRst calculated by the score calculation unit 35 with the threshold value (third threshold value) TH3 stored in advance in the memory 8 or the administrator folder, and compares the comparison result with the control unit 7. To communicate.

  When the similarity determination processing unit 34 determines that there is “similarity”, the control unit 7 causes the score calculation unit 35 c and the score comparison unit 36 c to execute the above processing. When SCRst ≦ TH3, it is determined that the input image data is not related to the registered image (no similarity), and the execution of the process on the input image data is permitted.

  On the other hand, based on the comparison result of the score comparison unit 36c, the control unit 7 determines that the input image data is related to the registered image (there is similarity) when SCRst> TH3, and processes the input image data. A signal for prohibiting or restricting execution of (processing according to the processing mode) is sent to the main control unit, and a notification signal indicating that processing for a registered image is requested by controlling the communication device 5 is transmitted in a predetermined manner. Send to the destination (for example, administrator).

  In the present embodiment, together with a notification signal indicating that processing for a registered image has been requested, the ID of the digital color multifunction device 1, the installation location and department of the digital color multifunction device 1, the index of the registered image (or the registered image) ), The document ID of the input image data, the time, date, day of the week when the processing request was input, the user ID of the user who input the processing request, and the contents of the processing request (processing mode, number of processed sheets, etc.) . Alternatively, the above-described various types of information are stored in an administrator folder of another device that is communicably connected to the digital color multifunction peripheral 1 via a memory or a network, and the administrator accesses the administrator folder as necessary. You may make it take out such information.

  As a result, the administrator determines whether the determination result in the digital color multifunction peripheral 1 is incorrect based on the various information transmitted from the digital color multifunction peripheral 1. It is possible to change (update) the above-mentioned reference evaluation values for the items that are considered to be factors of the above.

  In addition, although the change method of a reference | standard evaluation value is not specifically limited, In this embodiment, it corrects based on following formula (6).

xref ′ (i) = (M × xref (i) + x (i)) / (M + 1) (6)
Here, xref (i) is a set reference evaluation value (reference evaluation value before change), x (i) is an evaluation value calculated from input image data, and xref ′ (i) is after change. The standard evaluation value. M is a constant and is set to 100, for example.

  Thus, when the score comparison result is incorrect, by changing the reference evaluation value, the reference evaluation value can be set based on past processing results (for example, statistical data for each user group), It is possible to more appropriately determine whether or not to allow execution of processing on input image data.

  Next, similarity determination processing in the digital color multifunction peripheral 1 according to the present embodiment will be described with reference to the flowchart shown in FIG.

  First, when receiving an instruction input from the user via the operation panel 6 or the communication device 5, the control unit 7 initializes the score value SCRst stored in the memory 8 (SCRst = 0) (S141).

  Next, the control unit 7 acquires input image data obtained by reading a document image (S142), controls each part of the document collation processing unit 13, and performs feature point calculation processing (S143), feature amount calculation processing (S144), A voting process (S145) is performed. Then, it is determined whether or not the processing of S142 to S145 has been completed for all the document images. If not, the processing of S142 to S145 is repeated for the remaining document images.

  On the other hand, when the processing of S142 to S145 is completed for all the document images, the similarity determination processing unit 34 is caused to perform similarity determination processing based on the voting process result. If it is determined that there is no similarity, the process for the input image data is permitted (S148), and the process ends.

  On the other hand, when it is determined that there is similarity, the control unit 7 causes the score calculation unit 35c to calculate the score value SCRst (S149), and causes the score comparison unit 36c to perform comparison processing between the score value SCRst and the threshold value TH3 ( S150).

  If SCRst ≦ TH3, execution of processing (processing according to the processing mode) for the input image data is permitted (S148), and the processing is terminated.

  On the other hand, if SCRst> TH3, the execution of the processing on the input image data (processing according to the processing mode) is prohibited or restricted (S151), and a notification signal indicating that the processing on the registered image is requested, And the ID of the digital color multifunction peripheral 1, the installation location and department of the digital color multifunction peripheral 1, the index (or registered image) of the registered image, the document ID of the input image data, the time, date, day of the week when the processing request is input, Various information such as the user ID of the user who has input the processing request and the details of the processing request (processing mode, number of processed sheets, etc.) are transmitted to a predetermined transmission destination (for example, an administrator) (S152), and the processing is terminated.

  When the administrator receives the notification signal (S161), the administrator checks the input image data based on the various information (S162), and the input image data should actually prohibit or limit the execution of the process. It is verified whether it is related to the registered image or not, and whether or not a measure for prohibiting or restricting execution of processing on the input image data is appropriate (S163). If it is determined to be appropriate, the process is terminated as it is.

  On the other hand, when it is determined that it is not appropriate, that is, when it is determined that it is a misclassification, the reference evaluation value for the item considered to be a cause of the misclassification is appropriately changed (S164), and the process is terminated. Specifically, when the administrator determines that the determination is an erroneous determination, the administrator notifies the digital color multifunction peripheral 1 of an item considered to be a cause of the erroneous determination. When this notification is received via the communication device (adequacy input unit) 5 or the operation panel (adequacy input unit) 6, the control unit 7 changes the reference evaluation value of the notified item based on, for example, the above formula (6). To do.

