JP4436858B2 - Image processing apparatus, image forming apparatus, image transmitting apparatus, image reading apparatus, image processing system, image processing method, image processing program, and recording medium thereof - Google Patents

Description

  The present invention relates to an image processing apparatus, an image forming apparatus, an image transmitting apparatus, an image reading apparatus, an image processing system, and image processing that store in a storage unit identification information for identifying a registered image in association with a feature amount of the registered image The present invention relates to a method, an image processing program, and a recording medium thereof.

  Conventionally, various techniques for comparing the input image data obtained by reading a document image with a scanner and a registered image registered in advance and determining the similarity between the two have been proposed.

For example, Patent Document 1 generates a descriptor selected so as to be invariant to distortion caused by digitization of a document from the characteristics of the input document and a difference between the input document and a matching document in the document database, A technique is disclosed in which a descriptor and a document in a document database including a feature from which the descriptor is extracted are associated with each other and recorded in the descriptor database, and the input document and the document in the document database are matched using the descriptor database. Has been. In this technique, when the descriptor database is scanned, votes for each document in the document database are accumulated so that one document with the maximum number of votes or a document with a number of votes exceeding a certain threshold is regarded as a consistent document. It has become.
Japanese Patent Laid-Open No. 7-282088 (released on October 27, 1995)

  However, in the technique of the above-mentioned Patent Document 1, when deleting a document registered in the descriptor database, it takes a long time for the deletion process, and an excessive load is applied to the means for performing the deletion process, resulting in a decrease in system performance. There is a problem of doing.

  This problem will be described in more detail. FIG. 31 is an explanatory diagram illustrating an example of a database in which feature amounts (descriptors) H1, H2, H3, H4,... And registered image (registered document) indexes are recorded in association with each other.

  As shown in this figure, in the index storage area corresponding to each feature amount, the index of the registered image registered in advance is stored. Since a plurality of feature amounts are normally extracted from one registered image, one index is stored in association with a plurality of feature amounts. In addition, since a common feature amount may be extracted from different registered images, a plurality of indexes are associated with one feature amount. Therefore, when it is desired to delete a specific index, it is not possible to determine at which address and in which address the index is stored by searching the entire database. For this reason, for example, when the number of registered images registered in the database reaches the upper limit of the number that can be registered in this database, and it is desired to delete the old index so that a new index can be registered, It is necessary to specify at which address and at which address each index for searching and erasing the entire database is stored.

  In addition, after specifying at which address and position where the index to be erased is stored, a mask process for an address that is not an object to be erased (for example, a process for creating a mask signal indicating whether or not each address is an object to be erased) ) To prevent erroneous erasure and then erase. For example, when it is desired to delete ID0 to ID2047 in FIG. 31, the masking process is performed on the area other than the area where ID0 to ID2047 is stored (colored area in FIG. 31), and then ID0 to ID2047 are deleted. Need to do.

  For this reason, in order to delete the index of the registered image registered in the database, it takes a long time for the erasing process and an excessive load is applied to the means for controlling the erasing process. In addition, the larger the number of indexes that can be registered, the larger the capacity of the database. Therefore, the update time of the database becomes longer and the performance of the system is significantly reduced.

  The present invention has been made in view of the above problems, and an object of the present invention is to provide an image processing apparatus or an image that stores identification information for identifying a registered image in a storage unit in association with a feature amount of the registered image. In the processing system, the time required for updating the registered image is shortened and the load on the means for updating the registered image is reduced.

  In order to solve the above problems, an image processing apparatus according to the present invention includes an registration control unit that stores identification information for identifying a registered image in a storage unit in association with a feature amount of the registered image. The registration control unit divides the storage area of the storage unit into a plurality of divided areas, and the registration condition that is a condition of a registered image for storing the identification information in the divided areas and the divided areas. Is associated with each divided area, and when the identification information is stored in the storage unit, a storage area for storing the identification information is selected from the plurality of divided areas according to the registration condition. It is characterized by that.

  According to the above configuration, the registration control unit divides the storage area of the storage unit into a plurality of divided areas, and each registration area and a registration condition that is a condition of a registered image for storing identification information in each divided area. This is associated with each divided area. Then, when storing the identification information of the registered image in the storage unit, the storage area for storing the identification information is selected from a plurality of divided areas according to the registration conditions. Thereby, the identification information of the registered image corresponding to the registration condition corresponding to each divided area is stored (registered) in each divided area. For this reason, when it is desired to update (erase or overwrite) a part of the registered image stored in the storage unit, it is easy and quick to determine the divided area to be updated according to the registration condition of the registered image to be updated. Can be identified. In addition, it is not necessary to perform mask processing or the like on information that is not to be updated, and registered images registered in the divided area to be updated can be updated in a batch. Therefore, the time required for updating the registered image can be shortened, and the load accompanying the update process of the registered image can be reduced.

  Further, the registration control unit may be configured to select a divided region in which the identification information is stored so that the time when the processing for storing the identification information is performed is different for each divided region.

  According to said structure, the registration control part makes the time which performed the process which memorize | stores identification information differ for every division area. As a result, when a part of the registered images stored in the storage unit is to be updated, it is possible to easily and quickly specify the divided region to be updated according to the registration time of the registered image to be updated. Therefore, the time required for updating the registered image can be shortened, and the load accompanying the update process of the registered image can be reduced.

  For example, the registration control unit continues the identification information in the divided area until the number of the identification information stored in one divided area reaches the upper limit of the number of pieces of identification information that can be stored in the divided area. The identification information may be stored in the next divided area when the number of the identification information stored in the divided area reaches the upper limit.

  According to said structure, the division area where identification information is memorize | stored can be varied according to the time which performed the process which memorize | stores identification information. For this reason, for example, the divided area in which the oldest identification information is stored is updated, and the divided area to be updated can be easily and quickly specified according to the time when the identification information is stored. Therefore, the time required for updating the registered image can be shortened, and the load accompanying the update process of the registered image can be reduced.

  In addition, the registration control unit associates each of the divided areas with a period for performing the process for storing the identification information in advance, and when performing the process for storing the identification information, the timing for performing the process belongs. A configuration may be adopted in which a divided region in which identification information is stored is selected according to a period.

  According to the above configuration, the divided areas to be subjected to the update process according to the time when the identification information is stored by associating the divided areas with the period for performing the process of storing the identification information in advance. Can be identified easily and quickly. Therefore, the time required for updating the registered image can be shortened, and the load accompanying the update process of the registered image can be reduced. In addition, the identification information can be updated every predetermined period. For example, the storage unit is divided into first to fourth divided areas, and the period for performing the process of storing the identification information in each divided area is set to January to March, April to June, July to September, respectively. By setting the period from October to December, it is possible to easily and quickly perform a process of updating a divided area in which old identification information is stored every three months or every six months.

  In addition, the registration control unit associates each divided area with a priority of a registered image in which identification information is stored in each divided area, and corresponds to the identification information when storing the identification information. Depending on the priority of the registered image to be registered, a divided region for storing the identification information may be selected.

  According to said structure, a registration control part changes the division area which memorize | stores identification information for every priority of a registration image. Thereby, when it is desired to update a part of the registered images stored in the storage unit, it is possible to easily and quickly specify the divided region to be updated according to the priority of the registered image to be updated. Therefore, the time required for updating the registered image can be shortened, and the load accompanying the update process of the registered image can be reduced. Further, for example, in order to secure a storage capacity for storing new identification information in the storage unit, it is necessary to erase a part of the identification information already stored, or the identification information is already stored. When it is necessary to overwrite new identification information in the storage area, the identification information of the registered image with the higher priority is left without being updated, and the identification information of the registered image with the lower priority is deleted or overwritten. It can be performed.

  Further, the registration control unit associates, for each divided area, the divided area and an erasing condition that is a condition for erasing the identification information stored in the divided area. When present, the identification information stored in the divided area may be deleted, or new identification information may be overwritten and stored in the divided area.

  According to the above configuration, by setting the erasing condition in advance, it is possible to easily and quickly specify the divided area where the identification information is erased or overwritten.

  In addition, an instruction input unit that receives an instruction input from a user and a notification output unit that outputs information to be notified to the user. Before erasing or overwriting, information indicating that there is a divided area corresponding to the erasure condition is output from the notification output unit, and when there is an erasure or overwriting instruction from the user, A configuration may be employed in which erasure or overwriting is performed. The instruction input unit may receive an instruction input input via an input unit provided in the image processing apparatus, or may be input from an external apparatus that is communicably connected to the image treatment apparatus. It may be one that receives an instruction input. The notification output unit may output the information to a notification unit (for example, a display unit, an audio output unit, a vibration unit, a display lamp, etc.) provided in the image processing apparatus, or the image processing apparatus. Alternatively, the information may be output to an external device that is connected to be communicable.

  According to the above configuration, when there is a divided area that satisfies the deletion condition, the user is notified of information indicating that there is a divided area that satisfies the deletion condition, and waits for an erase or overwrite instruction from the user. It is possible to erase or overwrite the divided area. Therefore, it is possible to prevent the identification information from being erroneously updated against the user's intention.

  Moreover, it is good also as a structure which comprises the instruction | indication input part which receives the instruction | indication input about the division area which erase | eliminates the said identification information, and the said registration control part erase | eliminates the identification information memorize | stored in the division area according to the said instruction input. . The instruction input unit may receive an instruction input input via an input unit provided in the image processing apparatus, or may be input from an external apparatus that is communicably connected to the image treatment apparatus. It may be one that receives an instruction input.

  According to said structure, the division area which updates identification information according to the instruction | indication input from a user can be specified easily and rapidly. In addition, it is not necessary to perform mask processing or the like on information that is not to be updated, and registered images registered in the divided area to be updated can be updated in a batch. Therefore, the time required for updating the registered image can be shortened, and the load accompanying the update process of the registered image can be reduced.

  The registration unit includes a counting unit that counts the number of pieces of identification information stored in the storage unit, and the registration control unit is preset when a count value of the counting unit reaches a preset threshold value. A configuration may be adopted in which a divided area corresponding to the erasing condition is selected and the identification information stored in the divided area is erased, or new identification information is overwritten and stored in the divided area.

  According to the above configuration, when the number of pieces of identification information stored in the storage unit reaches a preset threshold value, a divided area corresponding to a predetermined erasing condition is selected and stored in the divided area. The identified identification information can be erased, or new identification information can be overwritten and stored in the divided area. Accordingly, it is possible to prevent a storage capacity for storing the identification information of the new registered image in the storage unit from being insufficient, and to appropriately update the identification information of the registered image.

  Further, the identification information is stored in each of the divided areas so that the time when the identification information is stored differs for each divided area, and the registration control unit has the most time when the identification information is stored. A configuration may be adopted in which an old divided area is selected as a divided area corresponding to the erasing condition.

  According to said structure, when the number of the identification information memorize | stored in the memory | storage part reaches the preset threshold value, the identification information memorize | stored in the division area where the oldest identification information is memorize | stored Alternatively, new identification information can be overwritten and stored in the divided area. Therefore, it is possible to prevent a storage capacity for storing the identification information of a new registered image in the storage unit from being insufficient, and to store the latest identification information of the registered image.

  Further, the identification information is stored in each of the divided areas so that the importance level of the registered image is different for each divided area, and the registration control unit uses the divided area having the lowest importance level as the erasing condition. It is good also as a structure selected as a corresponding division area.

  According to said structure, when the number of the identification information memorize | stored in the memory | storage part reaches the preset threshold value, it is memorize | stored in the division area where the identification information of the registered image with low importance is memorize | stored. Existing identification information can be erased, or new identification information can be overwritten and stored in the divided area. Therefore, it is possible to prevent a storage capacity for storing the identification information of a new registered image in the storage unit from being insufficient, and to leave the identification information of the registered image having a high importance level without being erased.

  The registration control unit includes an instruction input unit that receives an instruction input from a user and a notification output unit that outputs information to be notified to the user, and the registration control unit has reached a preset threshold value of the counting unit In this case, before the erasure or overwriting, information indicating that the number of pieces of identification information stored in the storage unit has reached a threshold is output from the notification output unit, and an erasure or overwriting instruction is issued from the user. A configuration may be adopted in which the erasure or the overwriting is performed on the corresponding divided region.

  According to said structure, when the number of the identification information memorize | stored in the memory | storage part reaches the preset threshold value, a user is notified of the information which shows that, and according to the deletion or overwriting instruction from a user The erasure or the overwriting can be performed on the divided area. Therefore, it is possible to prevent the identification information from being erroneously updated against the user's intention.

  Further, an input data acquisition unit that acquires input image data, a feature amount extraction unit that extracts a feature amount of the input image data, a feature amount acquired from the input image data, and a registered image stored in the storage unit It is good also as a structure provided with the similarity determination part which determines the similarity of an input image and a registration image by comparing a feature-value. Note that the input data acquisition unit may acquire input image data by reading a document with a scanner, for example, and an input created by inputting necessary items using software as a format of electronic data Image data may be acquired, input image data directly created as electronic data may be acquired, and input transmitted from a device connected to be communicable with the image processing device Image data may be acquired. The similarity determination described above may determine whether there is similarity or may determine (calculate) a similarity indicating the degree of similarity.

  According to the above configuration, the similarity between the input image and the registered image can be determined by comparing the feature amount acquired from the input image data with the feature amount of the registered image stored in the storage unit. .

  In addition, an instruction input unit that receives an instruction input from a user may be provided, and the registration control unit may delete the feature amount and identification information of the registered image specified by the instruction input from the storage unit.

  According to said structure, the feature-value and identification information of the registration image which a user desires to delete can be deleted appropriately from a memory | storage part.

  Further, an input data acquisition unit that acquires input image data, a feature amount extraction unit that extracts a feature amount of the input image data, a feature amount acquired from the input image data, and a registered image stored in the storage unit A similarity determination unit that determines the similarity between the input image and the registered image by comparing the feature quantity; and a display unit that displays information. The registration control unit includes the similarity determination unit that includes the input image data. A thumbnail image or a list of registered images determined to be similar to each other may be displayed on the display unit.

  According to the above configuration, the registration control unit causes the display unit to display thumbnail images or a list of registered images similar to the input image. Thereby, the user can easily select a registered image to be deleted.

  The registration processing unit displays a thumbnail image of the registered image on the display unit when the number of registered images determined to be similar to the input image is less than a predetermined number, and resembles the input image. If the number of registered images determined to be greater than or equal to a predetermined number, a list of registered images may be displayed. The predetermined value may be appropriately set according to the environment such as the size of the display unit.

  According to the above configuration, when the number of registered images determined to be similar to the input image is less than a predetermined number, the thumbnail image of the registered image is displayed on the display unit, thereby allowing the user to register the registered image. Can be visually recognized. In addition, when the number of registered images determined to be similar to the input image is greater than or equal to a predetermined number, a list of the registered images is displayed, thereby reducing user visibility when the number of registered images is large. The registered image can be displayed without any problem.

  In addition, when the number of registered images determined to be similar to the input image is greater than or equal to a predetermined number, the registration processing unit divides the thumbnail image or list of the registered image into a plurality of pages for display. It is good also as a structure.

  According to the above configuration, the thumbnail image size is larger than when displaying thumbnail images or a list of each registered image on one page regardless of the number of registered images determined to be similar to the input image. Alternatively, it is possible to prevent the visibility from decreasing due to the font of the list becoming too small.

  Further, an input data acquisition unit that acquires input image data, a feature amount extraction unit that extracts a feature amount of the input image data, a feature amount acquired from the input image data, and a registered image stored in the storage unit A similarity determination unit that determines the similarity between the input image and the registered image by comparing the feature amount; and a display unit that displays information. The registration control unit includes a degree of similarity between the registered image and the input image. It is good also as a structure on which the indicator which shows is displayed on the said display part.

  According to the above configuration, the registered image to be deleted can be easily selected by the user by displaying the degree of similarity of the registered image with respect to the input image.

  Further, an input data acquisition unit that acquires input image data, a feature amount extraction unit that extracts a feature amount of the input image data, a feature amount acquired from the input image data, and a registered image stored in the storage unit A similarity determination unit that determines similarity between an input image and a registered image by comparing feature amounts, and an instruction input unit that receives an instruction input from a user. The instruction input unit is similar to the input image. An instruction for selecting a divided region in which a registered image to be determined is registered or an instruction input regarding a registration condition of a registered image for determining similarity to an input image is received, and the instruction input unit receives the registration processing unit. For a registered image in which feature amounts and identification information are stored in a divided region corresponding to the selected instruction or a divided region corresponding to the registration condition received by the instruction input unit, May be configured to perform similarity determination that entry force image.

  According to the above configuration, the area to be subjected to the similarity determination process is divided into a divided area corresponding to the selection instruction received by the instruction input unit or a divided area corresponding to the registration condition received by the instruction input unit. It can be limited to registered images that store feature quantities and identification information. Therefore, the processing time can be shortened compared to the case where the similarity determination process is performed on all the divided areas in the storage unit.

  The registration control unit is identification information that is different from the identification information associated with the feature amount of another registered image stored in the same divided area as the feature amount of the registered image, as identification information associated with the feature amount of the registered image. Thus, a configuration may be used in which identification information that is common to identification information associated with at least one feature amount among other registered images stored in a divided region different from the feature amount of the registered image is used.

  According to the above configuration, by using common identification information in different divided areas, the types of identification information can be reduced as compared with the case where different pieces of identification information are associated with the feature amounts of all registered images in all divided areas. Therefore, it is possible to improve the processing efficiency of processing for storing a registered image, processing for determining similarity between an input image and a registered image, and processing for deleting a registered image. Further, the number of bits of identification information stored in the storage unit can be reduced, and the storage capacity required for the storage unit can be reduced. Alternatively, it is possible to store more feature amounts of registered images without increasing the storage capacity of the storage unit.

  Further, an input data acquisition unit that acquires input image data, a feature amount extraction unit that extracts a feature amount of the input image data, a feature amount acquired from the input image data, and a registered image stored in the storage unit A similarity determination unit that determines the similarity between the input image and the registered image by comparing the feature amount may be provided, and the similarity determination unit may perform the similarity determination process for each divided region.

  According to the above configuration, since the similarity determination process is performed for each divided region, for registered images that are different registered images stored in different divided regions and are associated with common identification information, Similarity determination processing can be performed appropriately.

  An image forming apparatus of the present invention includes any one of the above-described image processing apparatuses and an image output unit that forms an image corresponding to input image data on a recording material. An image transmission apparatus according to the present invention includes any one of the above-described image processing apparatuses and a transmission apparatus that transmits input image data to another apparatus that is communicably connected. The image reading apparatus of the present invention includes an image input apparatus that reads an original image and acquires input image data, and any one of the image processing apparatuses described above.

  According to the image forming apparatus, the image transmitting apparatus, and the image reading apparatus described above, it is possible to reduce the time required for updating the registered image and to reduce the load associated with the process for updating the registered image.

  In order to solve the above problems, an image processing system according to the present invention includes an image processing device and a server device that is communicably connected to the image processing device, and identification information for identifying a registered image. The image processing device or the server device includes a storage unit that stores the feature amount of the registered image and a registration control unit that associates the identification information with the feature amount and stores the feature information in the storage unit. Or an image processing system provided in a distributed manner in the image processing apparatus and the server apparatus, wherein the registration control unit divides the storage area of the storage unit into a plurality of divided areas, and A division area and a registration condition that is a condition of a registered image for storing the identification information in each division area are associated with each division area, and the identification information is stored in the storage unit. In Rutoki, a storage area for storing the identification information, and characterized by selecting from among the plurality of divided regions in accordance with the registration condition.

  According to the above configuration, the storage area of the storage unit is divided into a plurality of divided areas, and each divided area and a registration condition that is a condition of a registered image in which identification information is stored in each divided area correspond to each divided area. In addition, when storing the identification information of the registered image in the storage unit, the storage area for storing the identification information is selected from a plurality of divided areas according to the registration conditions. Thereby, identification information of a registered image corresponding to the registration condition corresponding to each divided region is stored in each divided region (registered image is registered). For this reason, when it is desired to update (erase or overwrite) a part of the registered image stored in the storage unit, it is easy and quick to determine the divided area to be updated according to the registration condition of the registered image to be updated. Can be identified. In addition, it is not necessary to perform mask processing or the like on information that is not to be updated, and registered images registered in the divided area to be updated can be updated in a batch. Therefore, the time required for updating the registered image can be shortened, and the load accompanying the update process of the registered image can be reduced.

  In order to solve the above-described problem, an image processing method of the present invention is an image processing method in which identification information for identifying a registered image and a feature amount of the registered image are associated with each other and stored in a storage unit. Dividing the storage area of the storage unit into a plurality of divided areas, and associating each divided area with a registration condition that is a condition of a registered image for storing the identification information in each divided area; And a step of selecting a storage area for storing the identification information from the plurality of divided areas according to the registration condition when the identification information is stored in the storage unit.

  According to the above configuration, the storage area of the storage unit is divided into a plurality of divided areas, and each divided area and a registration condition that is a condition of a registered image in which identification information is stored in each divided area correspond to each divided area. In addition, when storing the identification information of the registered image in the storage unit, the storage area for storing the identification information is selected from a plurality of divided areas according to the registration conditions. Thereby, identification information of a registered image corresponding to the registration condition corresponding to each divided region is stored in each divided region (registered image is registered). For this reason, when it is desired to update (erase or overwrite) a part of the registered image stored in the storage unit, it is easy and quick to determine the divided area to be updated according to the registration condition of the registered image to be updated. Can be identified. In addition, it is not necessary to perform mask processing or the like on information that is not to be updated, and registered images registered in the divided area to be updated can be updated in a batch. Therefore, the time required for updating the registered image can be shortened, and the load accompanying the update process of the registered image can be reduced.

  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, in the image processing apparatus and the image processing system according to the present invention, the registration control unit divides the storage area of the storage unit into a plurality of divided areas, and the divided areas and the divided areas are divided into the divided areas. A registration condition that is a condition of a registered image in which identification information is stored is associated with each divided area, and when the identification information is stored in the storage unit, the storage area in which the identification information is stored is the registration condition. Depending on the selection, a selection is made from among the plurality of divided regions.

  The image processing method of the present invention includes a step of dividing the storage area of the storage unit into a plurality of divided areas, and a registration image condition for storing the identification information in the divided areas and the divided areas. A step of associating a condition with each divided area, and when storing the identification information in the storage unit, a storage area for storing the identification information is selected from the plurality of divided areas according to the registration condition Process.

  An image forming apparatus, an image transmitting apparatus, and an image reading apparatus according to the present invention include the image processing apparatus.