[Embodiment 4]
Still another embodiment of the present invention will be described. For convenience of explanation, members having the same functions as those in the above-described embodiment are denoted by the same reference numerals, and description thereof is omitted.

  FIG. 20 is an explanatory diagram showing a schematic configuration of the image processing system 100 according to the present embodiment. As shown in this figure, an image processing system 100 includes a server device 50, multifunction peripherals (MFPs) A, B,..., Printers A, B,. A, B,..., Digital cameras A, B,..., Scanners A, B,.

The server device 50 executes part or all of the functions of the control unit 7 and the document collation processing unit 13 in the first to third embodiments. That is, the server device 50 receives the input image data or the feature amount of the input image data from another device (for example, a multifunction device, a printer, a facsimile, a computer, a digital camera, a scanner, etc.) connected via the network, A similarity determination process is performed based on the received information.

  Here, an example of processing in the image processing system 100 will be described. Here, as shown in FIG. 20, an example in which the digital color multifunction peripheral 1 (color image processing device 3) provided in the image processing system 100 and the server device 50 cooperate to perform processing will be described.

  As shown in FIG. 21, the color image processing apparatus 3 of the digital color multifunction peripheral 1 controls the operation of the document matching processing unit 13a including the feature point calculating unit 31 and the feature amount calculating unit 32 and the document matching processing unit 13a. Control unit 7a, a memory 8a for storing information necessary for processing of the document collation processing unit 13a, and a communication device 5 for communicating with an external device. The server device 50 also includes a communication device 51 that communicates with an external device, a document matching processing unit 13b that includes a voting processing unit 33, a score calculation unit 35, a cumulative score comparison unit 36, and a registration processing unit 37. And a control unit 7b for controlling the document collation processing unit 13b and a memory 8b for storing information necessary for the processing of the document collation processing unit 13b.

  FIG. 22 is a flowchart showing the flow of processing in the image processing system 100.

  When acquiring the input image data (S61), the control unit 7a of the digital color multifunction peripheral 1 controls the feature point calculation unit 31 and the feature amount calculation unit 32 to perform feature point calculation processing (S62) and feature amount calculation processing (S63). ).

  Next, the control unit 7a transmits the feature amount (hash value) calculated by the feature amount calculation unit 32 to the server device 50 via the communication device 5 (S64). At this time, the document ID, input image data, and the like may be transmitted together with the feature amount as necessary.

  In the server device 50, when the communication device 51 receives the feature amount (S71), the control unit 7b controls the voting processing unit 33, and the feature amount (hash value) received by the communication device 51 is stored in the memory 8b. A voting process is performed based on the hash table (S72). Moreover, the control part 7b controls the score calculation part 35 and the accumulation score comparison part 36, and performs a similarity determination process (S73). Here, the similarity determination process similar to that of the second embodiment is performed. However, the present invention is not limited to this, and the similarity determination process may be performed by the method described in the first or third embodiment, for example.

  Then, the control unit 7b transmits a determination signal indicating the determination result (similar / not similar) of the similarity determination process to the digital color multifunction peripheral 1 via the communication device 51 (S74).

  When the communication device 5 receives the determination signal (S65), the control unit 7a of the digital color multifunction peripheral 1 determines whether there is similarity (S66).

  If it is determined that there is no similarity in S66, the control unit 7a determines whether or not the processing for all input image data has been completed (S67). If unprocessed input image data remains, the control unit 7a The processing from S61 is performed on the data, and if the processing has been completed for all input image data, the operation is terminated.

  On the other hand, if it is determined in S66 that there is similarity, the control unit 7a displays the log (operation record information; for example, the document ID of the input image, the user ID of the user who input the processing request, the date when the processing request is input, and the day of the week. , Time, contents of processing request, etc.) are generated and the input image data and log are transmitted from the communication device 5 to the server device 50 (S68), and the processing (for example, copy, print, transmission) for the input image data is performed. , Editing, processing, saving, etc.) are prohibited (S69), and the operation is terminated.

  When the communication device 51 receives the input image data and the log from the digital color multifunction peripheral 1, the control unit 7b of the server device 50 stores these pieces of information in the memory 8b (S75) and ends the process.

  In the above description, the log is transmitted from the communication device 5 to the server device 50 when it is determined that there is a similarity in S66. However, the present invention is not limited to this. When transmitting the feature amount, the log may be transmitted together with the feature amount. In addition to the log, the document ID of the input image, the input image data (or compressed image data obtained by compressing the input image data or image data reduced in resolution), the index of the registered image, and the like may be transmitted. Also, instead of input image data (or compressed image data obtained by compressing input image data or image data reduced in resolution), a registered image corresponding to the input image (or compressed image data obtained by compressing this registered image or reduced resolution) Image data) may be notified. In this case, the document ID of the input image and the registered image (or compressed image data obtained by compressing the registered image or image data reduced in resolution) may be notified, and the registered image (or the registered image is compressed). Only compressed image data or image data with reduced resolution) may be notified.

  FIG. 23 is a flowchart showing the flow of processing in this case. When the control unit 7a of the digital color multifunction peripheral 1 acquires the input image data (S81), the control unit 7a controls the feature point calculation unit 31 and the feature amount calculation unit 32 to perform feature point calculation processing (S82) and feature amount calculation processing (S83). ).