  Therefore, according to the image processing device, the image processing system, the image processing method, the image forming device, the image transmitting device, and the image reading device of the present invention, the time required for updating the registered image is shortened and the registered image is updated. The load accompanying processing can be reduced.

[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 between the input image data and the registered image ((similarity / no similarity)). The document collation processing unit 13 directly inputs the input RGB signal to the subsequent input. The data is output to the gradation correction unit 14. The 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 multifunction peripherals, facsimile 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 requests processing of input image data via the operation panel 6 (for example, processing mode (copying, printing, transmission, editing, etc.), number of processed sheets (number of copies, number of printed sheets), transmission destination of input image data, registration image Update, etc.). 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. 3 is a block diagram illustrating a schematic configuration of the document matching processing unit 13. 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 similarity determination processing unit 34, a registration processing unit 37, a control unit 7, and a memory 8. I have.

  The control unit 7 controls the operation of each unit of the document collation processing unit 13. 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. It may control the operation of the processing unit 13.

  The control unit 7 also divides the storage area of the hash table 103 provided in the memory 8 into a plurality of divided areas, and sets the feature amount of the registered image calculated by the feature amount calculation unit 32 to a preset condition. Control to store (register) in the corresponding divided area is performed. In addition, the control unit 7 corresponds to a case where the number of registered images registered in the hash table 103 reaches a predetermined number, when there is an erasure or overwrite instruction from the user, or to a preset erasure condition or overwriting condition. In such a case, control for deleting a part of the data registered in the hash table 103 or overwriting a part of the data registered in the hash table 103 with new data is performed. Details of these processes will be described later.

  The memory 8 stores various data used for processing of each unit of the document matching processing unit 13, processing results, and the like. The hash table 103, the total registration number counter 104, the registration number counter 105 for each area, the area counter 106, and the like. It has.

  The hash table 103 is a table (storage unit) that stores a registered image index (identification information for identifying a registered image) and a feature amount of the registered image in association with each other. The total registration number counter 104 stores a count value obtained by counting the number of registered images registered in the hash table 103. The registration number counter 105 for each area stores a count value obtained by counting the number of registered pixels registered in each divided area described later for each divided area. The area counter 106 stores a value indicating a divided area currently set as a divided area for registering a registered image. Details of the hash table 103 and each counter will be described later.

  Note that the memory 8 or a part of the memory 8 (for example, the hash table 103) is a folder that can be accessed only by a specific user (for example, a security officer (administrator) at a company, a store, etc.) who is permitted to view and edit in advance. May be provided. In this case, for example, authentication information (for example, a user name, password, etc.) of a specific user is stored in the folder, and when access is requested, authentication processing is performed using this authentication information, and access permission / inhibition is performed. What is necessary is just to determine permission. The authentication method in this case is not particularly limited, and various conventionally known methods can be used.

  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. However, the configuration of the feature point calculation unit 31 is not limited to this. For example, the feature points may be calculated by various conventionally known methods.

  FIG. 4 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 an 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.

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

  For example, the achromatic 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 components such as lenses and mirrors, aperture aperture of the light receiving surface of the CCD, transfer efficiency and afterimages, integration effects due to physical scanning, and uneven operation. 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. 5 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. 6 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. 7 is an explanatory diagram illustrating 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. 8, 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. 8, when the feature point a is the target feature point, the four feature points b, c, d, and e are extracted as the peripheral feature points, and when the feature point b is the target feature point, 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. 9A to 9C, when the feature point a shown in FIG. 8 is the feature point of interest, three of the peripheral feature points b, c, d, and e are selected. 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) Hij 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 defined as an 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. 9A, 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. 9B, 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. 9C, 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. 9A to 9C.

Next, the hash value calculation unit 32c calculates a remainder value of (Hi1 × 10 ² + Hi2 × 10 ¹ + Hi3 × 10 ⁰ ) / D as a hash value (one of feature amounts) Hi and stores it 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 for calculating the invariant Hij is not particularly limited. For example, the cross ratio of five points in the vicinity of the feature point of interest, or the double ratio of five points extracted from the neighboring n points (n is an integer of n ≧ 5). The value calculated based on the arrangement of m points extracted from n points in the vicinity (m is an integer of m <n and m ≧ 5) and the cross ratio of the five points extracted from m points, etc. The invariant Hij may be used. 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 4) 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. 8, when the extraction of the peripheral feature points and the hash value when the feature point a is the target feature point is finished, the peripheral feature points and the hash value are extracted when the feature point b is the target feature point. I do. In the example of FIG. 8, when the feature point b is the target feature point, four feature points a, c, e, and f are extracted as the peripheral feature points. Then, as shown in FIGS. 10A to 10C, 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.

  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. 45A to 45D, when the feature point a shown in FIG. 8 is the feature point of interest, three of the peripheral feature points b, c, d, and e 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 for the geometric deformation may be calculated.

Further, when the feature point b shown in FIG. 8 is set as the feature point of interest, as shown in FIGS. 46 (a) to 46 (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 + Hi3 × 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 connected. The line segment is set as Bij. However, the present invention is not limited to this. For example, the line segment used for calculation of the invariant Hij may be selected by an arbitrary method such as selecting the line segment connecting the peripheral feature points as a reference. Good.

  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 (registered image) in the hash table 103 provided in the memory 8. (See FIG. 11A). 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 calculated hash values are the same value (H1 = H5 in the example of FIG. 11B), these may be combined and registered in the hash table 103. In addition, the registration processing unit 37 divides the hash table 103 into a plurality of storage areas (divided areas) in accordance with an instruction from the control unit 7 and registers a registered image in accordance with preset registration conditions. And register a registered image in the selected divided area. Details of the division method and the registration method will be described later.

  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 103, 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. 12 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 TH1 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 sent to the control unit Send to 7. That is, when the maximum number of votes is greater than or equal to a predetermined threshold TH1, it is determined that “similarity exists (input image data is image data of a registered image)”. No determination is made (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). And a predetermined threshold TH1 (for example, 80% of the total number of votes) may be compared to determine the similarity.

  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 TH1 (for example, 80% of the total number of votes). That is, if the calculated similarity is equal to or higher than the threshold value TH1, it is determined as “similarity”, and if it is lower than the threshold value TH1, it is determined as “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 TH1 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 the threshold value TH1.

  In determining similarity, the threshold TH1 is kept constant, while the similarity is determined by multiplying the number of votes for each registered image (the number of votes for each registered image) by the weighting coefficient of each registered image. Good. 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 correction vote number may be compared with the threshold value TH1, or the maximum correction vote number normalized by the total number of votes may be compared with the threshold value TH1, and the maximum correction vote number is normalized by the maximum registration number. This may be compared with the threshold value TH1. In this case, for example, the weighting factor may be set to a value larger than 1, and to become 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.

(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 a flowchart shown in FIG.

  First, the control unit 7 acquires input image data and a processing request (instruction input) input from the user via the operation panel 6 or the communication device 5 (S1, S2). The input image data may be acquired by reading a document image with the color image input device 2, or input image data transmitted from an external device may be acquired with the communication device 5. The input image data may be read and acquired from various recording media via a card reader (not shown) provided in FIG.

  Next, the control unit 7 determines whether or not the process requested by the process request is a registration process (S3). If it is determined that the process is a registration process, the control unit 7 controls each unit of the document collation processing unit 13, and performs a feature point calculation process (S4) and a feature amount calculation process (S5) for the input data acquired in S1. The calculated feature value and the document ID (registered image index) are associated with each other and registered in the hash table 103 (S6), and the process ends. Details of the registration method to the hash table 103 will be described later.

  On the other hand, when it is determined that the registration process is not performed in S3, the control unit 7 controls each unit of the document collation processing unit 13, and performs feature point calculation processing (S7) and feature amount calculation processing (S8) for the input data acquired in S1. ), Voting processing (S9), and similarity determination processing (S10). Then, the control unit 7 determines whether or not it is determined that there is similarity as a result of the similarity determination process (S11). If it is determined that there is no similarity, the control unit 7 permits execution of image processing (copying, electronic distribution, facsimile transmission, filing, image data correction, editing, etc.) for the input image data (S12). Exit.

  On the other hand, when determining that there is similarity in S11, the control unit 7 prohibits execution of image processing on the input image data (S13), and ends the processing. In the present embodiment, an example is described in which execution of a process is permitted when there is a similarity and execution of the process is prohibited when there is no similarity, but the present invention is not limited to this. For example, the similarity determination result may be notified to a predetermined notification destination. Further, it is necessary to record the input image data according to the similarity determination result, whether to superimpose a predetermined symbol or the like on the output image corresponding to the input image data, whether to perform user authentication, similarity It may be determined whether or not to display the sex determination result.

(1-4. Editing method of hash table 103)
(1-4-1a. Configuration of hash table 103)
As shown in FIGS. 11A and 11B described above, the hash table 103 can store indexes of a plurality of registered images corresponding to one hash value. Specifically, in the present embodiment, the number of images that can be registered as the entire hash table 103 is 8192, the number of feature points per image of 300 dpi is 2048, the hash value is calculated in seven ways, and the number of hash values is Assuming that there are 65536 images, the number of images that can be registered corresponding to one hash value is set to 64. However, the number of images that can be registered corresponding to one hash value is not limited to this, and depends on the resolution of registered images, the number of registered images, the number of hash values, etc. used in the apparatus or system to which the present invention is applied. What is necessary is just to set suitably.

  FIG. 1 is an explanatory diagram showing an example of hash values (hash values H1, H2, H3, H4,...) Stored in the hash table 103 and registered image indexes stored in association with the hash values. It is.

  In this embodiment, as shown in FIG. 1, the hash table 103 is divided into a plurality of areas (the first area to the fourth area in FIG. 1), and the index storage area corresponding to each hash value is divided into each divided area. It is designed to be distributed. For example, index storage areas H1_1, H1-2, H1_3, and H1_4 corresponding to the hash value H1 are provided in the first to fourth areas, respectively. Similarly, for the hash values H2, H3,..., Index storage areas corresponding to the hash values are provided in a distributed manner in the first to fourth areas.

  In the example of FIG. 1, as a storage area of an index corresponding to one hash value, an address of 128 bits per address is assigned to each divided area by two addresses. Therefore, as a whole hash table 103, 8 addresses are assigned to the storage area of the index corresponding to one hash value. In the example of FIG. 1, one index is expressed by 16 bits. Accordingly, 16 indexes can be registered for one hash value, and 64 indexes can be registered for the hash table 103 as a whole.

  In the present embodiment, the number of registered images that can be registered in the hash table 103 is set to 8192 (ID0 to ID8191), and the number of registered images that can be registered in each divided area is set to 2048. ing. The first area is allocated as index ID0 to ID2047, the second area is allocated as index ID2048 to ID4095, the third area is allocated as index ID4096 to ID6143, and the fourth area is allocated as index ID6144 to ID8191.

  Thus, if the index to be erased is designated, the divided area where the start address of the area to be erased and the divided area where the end address exists are calculated from the number of addresses provided in the hash table 103 and the number of divisions of the hash table 103. Can be determined uniquely. Further, for example, the erasure target area can be designated in units of divided areas so that the index ID0 to ID2047, that is, all indexes in the first area are erased. In this case, the erasing process can be performed more quickly, and the load on the control unit 7 for the erasing process can be further reduced.

(1-4-1b. Configuration example 2 of hash table 103)
In this embodiment, the number of registered images that can be registered in the hash table is 8192. In the example of FIG. 1, among the divided hash table areas, the first area is ID (index) 0 to ID 2047, The second area is allocated as ID 2048 to 4095, the third area is allocated as ID 4096 to 6143, and the fourth area is allocated as ID 6144 to 8191.

  However, the relationship between each divided area and the ID assigned to each divided area is not limited to this. For example, as shown in FIG. 33, the same ID may be assigned in each divided region. That is, in the example of FIG. 33, the storage areas of IDs 0 to 2047 are allocated to the divided areas of the hash table. With this configuration, the number of bits of the index is 13 bits (0-8191) in the example of FIG. 1, but can be reduced to 11 bits (0-2047) in the example of FIG. Therefore, when 8 indexes are stored at one address as shown in FIG. 33, the number of bits to be stored can be reduced by 2 bits × 8 = 16 bits per address. Therefore, the size of the hash table can be reduced, or more indexes can be registered with one address, so that more indexes can be registered without increasing the size of the hash table. In addition, since the number of bits of the index can be reduced, it is possible to improve the calculation processing efficiency during the voting process and the similarity determination process.

  In the example of FIG. 33, since the index assigned to each divided area is ID0 to 2047, different originals have the same ID among the plurality of divided areas. Therefore, if the voting process for the entire hash table is performed and only one set of histograms as shown in FIG. 12 is generated, voting is performed repeatedly on different originals having the same ID. As a result, the accuracy of collation determination is reduced.

  Therefore, voting processing may be performed for each divided region, and one set of histograms may be generated in the voting processing for each divided region.

  34 (a) and 35 (a) are explanatory diagrams showing voting processing results for different divided areas in the hash table. FIGS. 34 (b) and 35 (b) are diagrams for explaining the voting processing described above. It is a histogram which shows a result. For convenience of explanation, the indexes ID1 to ID6 are shown as ID1 'to ID6' in FIGS. 35 (a) and 35 (b).

In this way, by performing the voting process for each divided area, it is possible to prevent voting as the same ID for ID1 and ID1 ′ which are originally different documents.
In the similarity determination process, the maximum number of votes and the index of the registered image that obtained the maximum number of votes are extracted from the voting result histogram for each divided region, and compared with a predetermined threshold value. Judgment can be made appropriately. In the examples of FIGS. 34 (a), 34 (b), 35 (a), and 35 (b), ID4 in FIG. 34 (b) exceeds the threshold value, which corresponds to FIG. 34 (b). It is determined that ID4 of the divided area is similar.

  When performing voting processing and similarity determination processing for each divided region, a plurality of voting processing units and similarity determination processing units (for example, the same number as the number of divided regions) are provided, and voting processing and similarity determination are performed for each divided region. Processing may be performed in parallel. Alternatively, only one voting processing unit and similarity determination processing unit may be provided, and voting processing and similarity determination processing for each divided region may be sequentially performed.

  Moreover, although said description demonstrated the case where a voting process and a similarity determination process were performed for every divided area about each divided area, it is not restricted to this. For example, the voting process and the similarity determination process may be performed only on a specific divided area designated by the user. Alternatively, the control unit 7 may extract a divided region corresponding to a condition designated by the user, and perform voting processing and similarity determination processing for each divided region on the extracted divided region.

(1-4-2. Registration / Erase Method to Hash Table 103)
In the present embodiment, the user can arbitrarily select the storage area dividing method of the hash table 103 from the following four dividing methods.

  Specifically, the user inputs that he / she wants to specify the division method via the operation panel 6 or an external device that is communicably connected to the digital color multifunction peripheral 1 (for example, the operation panel 6 or the external device (computer etc. ) Is selected), the control unit 7 sets (i) the number of divisions of the storage area, and (ii) one division area. Screen for inquiring which division method to select: (iii) setting the management period of registered images, or (iv) setting the priority (importance) of registered images Is displayed on the display screen. The user can select a desired method from among these division methods by key operation, touch panel operation, mouse operation, or the like.

  Here, the respective division methods (i) to (iv) will be described. In the present embodiment, the number of indexes that can be registered as the entire hash table 103 is 8192 (ID0 to ID8191).

(I) When setting the number of divisions of the storage area When the user selects the above (i) as the division method, the control unit 7 displays a screen prompting the designation of the number of divisions as shown in FIG. Display. The user can set the number of divisions of the storage area by inputting a desired number of divisions according to the display screen. Note that the method of designating the number of divisions is not limited to this. For example, as shown in FIG. 14B, the number of divisions selectable by the control unit 7 is displayed on the display screen, and the number of divisions displayed is displayed. The number of divisions desired by the user may be selected.

  FIG. 15 is a flowchart showing the flow of processing when registering a new registered image in the hash table 103 (the processing of S6 in FIG. 13 described above) when the division method (i) is selected. is there. Here, the number of registered image indexes that can be registered in the entire hash table 103 is 8192, the number of storage area divisions of the hash table 103 is 4, and the number of registered image indexes that can be registered in each of the divided areas is 4. A case of 2048 will be described. First, the index of the registered image is registered in the first area. When the registration number in the first area reaches the upper limit value, the index is registered in the second area, and the registration number in the second area reaches the upper limit value. A case will be described in which registration is sequentially performed for each of the divided areas, such as registration in the third area when reaching.

  When the feature amount of the registered image is acquired by the processing of S1 to S5 in FIG. 13, the control unit 7 determines whether or not the count value of the total registration number counter 104 has reached a preset threshold value TH2 (S21). . The threshold TH2 setting method is not particularly limited, but in this embodiment, the threshold TH2 is set to 6144, which is 75% of the number of images that can be registered as the hash table 103 as a whole.

  If it is determined that the count value of the total registration number counter 104 has reached the threshold value TH2, the control unit 7 deletes the registered image in the divided area where the oldest registered image is registered (S22). Then, the counter value of the total registration number counter 104 is updated by subtracting the deleted registered image number from the counter value of the total registration number counter 104 (S23). Further, the count value of the registered number counter 105 for each erased divided area is reset (S24).

  After resetting the registered number counter 105 for each area in S24, or when it is determined in S21 that the count value of the total registered number counter 104 is less than the threshold value TH2, the control unit 7 sets the divided area currently set as the registration destination. It is determined whether or not the count value of the registration count by area counter 105 for (the divided area corresponding to the counter value of the current area counter 106) is an upper limit value corresponding to the number of images that can be registered in this divided area ( S25). In the example of FIG. 15, the initial value of the registered number counter 105 for each area is 0, and the upper limit value is 2047 for each divided area. Therefore, when the count value of the registration number counter 105 for each area is 2047, it means that 2048 registered image indexes are registered in the divided area.

  If it is determined in S25 that the count value of the region-specific registration counter 105 is the upper limit value, the control unit 7 starts registration in the next divided region (S26), and the count value of the region counter 106 is registered as described above. It is updated to a value corresponding to the performed divided area (S27). FIG. 16 is an explanatory diagram showing an outline of the area counter 106. The area counter 106 is a counter for indicating a divided area for registering a registered image, and the counter values 0 to 3 correspond to the first to fourth areas, respectively. The control unit 7 increments the counter value of the area counter 106 by 1 each time the number of registrations in a certain divided area reaches the upper limit value and registration in the next divided area is started.

  On the other hand, when it is determined in S25 that the count value of the registration number counter 105 by area does not reach the upper limit value, the control unit 7 registers the index of the registered image in the divided area currently set as the registration destination (S28). ).

  After the processing of S27 or S28, the control unit 7 increments the count value of the registered number counter 105 for each area corresponding to the registered divided area and the count value of the total registered number counter 104 (S29, S30). The process ends.

  In the example of FIG. 15 described above, when it is determined in S21 that the count value of the total registration number counter 104 has reached the threshold value TH2, the control unit 7 registers the divided area in which the oldest registered image is registered. The image is automatically deleted, but the present invention is not limited to this. For example, as shown in FIG. 17A, the control unit 7 displays a notification / warning that the remaining number of registrables has decreased, and an inquiry as to whether or not to delete the oldest registered image. May be displayed on the display unit of the operation panel 6 or the display unit of the external device, and it may be determined whether or not to delete the registered image in response to a user instruction input for this display.

(Ii) When setting the number of registrable per divided area When the user selects the above (ii) as the division method, the control unit 7 displays the operation panel 6 or the display unit of the external device as shown in FIG. In this way, a screen that prompts the user to specify the number of registrations per division area is displayed. The user can set the number of registration images that can be registered in each divided region by inputting a desired numerical value in accordance with the display screen. Note that the number that can be registered for each divided region can be set to an arbitrary value. However, in order to facilitate address management, it is preferable to set the registerable number to 2 to the nth power. As shown in FIG. 32, access to each divided area is performed by dividing the hash table so that the number of registrations in each divided area is 2 to the nth power (n is an integer of 2 or more). This is because it becomes easier.

  FIG. 32 is an explanatory diagram showing an example in which division is performed so that the number that can be registered in each divided area (division unit; the number of addresses included in each divided area) in the hash table is the 11th power of 2 addresses.

  As shown in this figure, the start address for each divided region can be uniquely determined by setting the number of registrations possible to each divided region to the power of 2 and assigning a region counter value to each divided region. For this reason, for example, when DMA (Direct Memory Access) is performed on the external memory (when the external memory is directly accessed), the start address can be easily calculated.

Generally, the start address for a divided area can be calculated by (area counter value) × (number of registerable areas). In this case, the registerable number of each divided area may not be 2 to the nth power. In the divided area 1 shown in FIG. 32, the area counter value cnt is cnt = 0 × 1, and the number of registerable areas is 2 ¹¹ = 2048, so the start address “stad” for this divided area 1 is “stad = cnt ×”. Number of possible registrations = 2048 = 0 × 800. Similarly, in the divided area 2 shown in FIG. 32, the area counter value cnt is cnt = 0 × 2, and the number of registerable areas is 2 ¹¹ = 2048. Therefore, the start address “stad” for this divided area 2 is “stad”. = Cnt × number of registrations = 4096 = 0 × 1000.

  Here, when the size of each divided area in the hash table (the number of registerable areas in each divided area) is set to 2 to the power of n, the start address is set to the area counter and the size of the hash table (the number of registerable areas in each divided area) It can be expressed only by bit combination. For this reason, the start address can be easily calculated.

For example, the start address of the divided area 1 shown in FIG. 32 is that the number of divisions is 2 ² = 4, cnt = 01b, and the registerable number of each divided area is 2048 = 100000000000000b. 11 bits are bit-coupled to become 0100000000000000b = 0 × 800. Similarly, since the start address of divided area 2 is cnt = 10b and the registerable number of each divided area is 2048 = 100000000000000b, bit combination of cnt and the lower 11 bits of the registerable number 2048 is 1000000000000000 = 0 × 1000. .

  Note that the method of specifying the number that can be registered in each divided area is not limited to the method shown in FIG. 18A, and for example, as shown in FIG. 18B, numerical values that can be selected by the control unit 7 are displayed. The user may select a desired numerical value from the displayed numerical values.

  The processing for registering a registered image is the same as the processing in FIG. It should be noted that the comparison target value (2047 in FIG. 15) of the registered number by area 105 for determining whether to register in the current divided area or the next divided area in S21 is the value for each divided area. What is necessary is just to set to the value according to the number which can be registered.