  Next, the control unit 7a performs log (operation recording) based on, for example, the document ID of the input image, the user ID of the user who inputs the processing request, the date, day of the week, the time when the processing request is input, and the content of the processing request. Information) is generated, and the generated log and the feature amount (hash value) calculated by the feature amount calculation unit 32 are transmitted to the server device 50 via the communication device 5 (S64). The log is not particularly limited as long as it is information related to operation recording. For example, a log including any one or more of a document ID, a user ID, a processing mode, a number of processed sheets, and a time can be used. .

  In the server device 50, when the communication device 51 receives the feature value and the log (S91), the control unit 7b controls the voting processing unit 33, and the feature value (hash value) received by the communication device 51 is stored in the memory 8b. The voting process is performed based on the hash table (S92). Moreover, the control part 7b controls the score calculation part 35 and the accumulation score comparison part 36, and performs a similarity determination process (S93).

  Then, the control unit 7b transmits a determination signal indicating the determination result (similar / not similar) of the similarity determination process to the digital color multifunction peripheral 1 via the communication device 51 (S74).

  Further, the control unit 7b determines whether or not the result of the similarity determination process is similar (S95). If the result is similar, the log is stored in the memory 8b (S96), and the process ends. On the other hand, if there is no similarity, the process ends without recording a log.

  On the other hand, when the communication device 5 receives the determination signal (S85), the control unit 7a of the digital color multifunction peripheral 1 determines whether there is similarity based on the determination signal (S86). If it is determined that there is no similarity, the controller 7a determines whether or not the processing for all input image data has been completed (S87). On the other hand, the processing from S81 is performed, and when the processing is completed for all input image data, the operation is terminated.

  On the other hand, if it is determined in S86 that there is similarity, the control unit 7a prohibits processing (for example, copying, printing, transmission, editing, processing, saving, etc.) on the input image data (S88), and ends the operation. If it is determined that there is similarity in S86, the control unit 7a may transmit the input image data to the server device 50, and the server device 50 may store the input image data in the memory 8b together with the log. In the processing example shown in FIG. 23, the processing of S94, S85, S86, and S88 may be omitted, and the similarity determination result may not be transmitted from the server device 50 to the digital color multifunction peripheral 1.

  In the example of FIG. 21, all of the feature amount calculation unit 32 (feature point extraction unit 32a, invariant calculation unit 32b, hash value calculation unit 32c) is provided in the digital color multifunction peripheral 1, and the digital color multifunction peripheral is provided. Although the hash value is transmitted from 1 to the server device 50, the present invention is not limited to this.

  For example, as shown in FIG. 24, the feature point extraction unit 32a and the invariant calculation unit 32b may be provided in the digital color multifunction peripheral 1, while the hash value calculation unit 32c may be provided in the server device 50.

  FIG. 25 is a flowchart showing the flow of similarity determination processing in this case. When acquiring the input image data (S101), the control unit 7a of the digital color multifunction peripheral 1 controls the feature point calculation unit 31 to perform the feature point calculation process (S102), and the feature point extraction unit 32a and the invariant calculation. The unit 32b is controlled to calculate the invariant H′ij (S103).

  Next, the control unit 7a performs log (operation recording) based on, for example, the document ID of the input image, the user ID of the user who inputs the processing request, the date, day of the week, the time when the processing request is input, and the content of the processing request. Information) is generated, and the generated log and the invariant (feature amount) calculated by the invariant calculating unit 32b are transmitted to the server device 50 via the communication device 5 (S104).

  In the server device 50, when the communication device 51 receives the feature value and the log (S110), the control unit 7b controls the hash value calculation unit 32c to calculate the hash value (S111).

  Next, the control unit 7b controls the voting processing unit 33 to perform voting processing based on the hash value calculated by the hash value calculating unit 32c and the hash table stored in the memory 8b (S112). Moreover, the control part 7b controls the score calculation part 35 and the accumulation score comparison part 36, and performs a similarity determination process (S113).

  Then, the control unit 7b transmits a determination signal indicating the determination result (similar / not similar) of the similarity determination process to the digital color multifunction peripheral 1 via the communication device 51 (S114).

  In addition, the control unit 7b determines whether or not the result of the similarity determination process is similar (S115), and if the result is similar, stores the log in the memory 8b (S116) and ends the process. On the other hand, if there is no similarity, the process ends without recording a log.

  On the other hand, when the communication device 5 receives the determination signal (S105), the control unit 7a of the digital color multifunction peripheral 1 determines whether there is similarity based on the determination signal (S106). If it is determined that there is no similarity, the control unit 7a determines whether or not the processing for all input image data has been completed (S107). On the other hand, the processing from S101 is performed, and if the processing has been completed for all input image data, the operation is terminated.

  On the other hand, if it is determined in S106 that there is similarity, the control unit 7a prohibits processing (for example, copying, printing, transmission, editing, processing, saving, etc.) on the input image data (S108), and ends the operation. If it is determined that there is similarity in S106, the control unit 7a may transmit the input image data to the server device 50, and the server device 50 may store the input image data in the memory 8b together with the log. Since the hash value has a smaller data capacity than the invariant, it is preferable that the hash value is transmitted from the digital color multifunction peripheral 1 to the server device in order to improve the efficiency of communication processing. On the other hand, in order to simplify the configuration of the digital color multifunction peripheral 1, it is preferable to provide the hash value calculation unit 32c in the server device 50.

  Each unit of the feature amount calculation unit 32 is provided in the server device 50, and data related to the feature points calculated by the feature point calculation unit 31 is transmitted from the digital color multifunction peripheral 1 to the server device 50, and is provided in the server device 50. The feature amount calculation unit 32 may calculate a hash value based on the hash table stored in the memory 8b and the received feature point data. Further, the feature point calculation unit 31 and the feature amount calculation unit 32 are provided in the server device 50, and input image data is transmitted from the digital color multifunction peripheral 1 to the server device 50 to calculate the feature points provided in the server device 50. The unit 31 and the feature amount calculation unit 32 may calculate the hash value based on the input image data received from the server device 50 and the hash table stored in the memory 8b.

  Further, in the above description, an example in which the similarity determination process is performed has been described. However, in the case of performing the registration process, the registration processing unit 37 provided in the server device 50 has received from the digital color multifunction peripheral 1. The document ID and the hash value (or the hash value calculated by the hash value calculation unit 32c provided in the server device 50) may be registered in a hash table provided in the memory 8b. Whether the similarity determination process or the registration process is performed is designated by the user of the digital color multifunction peripheral 1 via the operation panel 6, and a signal indicating which process is performed is transmitted to the server device 50. Alternatively, the registration process may be performed for the input image that the server device 50 has determined as not similar as a result of the similarity determination process.

  When the server device 50 includes the hash value calculation unit 32c, the hash value is calculated by using a different method (using another hash function) from the method of calculating the hash value stored in the hash table. The hash table may be updated using the value. As a result, for example, an appropriate hash value referring to a feature value (invariant) can be registered (updated) in the hash table in accordance with the type of document image, and the voting process can be performed using the hash value. (Similarity determination accuracy) can be improved.

  In addition to the feature amount (hash value or invariant), for example, character information extracted from the input image data, compressed image data obtained by compressing the input image data, and the like may be transmitted to the server device 50. FIG. 26 is a block diagram illustrating a configuration example of the image processing system 100 in this case.

  In the image processing system 100 shown in this figure, the digital color multifunction peripheral 1 includes an OCR processing unit 61 and an image compression unit 62 in addition to the configuration shown in FIG.

An OCR (Optical Character Recognition) processing unit 61 extracts character information (text data) from input image data. As the OCR processing unit 61, those similar to various conventionally known OCR devices can be used.

  The image compression unit 62 compresses input image data to generate compressed image data. The compression method is not particularly limited, and various conventionally known methods can be used. For example, data in a high compression format such as a high compression PDF, or data in a compression format such as TIFF or JPEG may be generated.

  In addition, an input image data is provided with a region separation unit that separates input image data into a character region including a character and / or a line drawing and a region other than the character region. The input image data of the area and the input image data of the area other than the character area may be compressed by different methods. For example, the compressed image data may be created using a method described in Japanese Patent No. 2611012. In other words, the input image data is divided into character areas (characters, line drawings) and color image areas (full color, halftone images, etc.), and the color image area is cut out from the character area. The white area is filled with white information, and the whole is encoded with MMR, etc., and the color image area is filled with the average image data around the character area so that a large density change does not occur. Encoding may be performed by (adaptive discrete cosine transform encoding) or the like. By using data in a high compression format such as high compression PDF, the capacity of image data to be transferred can be reduced, and image data with good legibility of characters can be transmitted to the server device 50. Therefore, the server device 50 can store image data with good character readability as an image log.

  FIG. 27 is a flowchart showing the flow of similarity determination processing in the image processing system 100 shown in FIG. When acquiring the input image data (S121), the control unit 7a of the digital color multifunction peripheral 1 controls the feature point calculation unit 31 to perform a feature point calculation process (S122), and controls the feature amount calculation unit 32. A feature amount (hash value) is calculated (S123). Further, the control unit 7a controls the OCR processing unit 61 to extract character information from the input image data (S124). Further, the control unit 7b controls the image compression unit 62 to compress the input image data and generate compressed image data (S125). Further, the control unit 7b logs (operation record information) based on, for example, the document ID of the input image, the user ID of the user who has input the processing request, the date, day of the week, the time when the processing request is input, and the content of the processing request. Is generated (S126). Note that the feature amount calculation process, the character information extraction process, and the compressed image data generation process may be performed in parallel.

  Next, the control unit 7b transmits the feature amount, character information, compressed image data, and log from the communication device 5 to the server device 50 (S127). Then, the control unit 7a determines whether or not the processing for all input image data has been completed (S128). If unprocessed input image data remains, the processing from S121 is performed on the data. If the processing has been completed for all input image data, the operation is terminated.

  In the server device 50, when the communication device 51 receives the feature amount, character information, compressed image data, and log (S131), the control unit 7b controls the voting processing unit 33 to store the received feature amount and the memory 8b. A voting process is performed based on the stored hash table (S132). Moreover, the control part 7b controls the score calculation part 35 and the accumulation score comparison part 36, and performs a similarity determination process (S133).