  If it is determined in S21 that the count value of the total registration number counter 104 has reached the threshold value TH2, as shown in FIG. 17 (b), the control unit 7 notifies that the remaining number that can be registered has decreased. The warning and the index range of the registered image registered in each divided region may be displayed, and it may be determined which divided region to delete the registered image in response to an instruction input from the user. Further, as shown in FIG. 17C, a display screen prompting the user to input an instruction regarding the index range of the registered image to be deleted is displayed, and the registered image corresponding to the instruction input from the user is deleted. Also good.

(Iii) When setting the management period of the registered image When the user selects (iii) as the division method, the control unit 7 designates the management period of each divided area on the display screen as shown in FIG. A screen prompting you to display is displayed. The user can set the management period of each divided area by inputting a desired numerical value in accordance with this display screen. The method for specifying the management period of each divided area is not limited to the method shown in FIG. 19A. For example, as shown in FIG. 19B, management periods that can be selected by the control unit 7 are displayed on the display screen. The management period desired by the user may be selected from the displayed management periods. Although the case where the number of divisions of the storage area is four will be described here, the present invention is not limited to this. For example, the user may arbitrarily set the number of divisions of the storage area.

  FIG. 20 is an explanatory diagram showing the relationship between each divided area and the registration date of the registered image registered in each divided area when the management period of each divided area is set to 3 months. In the example shown in this figure, the index of registered images registered from January 1 to March 31, 2006 is stored in the first area, and April 1 to June 30, 2006 is stored in the second area. The index of registered images registered on the day is stored, the index of registered images registered from July 1 to September 30, 2006 is stored in the third area, and October 2006 is stored in the fourth area. An index of registered images registered from 1st to December 31st is stored.

  FIG. 21 is a flowchart showing the flow of processing (the processing of S6 in FIG. 13 described above) when a new registered image is registered in the hash table 103 when the division method (iii) is selected. is there. Here, the number of registered image indexes that can be registered in the entire hash table 103 is 8192, the number of storage area divisions of the hash table 103 is 4, and the number of registered image indexes that can be registered in each of the divided areas is 4. A case of 2048 will be described.

  When the feature amount of the registered image is acquired by the processes of S1 to S5 in FIG. 13, the control unit 7 determines whether or not the count value of the total registration number counter 104 has reached a preset threshold value TH2 (S31). . The threshold TH2 setting method is not particularly limited, but in this embodiment, the threshold TH2 is set to 6144, which is 75% of the number of images that can be registered as the hash table 103 as a whole.

  If it is determined that the count value of the total registration number counter 104 has reached the threshold value TH2, the control unit 7 deletes the registration image in the divided area where the registration image of the oldest registration period is registered (S32). Then, the counter value of the total registration number counter 104 is updated by subtracting the number of deleted registered images from the counter value of the total registration number counter 104 (S33). In addition, the count value of the registered number counter 105 for each erased divided area is reset (S34).

  After resetting the registration number counter 105 by area in S34 or when determining that the count value of the total registration number counter 104 is less than the threshold value TH2 in S31, the control unit 7 determines the current date (S35). The date determination method is not particularly limited, and various conventionally known methods can be used.

  Next, the control unit 7 selects a divided area corresponding to the date determined in S35 (S36). Then, it is determined whether or not the count value of the region-specific registration number counter 105 corresponding to the selected divided region is the upper limit value of the number that can be registered for the divided region (S37).

  If the upper limit value of the number of registered images has not been reached in S37, the control unit 7 registers the index of the registered image in the divided area selected in S36 (S38).

  On the other hand, when it is determined in S37 that the number is the upper limit of the number of registered images, the control unit 7 determines whether or not to register in another divided region (S39). For example, when the number of registrations in the divided area corresponding to the date has reached the upper limit value, the user sets in advance whether or not to register in another divided area, and the control unit 7 sets the preset condition. You may judge according to. In addition, information that prompts the controller 7 to input an instruction as to whether or not to register in another divided area may be displayed on the display screen, and the controller 7 may make a determination according to the instruction input from the user.

  If it is determined in S39 that the image is not registered in another divided area, the control unit 7 ends the process without performing registration.

  If it is determined in S39 to register in another divided area, the control unit 7 registers in the other divided area (S40) and sets the count value of the area counter 106 to the registered divided area. Update to the corresponding value (S41).

  Note that the divided area where the registered image is registered in S40 may be, for example, a divided area corresponding to the divided period next to the divided period to which the date determined in S35 belongs. Further, the information registered in the divided area corresponding to the oldest divided period may be erased and overwritten and registered in the divided area. For example, by storing the value of the area counter corresponding to each divided area and the period assigned to each divided area in the memory 8, it is possible to easily specify the divided area to be erased and overwritten. Further, for example, the value of the area counter corresponding to each divided area, the period allocated to each divided area, and the number of divided areas (the number of divisions of the hash table 103) are associated with each other and stored in the memory 8. Based on these pieces of information and the value of the current area counter 106 (the value of the area counter of the divided area selected in S36), the divided area corresponding to the oldest divided period can be specified.

  After the process of S38 or S41, the control unit 7 increments the count value of the registered number counter 105 for each area corresponding to the registered divided area and the count value of the total registered number counter 104 (S42, S43). The process ends.

  In the example illustrated in FIG. 20, the case where the period to be allocated to each divided region is specified in units of three months has been described, but the present invention is not limited to this. For example, you may set arbitrarily the period allocated to each division area. Further, the period may be set by an arbitrary index representing the time axis (period), such as year, month, day, day of the week, or specific day.

  In the example of FIG. 21 described above, when it is determined in S31 that the count value of the total registration number counter 104 has reached the threshold value TH2, the control unit 7 registers the divided area in which the oldest registered image is registered. The image is automatically deleted, but the present invention is not limited to this. For example, as shown in FIG. 17D, the control unit 7 displays a notification / warning that the remaining number of registrables has decreased and the registration period assigned to each divided area, and any registration period. The user's instruction input regarding whether to delete the registered image may be received, and the registered image in the divided area corresponding to the instruction input may be deleted. Further, as shown in FIG. 17E, a screen for prompting the user to input a registration period to be deleted may be displayed, and the registration image of the registration period corresponding to the user's instruction input may be deleted.

  Also, in the process of S40, a screen substantially similar to that shown in FIG. 17D or FIG. 17E is displayed, the registered image corresponding to the user's instruction input is erased, and the registered image is registered in the erased area. It may be.

(Iv) When setting the priority (importance) When the user selects (iv) as the division method, the control unit 7 displays the number of priority categories (priority) on the display screen as shown in FIG. Display a screen that prompts you to specify the number of levels. The user can set the number of priority categories by inputting a desired numerical value in accordance with the display screen. Note that a registered image having a high priority may be protected so that it is not erased. In this case, for example, as shown in FIG. 22B, a screen prompting the user to specify which priority registered image should be protected is displayed, and the registered image corresponding to the priority according to the user's instruction input is protected. You can make it.

  When the priority category number is selected, the control unit 7 divides the storage area of the hash table 103 into divided areas corresponding to the selected category number, and registers each divided area corresponding to one of the priority levels. Allocate as an image registration area. That is, the divided areas to be registered are made different according to the priority. FIG. 23 is an explanatory diagram showing the relationship between each divided area in the hash table 103 and the priority assigned to each divided area when the number of priority categories is set to four. In the example shown in this figure, the storage area of the hash table 103 is divided into first to fourth areas, the first area is a registration area for a priority 1 registration image, and the second area is a registration area for a priority 2 registration image. The area and the third area are assigned to the registration area of the registered image of priority 3, and the fourth area is assigned to the registration area of the registered image of priority 4. In the example shown in this figure, the priority level 1 is the highest priority level, and the priority level decreases toward the priority level 4. In the example shown in this figure, the number of registered images that can be registered in each divided area is 2048.

  FIG. 24 shows a process for registering a new registration image in the hash table 103 when the division method (iv) is selected and the number of priority categories is set to 4 (in FIG. 13 described above). It is a flowchart which shows the flow of a process of S6.

  When the feature amount of the registered image is acquired by the processing of S1 to S5 in FIG. 13, the control unit 7 determines whether or not the count value of the total registration number counter 104 has reached a preset threshold value TH2 (S51). . The threshold TH2 setting method is not particularly limited, but in this embodiment, the threshold TH2 is set to 6144, which is 75% of the number of images that can be registered as the hash table 103 as a whole.

  If it is determined that the count value of the total registration number counter 104 has reached the threshold value TH2, the control unit 7 deletes the registered image in the divided area where the registered image with the lowest priority is registered (S52). Then, the counter value of the total registration number counter 104 is updated by subtracting the deleted registered image number from the counter value of the total registration number counter 104 (S53). Also, the count value of the registered number counter 105 for each erased divided area is reset (S54).

  Next, the control unit 7 determines the priority of the registered image (S55), and selects a divided region according to the determined priority (S56). Note that the priority of the registered image may be determined by the control unit 7 in accordance with an instruction input from the user via the operation panel 6 or an external device, or according to a condition set in advance by the control unit 7. You may make it judge.

  Next, the control unit 7 determines whether or not the counter value of the registration number counter 105 for each divided area selected in S56 is the upper limit value of the number that can be registered for the divided area (S57). If the count value is the upper limit value, the process ends without performing registration. On the other hand, if the count value has not reached the upper limit value, registration in the divided area according to the priority is performed (S58), and the count value of the registered number counter 105 for each area corresponding to the divided area and the total value are calculated. The counter value of the registered number counter 104 is incremented (S59, S60), and the process is terminated.

  In the example of FIG. 24, when the number of registered images registered in the divided area corresponding to the priority of the registered image has already reached the upper limit, the registered image is not registered. This is not a limitation. For example, when the number of registered images in the divided area corresponding to priority 1 has reached the upper limit, the fourth area assigned as the registration area of priority 4 having the lowest priority is set as the registration area of priority 1. You may make it allocate. FIG. 25 is a flowchart showing the flow of processing in this case. In addition, since the process of S51-S60 is the same as FIG. 24, description is abbreviate | omitted here.

  If the control unit 7 determines in S57 that the count value of the registration number by region counter 105 for the divided region selected in S56 has reached the upper limit of the number that can be registered, the control unit 7 determines the priority of the registered image to be registered. It is determined whether or not 1 (S61). If the priority is not 1, the process ends.

  On the other hand, when it is determined in S61 that the priority is 1, the control unit 7 deletes the registered image of the divided area where the registered image having the lowest priority is registered, and registers the divided area with the priority 1 It is determined whether to use the image for registration (S62). This determination may be made based on, for example, an instruction input from the user via the operation panel 6 or an external device, or may be made by the control unit 7 based on a preset condition. If it is determined that the divided area is not used for registering a registered image with priority 1, the process ends without performing registration.

  On the other hand, if it is determined that the divided area is used for registering a registered image with priority 1, the registered image registered in the divided area is deleted (S63), and a new registered image is registered in the divided area. Is registered (S64). Further, the count value of the registration number counter 105 for each area and the counter value of the total registration number counter 104 corresponding to the divided area are updated so as to reflect the results of the erasure process and the registration process (S65, S66). Exit.

  In the above description, an example has been described in which when the number of registered images in the divided area corresponding to priority 1 reaches the upper limit, the divided area having the lowest priority is changed to a divided area having priority 1. Not limited to this, for example, when the number of registered images in the priority areas 2 and 3 reaches the upper limit, the lowest priority area is changed to a priority 2 or priority 3 area. You may make it do. Further, the divided area having the lowest priority may be further divided into a plurality of areas, and the divided areas may be assigned to the registered areas having the priorities 1 to 3.