  Then, the control unit 7b determines whether or not the result of the similarity determination process is similar (S134). If the result is similar, the log, character information, and compressed image data are stored in the memory 8b (S116). ), The process is terminated. On the other hand, if there is no similarity, the process ends without recording a log or the like.

  Thus, by generating compressed image data obtained by compressing the character information extracted from the input image data and the input image data, the character information and the compressed image data are stored in the memory 8b when it is determined that there is similarity. For example, when a plurality of document images having a high degree of similarity are extracted, the administrator can perform a search using character information, or can determine whether the determination is appropriate by referring to the character information or compressed image data. .

  In the example of FIG. 26, the configuration including the OCR processing unit 61 and the image compression unit 62 has been described. However, the configuration is not limited thereto, and only one of the configurations may be provided.

  In this embodiment, the case where the image processing system 100 includes the digital color multifunction peripheral 1 and the server device 50 has been described. However, the configuration of the image processing system 100 is not limited to this, and for example, the server device 50 and The image forming apparatus may include any one or more of a multifunction machine, a printer (image forming apparatus), a facsimile machine, a computer, a digital camera (image reading apparatus), and a scanner (image reading apparatus). In other words, the input image data, the hash value calculated based on the input image data, the invariant, etc. are transmitted from the MFP, printer, facsimile, computer, digital camera, scanner, etc. to the server device 50, and the server device 50 determines the similarity. Processing may be performed and a signal corresponding to the determination result may be returned.

  The scanner includes a document table, an optical scanning unit, a CCD (charge coupled device), etc., and scans the document image placed on the document table by the optical scanning unit to read the document image and generate image data. To do. The digital camera includes an imaging lens, a CCD, and the like, and captures a document image, a person, a landscape, and the like to generate image data. The scanner and the digital camera may have a function of performing predetermined image processing (for example, various correction processes) in order to appropriately reproduce the image.

  The printer prints an image based on image data generated by a computer, a scanner, and a digital camera on a sheet (recording paper). Further, the facsimile performs processing such as binarization processing, resolution conversion processing, and rotation on the image data read from the image input device, and transmits the image data compressed to a predetermined format to the other party. Then, the image data transmitted from the other party is expanded, subjected to rotation processing, resolution conversion processing, and halftone processing according to the performance of the image output apparatus, and output as an image in page units.

  The multifunction machine has at least two of a scanner function, a facsimile transmission function, and a printing function (copying function, printer function).

  The computer edits image data read by a scanner or a digital camera, or creates a document using application software.

  In each of the above-described embodiments, the index and the feature amount of the registered image are registered in the memory 8. However, the present invention is not limited to this, and the image data of the registered image may be stored. In this case, when performing the similarity determination process, the feature point calculation unit 31 and the feature amount calculation unit 32 may calculate the feature amount of the registered image data, and determine the similarity based on the calculated feature amount.

In each of the above embodiments, each unit (each block) constituting the document collation processing unit and the control unit provided in the digital color multifunction peripheral 1 and / or the server device 50 is realized by software using a processor such as a CPU. The That is, the digital color multifunction peripheral 1 and / or the server device 50 develops a central processing unit (CPU) that executes instructions of a control program that realizes each function, a read only memory (ROM) that stores the program, and the program. A random access memory (RAM), and a storage device (recording medium) such as a memory for storing the program and various data. An object of the present invention is to read the program code (execution format program, intermediate code program, source program) of the control program of the digital color multifunction peripheral 1 and / or the server device 50, which is software that realizes the functions described above, with a computer. This is achieved by supplying the recording medium recorded as possible to the digital color multifunction peripheral 1 and / or the server device 50, and reading out and executing the program code recorded on the recording medium by the computer (or CPU or MPU). .

  Examples of the recording medium include tapes such as magnetic tapes and cassette tapes, magnetic disks such as floppy (registered trademark) disks / hard disks, and disks including optical disks such as CD-ROM / MO / MD / DVD / CD-R. Card system such as IC card, IC card (including memory card) / optical card, or semiconductor memory system such as mask ROM / EPROM / EEPROM / flash ROM.

Further, the digital color multifunction peripheral 1 and / or the server device 50 may be configured to be connectable to a communication network, and the program code may be supplied via the communication network. The communication network is not particularly limited. For example, the Internet, intranet, extranet, LAN, ISDN, VAN, CATV communication network, virtual private network, telephone line network, mobile communication network, satellite communication. A net or the like is available. Also, the transmission medium constituting the communication network is not particularly limited. For example, even in the case of wired such as IEEE 1394, USB, power line carrier, cable TV line, telephone line, ADSL line, etc., infrared rays such as IrDA and remote control, Bluetooth ( (Registered trademark), 802.11 wireless, HDR, mobile phone network, satellite line, terrestrial digital network, and the like can also be used. The present invention can also be realized in the form of a computer data signal embedded in a carrier wave in which the program code is embodied by electronic transmission.