  Further, the present invention is not limited to the configuration in which the registered image of the divided area having the lowest priority is deleted. For example, a user instruction input regarding the divided area to be deleted may be received, and the divided area corresponding to the instruction input may be deleted. .

  In the example of FIGS. 24 and 25 described above, when it is determined in S51 that the count value of the total registration number counter 104 has reached the threshold value TH2, the control unit 7 registers the registered image with the lowest priority. However, the present invention is not limited to this. For example, for a divided area where a registered image with high priority is registered, protection is applied in advance so that the registered image cannot be deleted, and as shown in FIG. A display screen for inquiring whether or not to delete the registered image may be displayed, and it may be determined whether or not to delete the registered image in the divided area in accordance with an instruction input from the user. In addition, as shown in FIG. 17G, the control unit 7 displays the importance corresponding to the erasable divided area, and erases the registered image in the divided area in accordance with the instruction input from the user. Also good.

  Further, the method for dividing the storage area of the hash table 103 is not limited to the methods (i) to (iv) described above, and other division methods may be used. Further, any two or more of the above (i) to (iv) may be used in appropriate combination.

  FIG. 26 is an explanatory diagram showing an example in which the divided areas are set using the registration period (registration time) and the priority by combining the above (iii) and (iv). In the example shown in this figure, the storage area of the hash table 103 is divided into first to fourth areas and is set to be registered in one of the divided areas according to the registration period. In addition, each divided area is further divided into first to fourth small areas, and each small divided area is assigned to a registered area of priority 1 to 4, respectively.

  With the configuration as shown in FIG. 26, when the hash table for the current registration period becomes full, the low priority area in the other registration period is changed to the registration area for the current registration period. Alternatively, the low-priority area in the current registration period can be changed to the registration area of the registered image with high priority in the current registration period.

  Also, as shown in (V) below, the index of the document specified by the user may be deleted from the hash table.

(V) When erasing by specifying an index of a document FIG. 36 is a flowchart showing an example of processing for erasing an index of a document instructed by a user from a hash table.

  In the example shown in this figure, first, the user inputs image data of a document to be deleted from the hash table, and the control unit 7 acquires the image data of the document as input image data (S71). Here, the input image data may be acquired by reading a document image with the color image input device 2, or input image data transmitted from an external device may be acquired with the communication device 5. The input image data may be read and acquired from various recording media via a card reader (not shown) provided in the machine 1 or the like.

  Next, the control unit 7 controls each unit of the document collation processing unit 13 and performs feature point calculation processing (S72), feature amount calculation processing (S73), voting processing (S74), and similarity for the input data acquired in S71. Determination processing (S75) is performed. Then, the control unit 7 determines whether or not it is determined that there is similarity as a result of the similarity determination process, that is, whether or not there is a similar registered image (S76). If it is determined that there is no similarity, the control unit 7 determines that the document corresponding to the input image data is not registered (there is no registered image to be deleted), and ends the process.

  On the other hand, if it is determined in S76 that the images are similar, the control unit 7 displays the thumbnail images of the registered images determined to be similar, such as a computer externally connected via the display unit of the operation panel 6 or a network. Is displayed on the display device (S77).

  If a document to be deleted exists in the thumbnail-displayed registered image, the user selects the registered image to be deleted from the registered document displayed in thumbnail by a key operation, a touch panel operation, a mouse operation, or the like. The control unit 7 determines whether or not there is an erasure instruction (selection instruction for a registered image to be erased) from the user (S78).

  In S78, when there is no deletion instruction from the user, the control unit 7 determines that there is no registered image to be deleted, and the process ends. The determination as to whether or not there is an erasure instruction may be made, for example, when there is no input instruction even after a predetermined time has elapsed, and an instruction input from the user indicating that there is no registered image to be erased. You may make it judge based on.

  When there is an erasure instruction in S78, the control unit 7 erases the ID of the selected registered image from the hash table (S79).

  Thereafter, the control unit 7 determines whether there are other registered images to be deleted, that is, whether there are registered images whose similarity is equal to or higher than a predetermined value other than the registered images deleted in S79 (S80). If there is no other registered image to be deleted, the process is terminated. On the other hand, when there are other registered images to be erased, the processing from S77 onward is performed again on the registered images that are not erased and whose similarity is equal to or greater than a predetermined value.

  Note that the user may simultaneously select a plurality of registered images to be deleted from a plurality of thumbnail images, and the control unit 7 may delete the selected plurality of registered images at once. In this case, the process of S80 may be omitted.

  In addition, the user may designate a divided area (area condition where a registered image to be deleted exists) to be deleted and a document to be deleted. FIG. 37 is a flowchart showing an example of processing in this case.

  In the example shown in this figure, first, the user inputs image data of a document to be deleted from the hash table, and the control unit 7 acquires the image data of the document as input image data (S81). Here, the input image data may be acquired by reading a document image with the color image input device 2, or input image data transmitted from an external device may be acquired with the communication device 5. The input image data may be read and acquired from various recording media via a card reader (not shown) provided in the machine 1 or the like.

  Next, the control unit 7 controls each unit of the document matching processing unit 13 to perform a feature point calculation process (S82) and a feature amount calculation process (S83) on the input data acquired in S81.

  Further, the control unit 7 acquires an erasing condition (condition of a divided area where a registered image to be erased is registered) input by the user (S84). For example, the control unit 7 operates information for specifying the divided area, such as the number of the divided area, the management period of the registered image, the priority (importance) of the registered image, and other information associated with the registered image. The data is displayed on a display device such as a computer externally connected via the panel 6 or a network. In addition, as other information linked | related with a registered image, when dividing a hash table for every user, a user name, a user ID, etc. are mentioned, for example. The user refers to the displayed information and selects an erasing condition by a key operation, a touch panel operation, a mouse operation, or the like.

  In addition, the process of S82 and S83 and the process of S84 may be performed in parallel, and the process of S84 may be performed before the process of S82 and S83.

  Next, the control unit 7 controls each unit of the document collation processing unit 13 and votes using the feature amount extracted in S83 for the registered image registered in the divided area corresponding to the condition acquired in S84. Processing (S85) and similarity determination processing (S86) are performed. Since the subsequent processing of S87 to S91 is the same as the processing of S76 to 80 in FIG. 36, description thereof is omitted here.

  In this way, the user can specify the erasing conditions (division areas to be subjected to erasure processing), so that the target areas for the voting process and the similarity determination process can be limited. Therefore, the processing time for these processes can be greatly increased. Can be shortened.

  As described above, in the process of FIG. 36 or FIG. 37, when a plurality of registered images whose similarity to the input image data is greater than or equal to a predetermined value are extracted, the thumbnail images of these registered images are displayed on the operation panel 6. Alternatively, an arbitrary number of registered images to be deleted may be selected from a plurality of registered images displayed on the display unit of the external device, and the selected registered images may be deleted collectively. .

  FIG. 38 is an explanatory diagram showing a display example when eight registered images having a similarity to input image data equal to or greater than a predetermined value are extracted and thumbnail images of these registered images are displayed.

  Note that when a large number of registered images having a degree of similarity with the input image data greater than or equal to a predetermined value are extracted, thumbnail images of the extracted registered images may be displayed in a plurality of pages. In this case, a page feed button or the like for switching the page to be displayed may be displayed. Alternatively, a button for scrolling the thumbnail image of the registered image to be displayed may be displayed. FIG. 39 is an explanatory diagram showing a display example for one page when 38 registered images are extracted and thumbnail images of these registered images are displayed in five pages.

  In addition, when a large number of registered images having a similarity with the input image data equal to or greater than a predetermined value are extracted, a list (list) may be displayed instead of the thumbnail images of these registered images. FIG. 40 is a flowchart showing an example of processing when displaying a list.

  The processing of S101 to S107 in FIG. 40 is the same as the processing of S81 to S87 in FIG. When it is determined that there is similarity in S107, the control unit 7 determines whether or not the number of registered images determined to be similar (the number of registered images whose similarity is equal to or greater than a predetermined value) is less than a preset threshold value. Is determined (S108). The threshold value may be set as appropriate according to conditions such as the size of the display unit of the operation panel 6 or the external device.

  If it is determined that the value is less than the threshold, the control unit 7 displays a thumbnail image of each registered image determined to be similar to the operation panel 6 or the display unit of the external device (S109).

  On the other hand, if it is determined that the value is equal to or greater than the threshold value, the control unit 7 displays a list of registered images determined to be similar to the operation panel 6 or the display unit of the external device (S110). FIG. 41 is an explanatory diagram showing an example of a list display, and shows an example where the threshold is set to 10 and the number of registered images extracted is 15. FIG. 42 is an explanatory diagram showing another example of the list display, and shows an example in which the threshold is set to 50 and the number of registered images extracted is 70. As shown in this figure, when the number of registered images extracted is large, the list may be divided into a plurality of pages and displayed. In this case, a page feed button or the like for switching the page to be displayed may be displayed. Alternatively, buttons for scrolling a list of registered images to be displayed may be displayed.

  In the example shown in FIGS. 41 and 42, a list of the date, time, registrant's user ID, and the like when the document is registered is displayed. Further, it is possible to select whether or not to delete each registered document by a key operation, a touch panel operation, a mouse operation or the like. In addition to or in place of these pieces of information, the ID of each registered image may be displayed.

  After the process of S109 or S110, the control unit 7 determines whether or not there is an erasure instruction (selection instruction for a registered image to be erased) from the user (S111). If there is a document to be deleted in the thumbnail or list of registered images, the user selects the registered image to be deleted from the displayed registered documents by key operation, touch panel operation, mouse operation, etc. do it.

  In S111, when there is no deletion instruction from the user, the control unit 7 determines that there is no registered image to be deleted, and the process ends. The determination as to whether or not there is an erasure instruction may be made, for example, when there is no input instruction even after a predetermined time has elapsed, and an instruction input from the user indicating that there is no registered image to be erased. You may make it judge based on.

  If there is a deletion instruction in S111, the control unit 7 deletes the ID of the selected registered image from the hash table (S112). Thereafter, the control unit 7 determines whether or not there are other registered images to be deleted, that is, whether or not there is a registered image whose similarity is equal to or higher than a predetermined value other than the registered images deleted in S112 (S113). If there is no other registered image to be deleted, the process is terminated. On the other hand, when there are other registered images to be erased, the processing from S108 onward is performed again for the registered images whose similarity is equal to or greater than a predetermined value among the unregistered registered images.

  In this way, when the number of registered images whose similarity is equal to or greater than a predetermined value is greater than or equal to a threshold value, a list display is performed to display a registered image extracted when a large number of registered images are extracted. The visibility can be improved, and the user can be appropriately recognized. Also, if it is less than the threshold value, the extracted registered image can be recognized more appropriately by the user by performing thumbnail display. However, the present invention is not limited to this, and either thumbnail display or list display may always be performed regardless of the number of registered images extracted. In addition, the user may specify which display method to use.

  Further, when displaying thumbnail images or a list of extracted registered images, values indicating the similarity of the input image data to each registered image (for example, the number of votes for each registered image and the number of votes for each registered image are normalized) A difference or a ratio between the value and the number of feature values extracted from the input image data and the number of feature values matching the feature value of the registered image among the feature values may be displayed.

  Further, when displaying thumbnails or lists of extracted registered images, they may be displayed in descending order of similarity to input image data, or may be displayed in the order according to the registered date and time, You may display in the order according to importance, and may display for every user.

  In the examples of FIGS. 36, 37, and 40, the image data of the registered image to be deleted is read by the color image input device 2 or acquired from an external device by the communication device 5, or the digital color composite Although the case of obtaining from various recording media via a card reader (not shown) provided in the machine 1 has been described, the present invention is not limited to this. For example, thumbnail images of registered images registered in the hash table may be sequentially displayed. FIG. 43 is a flowchart showing a processing example in the case of sequentially displaying thumbnail images of registered images registered in the hash table.

  In the example shown in this figure, the control unit 7 first displays the thumbnail image of the registered image registered in the hash table on the operation panel 6 or the display unit of the external device (S121).

  Next, the control unit 7 determines whether or not to perform registration image deletion processing (S122). This determination may be made based on, for example, whether or not there has been an instruction to continue the erasure process from the user.

  When it is determined in S122 that the registered image erasing process is not performed, the control unit 7 ends the process.

  On the other hand, if it is determined in S122 that the registered image is to be erased, the control unit 7 receives a selection instruction for the registered image to be erased from the user (S123), and erases the ID of the selected registered image from the hash table. (S124). Then, the control part 7 performs the process after S122 again.

  In FIG. 43, the thumbnail image of the registered image registered in the hash table is displayed in S121. However, the present invention is not limited to this. For example, a list of registered images may be displayed. Similarly to the examples shown in FIGS. 36 and 37, the input image data of the document that the user desires to delete is acquired by the color image input device 2, the communication device 5, or a card reader (not shown). Similarity determination with respect to the registered image of the acquired input image data may be performed, and a thumbnail image or a list of registered images determined to be similar (registered images having a similarity equal to or higher than a predetermined value) may be displayed.

  In addition, the user may designate a divided area to be erased (a condition for an area where a registered image to be erased exists). FIG. 44 is a flowchart showing the flow of processing in this case.

  In the example shown in this figure, the control unit 7 first acquires an erasing condition (a condition of a divided area in which a registered image to be erased is registered) input from the user (S131). For example, the control unit 7 operates information for specifying the divided area, such as the number of the divided area, the management period of the registered image, the priority (importance) of the registered image, and other information associated with the registered image. The data is displayed on a display device such as a computer externally connected via the panel 6 or a network. Then, the user refers to the displayed information and selects an erasing condition by a key operation, a touch panel operation, a mouse operation, or the like.

  Next, the control unit 7 displays the thumbnail image of the registered image registered in the divided area corresponding to the erasing condition input by the user on the operation panel 6 or the display unit of the external device (S132). Note that the present invention is not limited to the configuration for displaying thumbnail images, and a list may be displayed. Further, thumbnail display may be performed when the number of corresponding registered images is less than the threshold, and a list may be displayed when the number is greater than the threshold. In addition, thumbnail images or lists may be displayed divided into a plurality of pages.

  Thereafter, the same processing as S122 to S124 in FIG. 43 is performed (S133 to S135).

  As described above, the digital color multifunction peripheral 1 according to the present embodiment includes the hash table 103 in which the feature quantity and the registered image having the feature quantity are registered in association with each other, and the feature quantity extracted from the input image data The similarity between the input image data and the registered image is determined based on the feature amount registered in the hash table 103. Then, the storage area of the hash table 103 is divided into a plurality of divided areas based on a predetermined registration condition, and the correspondence relationship between the registered image and the feature amount is distributed and registered in each divided area according to the registration condition. It has become.

  Thus, by determining the divisional area or registered image condition to be erased and updated, the area to be erased and updated can be easily specified, and the area can be processed collectively. Therefore, since deletion and update can be performed efficiently regardless of the storage capacity of the entire hash table, the processing time required for deletion and update of the registered image is shortened, and the load on the control unit associated with this procedure is reduced. Can be reduced.

  In the present embodiment, the configuration in which one hash table 103 is provided and the storage area of the hash table 103 is divided into a plurality of parts has been described. However, the present invention is not limited to this, and a plurality of hash tables may be provided, and each hash table may be used as each divided area in the above description. Further, a plurality of hash tables may be provided, each hash table may be divided into a plurality, and each divided area may be used as each divided area in the above description.

  In the present embodiment, 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. 27 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 this figure, the flatbed scanner 1 'includes a color image input device 2 and a color image processing device 3'. The color image processing apparatus 3 ′ includes an A / D conversion unit 11, a shading correction unit 12, a document collation processing unit 13, a control unit 7 (not shown in FIG. 27), and a memory 8 (not shown in FIG. 27). The color image input device 2 is connected to the 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.

  Further, a part of the function of the document matching processing unit 13 may be executed in an external device (such as a server device) connected to the digital color multifunction peripheral 1 so as to be communicable.

  FIG. 28 shows the functions of the document collation processing unit 13 described above for the server device 50 and multifunction devices (MFPs) A, B,..., Printer A, connected to the server device 50 through a network. .., Facsimile A, B,..., Computers A, B,..., Digital cameras A, B,..., Scanners A, B,. 1 is an explanatory diagram showing a configuration of an image processing system 100 realized by

  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 (image input device), and shoots 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 decompressed, subjected to rotation processing, resolution conversion processing, and halftone processing according to the performance of the image output apparatus, and output as a page unit image. 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.

  FIG. 29 is a block diagram illustrating a configuration example when the server device 50 includes some of the functions of the control unit 7 and the document collation processing unit 13.

As shown in FIG. 29, 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. In addition, the server device 50 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 similarity determination processing unit 34, a registration processing unit 37, and a registration processing unit 37. And information necessary for processing of the document collation processing unit 13b such as the control unit 7b for controlling the document collation processing unit 13b, the hash table 103, the total registration number counter 104, the registration number counter 105 for each area, the area counter 106, etc. And a memory 8b. When data transmission / reception is required between each functional block provided in the digital color multifunction peripheral 1 and each functional block provided in the server device 50, the control unit 7a and the control unit 7b are connected to the communication devices 5 and 51, respectively. To transmit and receive data as appropriate. Other functions are the same as those described above.

  In the example of FIG. 29, all of the feature amount calculation unit 32 (the feature point extraction unit 32a, the invariant calculation unit 32b, and the hash value calculation unit 32c) are provided in the digital color multifunction peripheral 1, but this is not limitative. For example, as shown in FIG. 30, the feature point extraction unit 32 a and the invariant calculation unit 32 b may be provided in the digital color multifunction peripheral 1, while the hash value calculation unit 32 c may be provided 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 103 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 103 stored in the memory 8b.

  Further, for example, the digital color multifunction peripheral 1 does not perform processing such as storing the similarity determination result between the input image data and the registered image, and notifying the administrator when it is determined that there is similarity to the registered image, but not the network. You may make it carry out via the server apparatus connected via this. Further, for example, the hash table 103 may be provided in a server device connected to the digital color multifunction peripheral 1 so as to be communicable.

  Further, as a result of the similarity determination between the input image data and the registered image in the digital color multifunction peripheral 1, the input image data determined to be similar and log information (operation record information; for example, document ID, for example) The user ID of the user who input the processing request, the date and time when the processing request was input, and the contents of the processing request (processing mode, number of processing, destination of transmission, editing contents, etc.) are connected to the digital color multifunction peripheral 1 so as to be communicable. The server device may be configured to transmit the information to the server device and store the information in the server device. If necessary, the server device may send the information to a predetermined transmission destination (for example, the administrator of the digital color multifunction peripheral 1). It may be configured to transmit.

  Further, input image data determined not to be similar to a registered image may be registered as a registered image. In this case, since the input image data determined not to be similar is sequentially registered as a registered image, the number of registered images registered in the hash table 103 is very large. For this reason, the hash table 103 overflows unless the index for the old registered image is deleted. Therefore, in such an application, since it is necessary to frequently delete and update the hash table 103, the effects of the present invention can be obtained particularly suitably.

  For example, by dividing the hash table into twelve months, each divided area can be allocated for storing job log results for one month. In this case, the storage area of the hash table is set by deleting all the registered images of the oldest month at a stage when registered images for a predetermined period (for example, 11 months) are registered. Can be avoided. In addition, when the number of registered documents in a month exceeds the number of documents that can be registered in one divided area, the divided area in which the registered image of the oldest month is recorded is used as the job log storage destination for the current month. By setting so as to expand, even when the number of registered images per month is large, the registered image of the current month can be surely registered.

  Further, when deleting a registered image registered in the hash table, the deletion process may be performed in a time zone with a relatively low system load such as midnight. Thereby, the system load can be distributed.

  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. Further, 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 shown in the claims. That is, embodiments obtained by combining technical means appropriately modified 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 stores identification information for identifying a registered image in a storage unit in association with a feature amount of the registered image.