  In addition, each block of the digital color multifunction peripheral 1 and / or the server device 50 is not limited to being realized using software, and may be configured by hardware logic, and performs a part of the processing. A combination of hardware and arithmetic means for executing software for controlling the hardware and performing the remaining processing may be used.

  The computer system of the present invention includes an image input device such as a flatbed scanner, a film scanner, and a digital camera, a computer in which various processes such as the similarity calculation process and the similarity determination process are performed by loading a predetermined program, An image display device such as a CRT display or a liquid crystal display that displays the processing results of the computer, and an image forming device such as a printer that outputs the processing results of the computer to paper or the like may be used. Furthermore, a network card, a modem, or the like as communication means for connecting to a server or the like via a network may be provided.

  The present invention is not limited to the above-described embodiments, and various modifications can be made within the scope of the claims. That is, embodiments obtained by combining technical means appropriately changed within the scope of the claims are also included in the technical scope of the present invention.

  The present invention can be applied to an image processing apparatus that determines the similarity between input image data and registered image data registered in advance, and performs control according to the determination result.

It is a block diagram which shows schematic structure of the document collation process part with which the image processing apparatus concerning one Embodiment of this invention is equipped. 1 is a block diagram illustrating a schematic configuration of an image processing apparatus according to an embodiment of the present invention. It is a block diagram which shows schematic structure of the feature point calculation part with which the image processing apparatus shown in FIG. 2 is equipped. It is explanatory drawing which shows an example of the filter coefficient of the mixing filter with which the MTF process part of the image processing apparatus shown in FIG. 2 is provided. FIG. 3 is an explanatory diagram illustrating an example of a connected region extracted from input image data by a feature point calculation unit of the image processing apparatus illustrated in FIG. 2 and a center of gravity of the connected region. It is explanatory drawing which shows an example of each gravity center (feature point) of the some connection area | region extracted from the character string contained in input image data by the feature point calculation part of the image processing apparatus shown in FIG. FIG. 3 is an explanatory diagram illustrating an example of a feature point of interest and peripheral feature points extracted when a feature amount is calculated by a feature amount calculation unit of the image processing apparatus illustrated in FIG. 2. (A)-(c) is explanatory drawing which shows an example of the combination of the attention feature point and surrounding feature point which are extracted when the feature-value calculation part of the image processing apparatus shown in FIG. 2 calculates a feature-value. . (A)-(c) is explanatory drawing which shows an example of the combination of the attention feature point and surrounding feature point which are extracted when the feature-value calculation part of the image processing apparatus shown in FIG. 2 calculates a feature-value. . (A) And (b) is explanatory drawing which shows an example of the index showing the hash value and input image data about each feature point registered into a hash table in the image processing apparatus shown in FIG. 3 is a graph showing an example of the number of votes for each registered image in the voting processing unit of the image processing apparatus shown in FIG. 2. It is a flowchart which shows the flow of a process in the image processing apparatus shown in FIG. It is a block diagram which shows schematic structure of the document collation process part with which the image processing apparatus concerning other embodiment of this invention is equipped. It is explanatory drawing which shows an example of the coefficient preset for every user, every time slot | zone, and every processing mode which are memorize | stored in the memory of the image processing apparatus shown in FIG. It is a flowchart which shows an example of the flow of a process in the image processing apparatus shown in FIG. It is explanatory drawing which shows an example of the information notified to an administrator from the image processing apparatus shown in FIG. 13, when the process with respect to a registration image is requested | required. 14 is a graph showing an example of a cumulative score and the number of originals calculated in the image processing apparatus shown in FIG. It is a flowchart which shows the other example of the flow of a process in the image processing apparatus shown in FIG. It is a block diagram which shows the modification of the image processing apparatus concerning one Embodiment of this invention. It is explanatory drawing which shows schematic structure of the image processing system concerning further another embodiment of this embodiment. It is a block diagram which shows schematic structure of the image processing system concerning further another embodiment of this embodiment. It is a flowchart which shows the flow of a process in the image processing system shown in FIG. It is a flowchart which shows the modification of the flow of a process in the image processing system shown in FIG. It is a block diagram which shows the modification of the image processing system shown in FIG. FIG. 25 is a flowchart showing the flow of processing in the image processing system shown in FIG. 24. It is a block diagram which shows the other modification of the image processing system shown in FIG. It is a flowchart which shows the flow of a process in the image processing system shown in FIG. (A)-(d) is description which shows an example of the combination of the attention feature point and peripheral feature point which are extracted when the feature-value calculation part of the image processing apparatus concerning one Embodiment of this invention calculates a feature-value. FIG. (A)-(d) is description which shows an example of the combination of the attention feature point and peripheral feature point which are extracted when the feature-value calculation part of the image processing apparatus concerning one Embodiment of this invention calculates a feature-value. FIG. It is a block diagram which shows schematic structure of the document collation process part with which the image processing apparatus concerning further another embodiment of this invention is equipped. It is explanatory drawing which shows an example of the evaluation value and reference | standard evaluation value which are used with the image processing apparatus shown in FIG. (A) is explanatory drawing which shows an example of the evaluation value used with the image processing apparatus shown in FIG. 29, (b) is explanatory drawing which shows an example of the reference | standard evaluation value used with the image processing apparatus shown in FIG. It is. It is a flowchart which shows the flow of a process in the image processing apparatus shown in FIG.

Explanation of symbols

1 Digital color MFP (image processing device, image forming device, image reading device)
1 'Flatbed scanner (image processing device, image reading device)
2 Color image input device (input data acquisition unit)
3,3 'color image processing device (image processing device)
4 Color image output device 5 Communication device (input data acquisition unit, suitability input unit)
6 Operation panel (processing input part, suitability input part)
7 Control unit (similarity determination unit, coefficient changing unit, restriction processing unit, notification processing unit, storage processing unit)
8, 8a, 8b Memory (storage unit, image storage unit, character information storage unit, log storage unit, coefficient storage unit, condition storage unit, evaluation value storage unit)
13 Document collation processing unit (similarity determination unit)
31 feature point calculation unit (similarity calculation unit)
32 feature amount calculation unit (feature amount extraction unit, similarity calculation unit)
32a Feature point extraction unit 32b Invariant calculation unit 32c Hash value calculation unit 33 Voting processing unit (similarity calculation unit)
34 Similarity determination processing unit (similarity calculation unit)
35 Score calculator (similarity calculator)
35c Score calculation unit (evaluation value calculation unit)
36 Cumulative score comparison unit (similarity calculation unit)
36c Score comparison unit 41 Signal conversion processing unit 42 Resolution conversion unit 43 MTF processing unit 44 Binarization processing unit 45 Center of gravity calculation unit 61 OCR processing unit (character identification unit)
62 Image compression unit

Claims (30)

An input data acquisition unit that acquires input image data, a feature amount extraction unit that extracts the feature amount of the input image data, a storage unit that stores the feature amount of the registered image, and a registered image from an external device that is communicably connected Whether or not the input image data is image data corresponding to the registered image by comparing the feature amount of the input image data and the feature amount of the registered image with at least one of the registered image acquisition units that acquire the feature amount of An image processing apparatus including a similarity determination unit that performs the determination process of
The image processing apparatus, wherein the similarity determination unit changes processing contents of the determination processing according to incidental information of the input image data. A processing input unit that receives a processing request for the input image data;
The supplementary information includes user information for identifying the user who has input the processing request, information indicating the date, day of the week or time when the processing request is input, information indicating the size or number of pages of the input image data, and the content of the processing request 2. The image processing apparatus according to claim 1, wherein the image processing apparatus includes at least one of information indicating whether or not an image having a predetermined hue is included in the input image data. A similarity calculator that calculates the similarity between the input image data and the registered image;
A coefficient storage unit that stores a coefficient determined according to the content of the incidental information,
The similarity determination unit
A corrected similarity calculated by correcting the similarity calculated by the similarity calculating unit based on the coefficient corresponding to the incidental information of the input image data is calculated, and the corrected similarity is compared with a preset threshold value. The image processing apparatus according to claim 1, wherein the determination process is performed. The similarity determination unit
When the input image data includes image data of a plurality of pages, the corrected similarity is calculated for each page, an added similarity obtained by adding the corrected similarities of a plurality of pages is calculated, and the added similarity is preset. The image processing apparatus according to claim 3, wherein the determination process is performed by comparing the first threshold value. The similarity determination unit
The input image data is divided into a plurality of blocks, the corrected similarity is calculated for each block, an added similarity obtained by adding the corrected similarities of the plurality of blocks is calculated, and the added similarity is preset. The image processing apparatus according to claim 3, wherein the determination process is performed by comparing with a second threshold value. A suitability input unit that accepts input related to the suitability of the determination result;
4. The coefficient change unit according to claim 3, further comprising a coefficient changing unit that changes the coefficient used in the determination process when the suitability input unit receives an input indicating that the determination result is incorrect. The image processing apparatus described. An evaluation value set for each group that further classifies each item according to the content of each item included in the incidental information, and an evaluation value storage unit that stores a reference evaluation value set for each item;
An evaluation value calculation unit that calculates an evaluation value for each item of the input image data based on the content of each item in the incidental information of the input image data and the evaluation value stored in the evaluation value storage unit ,
The similarity determination unit calculates a difference for each item between the evaluation value for each item calculated by the evaluation value calculation unit and the reference evaluation value for each item, and adds the differences. The image processing apparatus according to claim 1, wherein the value is compared with a preset third threshold value, and the determination process is performed based on the comparison result. A suitability input unit that accepts input related to the suitability of the determination result;
A reference evaluation value changing unit that changes the reference evaluation value stored in the evaluation value storage unit when the suitability input unit receives an input indicating that the determination result is incorrect. The image processing apparatus according to claim 7, wherein the apparatus is an image processing apparatus. A condition storage unit that stores at least one of the conditions of the incidental information when the determination process is performed on the input image data and the conditions of the incidental information when the determination process is not performed on the input image data With
The similarity determination unit determines whether or not it is necessary to perform the determination process on the input image data based on incidental information of the input image data and the conditions stored in the condition storage unit. The image processing apparatus according to claim 1, wherein: A similarity calculator that calculates the similarity between the input image data and the registered image;
A weighting coefficient storage unit that records weighting coefficients set for each of the registered images,
The similarity determination unit
By comparing the value calculated by the similarity calculator with the weighting coefficient corresponding to the registered image and a preset threshold value, or the registration calculated by the similarity calculator The image processing apparatus according to claim 1, wherein the determination process is performed by comparing a degree of similarity with an image and a value obtained by multiplying a predetermined threshold by the weighting coefficient corresponding to the registered image.   A restriction processing unit is provided for restricting the processing according to the processing request for the input image data when the input image data is determined to be image data corresponding to the registered image by the determination processing. The image processing apparatus according to claim 1, wherein:   The information processing apparatus according to claim 1, further comprising a notification processing unit configured to notify a preset notification destination when the input image data is determined to be image data corresponding to the registered image by the determination process. The image processing apparatus according to 1.   When the determination process determines that the input image data is image data corresponding to the registered image, the input image data or the registered image corresponding to the input image data is stored in a preset storage destination. The image processing apparatus according to claim 1. A storage unit that stores the feature amount of the registered image;
A registration unit that stores the feature amount of the registered image in the storage unit,
The feature amount extraction unit extracts the feature amount of the registered image,
The image processing apparatus according to claim 1, wherein the registration unit stores the feature amount of the registered image extracted by the feature amount extraction unit in the storage unit. A registered image acquisition unit that acquires a feature amount of a registered image from an external device that is communicably connected;
A registered image output unit for transmitting the feature amount of the registered image to the external device,
The feature amount extraction unit extracts the feature amount of the registered image,
The image processing apparatus according to claim 1, wherein the registered image output unit transmits the feature amount of the registered image extracted by the feature amount extraction unit to the external device. An image forming apparatus for forming an image according to input image data,
An image forming apparatus comprising the image processing apparatus according to claim 1. An image reading device that reads an original and obtains input image data,
An image reading apparatus comprising the image processing apparatus according to claim 1. An image processing system comprising an image processing device and a server device communicably connected to the image processing device,
An input data acquisition unit for acquiring input image data;
A feature amount extraction unit for extracting feature amounts of input image data;
A storage unit that stores the feature amount of the registered image;
A similarity determination unit that compares the feature amount of the input image data with the feature amount of the registered image and determines whether or not the input image data is image data corresponding to the registered image, and the image processing apparatus. Distributed to the above server devices,
The image processing system, wherein the similarity determination unit changes processing contents of the determination processing according to incidental information of the input image data. The feature amount extraction unit is provided in the image processing device, the similarity determination unit is provided in the server device,
The image processing device outputs the feature amount of the input image data extracted by the feature amount extraction unit to the server device,
The image processing system according to claim 18, wherein the server device performs the determination processing based on a feature amount acquired from the image processing device. The image processing apparatus includes a log generation unit that generates log information related to the input image data.
The image processing device outputs the log information to the server device,
The server device stores the log information in a log storage unit provided in the server device when the similarity determination unit determines that the input image data is image data corresponding to the registered image. The image processing system according to claim 18. The image processing apparatus includes an image compression unit that compresses input image data and generates compressed image data.
The image processing device outputs the compressed image data to the server device,
The server device stores the compressed image data in an image storage unit provided in the server device when the similarity determination unit determines that the input image data is image data corresponding to the registered image. The image processing system according to claim 18. The image processing apparatus includes a region separation unit that separates input image data into a character region including characters and / or line drawings and a region other than the character region,
The image processing system according to claim 21, wherein the image compression unit compresses a character area in the input image data and an area other than the character area by different compression methods. The image processing apparatus includes a character identification unit that identifies character information included in input image data.
The image processing device outputs the character information to the server device,
The server device stores the character information in a character information storage unit included in the server device when the similarity determination unit determines that the input image data is image data corresponding to the registered image. The image processing system according to claim 18.   In the image processing apparatus or the server apparatus, a notification processing unit that performs notification to a preset notification destination when the similarity determination unit determines that the input image data is image data corresponding to the registered image. The image processing system according to claim 18, further comprising:   When the similarity determination unit determines that the input image data is image data corresponding to the registered image, the image processing apparatus or the server apparatus includes the input image data and log information related to the input image data. The image processing system according to claim 18, wherein at least one of the two is stored in a preset storage destination. A second feature amount extraction unit for extracting the feature amount of the registered image;
The image processing system according to claim 18, further comprising: a registration unit that stores the feature amount of the registered image extracted by the second feature amount extraction unit in the storage unit. A registration unit for storing the feature amount of the registered image in the storage unit;
The feature amount extraction unit extracts the feature amount of the registered image,
The image processing system according to claim 18, wherein the registration unit stores the feature amount of the registered image extracted by the feature amount extraction unit in the storage unit. An input data acquisition step of acquiring input image data;
A feature amount extraction step for extracting feature amounts of the input image data;
A registration data acquisition step for acquiring a feature amount of a registered image;
A similarity determination step of comparing whether or not the input image data is image data corresponding to the registered image by comparing the feature amount of the input image data with the feature amount of the registered image. And
An image processing method, wherein the processing content of the determination processing in the similarity determination step is changed according to incidental information of the input image data.   A program for operating the image processing apparatus according to any one of claims 1 to 15, wherein the program causes a computer to function as each unit.   A computer-readable recording medium on which the program according to claim 29 is recorded.

Images