It is explanatory drawing which shows an example of the registration method of the registration image with respect to the hash table in the image processing apparatus concerning one Embodiment of this invention. 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 document collation process part with which the image processing apparatus concerning one Embodiment of this invention is equipped. It is a block diagram which shows schematic structure of the feature point calculation part with which the image processing apparatus concerning one Embodiment of this invention 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 concerning one Embodiment of this invention is provided. It is explanatory drawing which shows an example of the connection area | region extracted from input image data by the feature point calculation part of the image processing apparatus concerning one Embodiment of this invention, and the gravity center of this connection area | 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 concerning one Embodiment of this invention. It is explanatory drawing which shows an example 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. (A)-(c) is explanation which shows an example of the combination of the attention feature point and peripheral feature point extracted when calculating the feature-value by the feature-value calculation part of the image processing device concerning one embodiment of the present invention. FIG. (A)-(c) is explanation which shows an example of the combination of the attention feature point and peripheral feature point extracted when calculating the feature-value by the feature-value calculation part of the image processing device concerning one embodiment of the present invention. FIG. (A) And (b) is explanatory drawing which shows an example of the index showing the hash value about each feature point registered into a hash table, and input image data in the image processing apparatus concerning one Embodiment of this invention. . It is a graph which shows an example of the number of votes with respect to each registration image in the voting process part of the image processing apparatus concerning one Embodiment of this invention. It is a flowchart which shows the flow of a process in the image processing apparatus concerning one Embodiment of this invention. (A) And (b) is explanatory drawing which shows an example of the display screen displayed on the display part of the image processing apparatus concerning one Embodiment of this invention. It is a flowchart which shows an example of the registration process in the image processing apparatus concerning one Embodiment of this invention. It is explanatory drawing which shows an example of the area | region counter with which the image processing apparatus concerning one Embodiment of this invention is equipped. (A) And (b) is explanatory drawing which shows an example of the display screen displayed on the display part of the image processing apparatus concerning one Embodiment of this invention. (A) And (b) is explanatory drawing which shows an example of the display screen displayed on the display part of the image processing apparatus concerning one Embodiment of this invention. (A) And (b) is explanatory drawing which shows an example of the display screen displayed on the display part of the image processing apparatus concerning one Embodiment of this invention. It is explanatory drawing which showed an example of the conditions of the registration image registered into each division area in the hash table of the image processing apparatus concerning one Embodiment of this invention. It is a flowchart which shows the other example of the registration process in the image processing apparatus concerning one Embodiment of this invention. (A) And (b) is explanatory drawing which shows an example of the display screen displayed on the display part of the image processing apparatus concerning one Embodiment of this invention. It is explanatory drawing which showed an example of the conditions of the registration image registered into each division area in the hash table of the image processing apparatus concerning one Embodiment of this invention. It is a flowchart which shows the further another example of the registration process in the image processing apparatus concerning one Embodiment of this invention. It is a flowchart which shows the further another example of the registration process in the image processing apparatus concerning one Embodiment of this invention. It is explanatory drawing which showed an example of the conditions of the registration image registered into each division area in the hash table of the image processing apparatus concerning one Embodiment of this invention. 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 the structure of the image processing system concerning one Embodiment of this invention. 1 is a block diagram illustrating a configuration example of an image processing system according to an embodiment of the present invention. It is a block diagram which shows the other structural example of the image processing system concerning one Embodiment of this invention. It is explanatory drawing for demonstrating the registration method of the registration image with respect to a hash table in the conventional image processing apparatus. It is explanatory drawing which shows the example at the time of setting the number of registration possible to each division area in a hash table to the 11th power of 2 in the image processing apparatus concerning one Embodiment of this invention. It is explanatory drawing which shows an example of the allocation method of the identification information with respect to the registration image registered into each division area in the image processing apparatus concerning one Embodiment of this invention. (A) is a table | surface which shows the voting result with respect to mutually different division area in the image processing apparatus concerning one Embodiment of this invention, (b) is a histogram of the voting result shown to (a). (A) is a table | surface which shows the voting result with respect to mutually different division area in the image processing apparatus concerning one Embodiment of this invention, (b) is a histogram of the voting result shown to (a). It is a flowchart which shows an example of the deletion process of the registration image in the image processing apparatus concerning one Embodiment of this invention. It is a flowchart which shows the other example of the deletion process of the registration image in the image processing apparatus concerning one Embodiment of this invention. FIG. 10 is an explanatory diagram illustrating a display example when displaying a thumbnail image of a registered image having a similarity with input image data equal to or greater than a predetermined value in the image processing apparatus according to the embodiment of the present invention. FIG. 10 is an explanatory diagram illustrating another display example when displaying a thumbnail image of a registered image whose similarity to input image data is a predetermined value or more in the image processing apparatus according to the embodiment of the present invention. It is a flowchart which shows the further another example of the deletion process of the registration image in the image processing apparatus concerning one Embodiment of this invention. FIG. 10 is an explanatory diagram showing still another display example when displaying a list of registered images whose similarity to input image data is a predetermined value or more in the image processing apparatus according to the embodiment of the present invention. FIG. 10 is an explanatory diagram illustrating another display example when displaying a list of registered images whose similarity to input image data is a predetermined value or more in the image processing apparatus according to the embodiment of the present invention. It is a flowchart which shows the further another example of the deletion process of the registration image in the image processing apparatus concerning one Embodiment of this invention. It is a flowchart which shows the further another example of the deletion process of the registration image in the image processing apparatus concerning one Embodiment of this invention. (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.

Explanation of symbols

1 Digital color MFP (image processing device, image forming device, image reading device, image processing device)
1 'Flatbed scanner (image processing device, image reading device)
2 Color image input device (image input device)
3,3 'color image processing device (image processing device)
4 color image output device (image output unit)
5 Communication devices (notification output unit, instruction input unit, transmission device)
6 Operation panel (notification output unit, instruction input unit)
7, 7a, 7b Control unit (registration control unit, similarity determination unit)
8, 8a, 8b Memory (storage unit)
13, 13a, 13b Document collation processing unit (registration control unit)
31 feature point calculation unit 32 feature amount calculation unit 32a feature point extraction unit 32b invariant calculation unit 32c hash value calculation unit 33 voting processing unit (similarity determination unit)
34 Similarity determination processing unit (similarity determination unit)
37 Registration Processing Unit (Registration Control Unit)
50 Server apparatus 100 Image processing system 103 Hash table (storage unit)
104 Total registered number counter 105 Registered number counter by area 106 Area counter

Claims (21)

An input data acquisition unit that acquires input image data, a feature amount extraction unit that extracts a feature amount of the input image data, and identification information for identifying a registered image associated with the feature amount of the registered image in the storage unit A registration control unit to be stored, and a similarity determination unit that determines the similarity between the input image and the registered image by comparing the feature amount extracted from the input image data with the feature amount of the registered image stored in the storage unit An instruction input unit that receives an instruction input from a user, and a display unit that displays information ,
The registration control unit
The storage area of the storage unit is divided into a plurality of divided areas, and each divided area is associated with a registration condition that is a registered image condition for storing the identification information in each divided area. When storing the identification information in the storage unit, the storage area for storing the identification information is selected from the plurality of divided areas according to the registration conditions , and the plurality of registered images are common features If there is a quantity, the identification information of a plurality of registered images having the feature quantity is stored in association with one feature quantity,
The instruction input unit receives an instruction for selecting a divided region in which a registered image for determining similarity to an input image is registered, or an instruction regarding registration conditions for a registered image for determining similarity to an input image,
The registration control unit
The similarity determination unit includes the registered image in which the feature amount and the identification information are stored in the divided region corresponding to the selection instruction received by the instruction input unit or the divided region corresponding to the registration condition received by the instruction input unit. Let us determine the similarity with the input image,
A list of registered images or a thumbnail image that the similarity determination unit determines to be similar to the input image is displayed on the display unit;
An image processing apparatus , wherein identification information of a registered image selected by a user via the instruction input unit from a list or thumbnail image displayed on the display unit is deleted from the divided area .   2. The image according to claim 1, wherein the registration control unit selects a divided region in which the identification information is stored so that a time at which the processing for storing the identification information is performed is different for each divided region. Processing equipment.   The registration control unit continuously transmits the identification information to the divided area until the number of the identification information stored in one divided area reaches the upper limit of the number of pieces of identification information that can be stored in the divided area. The image processing apparatus according to claim 2, wherein the identification information is stored in the next divided area when the number of the identification information stored and stored in the divided area reaches the upper limit value.   The registration control unit associates each of the divided areas with a period for performing the process for storing the identification information in advance, and when performing the process for storing the identification information, the registration control unit includes a period for performing the process. The image processing apparatus according to claim 2, wherein a divided area in which identification information is stored is selected according to the selection.   The registration control unit associates in advance each divided area and a priority of a registered image for storing identification information in each divided area, and stores the identification information when the identification information is stored. The image processing apparatus according to claim 1, wherein a divided area in which identification information is stored is selected according to the priority of the image.   The registration control unit associates the divided area with an erasing condition that is a condition for erasing the identification information stored in the divided area, and there is a divided area that satisfies the erasing condition. 2. The image processing apparatus according to claim 1, wherein the identification information stored in the divided area is erased, or new identification information is overwritten and stored in the divided area. . Includes a notification output unit for outputting information to notify the User chromatography THE,
If there is a divided area that satisfies the erasure condition, the registration control unit outputs information indicating that the divided area that satisfies the erasure condition exists before performing erasure or overwriting on the divided area. The image processing apparatus according to claim 6, wherein the divided area is erased or overwritten when an instruction for erasing or overwriting is issued from a user. A counting means for counting the number of identification information stored in the storage unit;
The registration control unit selects a divided area according to a predetermined erasing condition when the count value of the counting means reaches a preset threshold value, and the identification information stored in the divided area The image processing apparatus according to claim 1, wherein the image processing apparatus is erased or new identification information is overwritten and stored in the divided area. In each of the divided areas, the identification information is stored so that the time when the identification information is stored differs for each divided area.
The image processing apparatus according to claim 8 , wherein the registration control unit selects a divided area having the oldest time when the identification information is stored as a divided area corresponding to the erasing condition. In each of the divided areas, the identification information is stored so that the importance of the registered image is different for each divided area.
The image processing apparatus according to claim 8 , wherein the registration control unit selects the divided area having the lowest importance as a divided area corresponding to the erasing condition. Includes a notification output unit for outputting information to notify the User chromatography THE,
When the count value of the counting means has reached a preset threshold value, the registration control unit has reached the threshold number of identification information stored in the storage unit before performing the erasure or the overwriting The image processing apparatus according to claim 8 , wherein information indicating the effect is output from the notification output unit, and the erasure or the overwriting is performed on a divided area in accordance with an erasure or overwrite instruction from a user. When the number of registered images determined to be similar to the input image is less than a predetermined number, the registration control unit displays a thumbnail image of the registered image on the display unit and resembles the input image. The image processing apparatus according to claim 1 , wherein a list of registered images is displayed when the number of registered images determined to be greater than or equal to a predetermined number. When the number of registered images determined to be similar to the input image is greater than or equal to a predetermined number, the registration control unit displays the thumbnail image or list of the registered image divided into a plurality of pages. The image processing apparatus according to claim 1 , wherein: Upper Symbol registration control unit, an image processing apparatus according to an index indicating the degree of similarity to the input image of the registered image to claim 1, characterized in that causes the display section to display. 15. An image forming apparatus comprising: the image processing apparatus according to claim 1; and an image output unit that forms an image corresponding to input image data on a recording material. 15. An image transmission apparatus comprising: the image processing apparatus according to claim 1; and a transmission apparatus that transmits input image data to another apparatus connected to be communicable. An image input device that reads a document image and obtains input image data;
An image reading apparatus comprising: the image processing apparatus according to claim 1. An image processing device and a server device connected to the image processing device so as to be communicable with each other, an input data acquisition unit for acquiring input image data, and a feature amount extraction unit for extracting the feature amount of the input image data When a storage unit for storing a feature quantity included in the registration image and the identification information for identifying the registered image, and a registration control unit in association with each other and the identification information and the feature amount is stored in the storage unit, an input A similarity determination unit that determines the similarity between the input image and the registered image by comparing the feature amount extracted from the image data with the feature amount of the registered image stored in the storage unit, and an instruction input from the user instruction input unit and, if the display unit for displaying information provided in the image processing apparatus or the server apparatus, or et includes dispersed in the above image processing apparatus and the server apparatus which accepts And has an image processing system,
The registration control unit divides the storage area of the storage unit into a plurality of divided areas, and sets each divided area and a registration condition that is a condition of a registered image for storing the identification information in each divided area. When the identification information is stored in the storage unit, the storage area for storing the identification information is selected from the plurality of divided areas according to the registration condition , and When registered images have a common feature amount, identification information of a plurality of registered images having the feature amount is stored in association with one feature amount,
The instruction input unit receives an instruction for selecting a divided region in which a registered image for determining similarity to an input image is registered, or an instruction regarding registration conditions for a registered image for determining similarity to an input image,
The registration control unit
For the registered image in which the feature amount and the identification information are stored in the divided region corresponding to the selection instruction received by the instruction input unit or the divided region corresponding to the registration condition received by the instruction input unit, the similarity determining unit Let us determine the similarity with the input image,
A list of registered images or a thumbnail image that the similarity determination unit determines to be similar to the input image is displayed on the display unit;
An image processing system, wherein the identification information of a registered image selected by a user via the instruction input unit from a list or thumbnail image displayed on the display unit is deleted from the divided area . An image in which identification information for identifying a registered image and a feature amount of the registered image are associated with each other and stored in the storage unit, and the identification information stored in the storage unit is erased in response to an instruction from the user A processing method,
Dividing the storage area of the storage unit into a plurality of divided areas;
Associating each divided area with a registration condition that is a condition of a registered image for storing the identification information in each divided area for each divided area;
When storing the identification information in the storage unit, a storage area for storing the identification information is selected from the plurality of divided areas according to the registration condition , and a plurality of registered images are common features A step of storing the identification information of a plurality of registered images having the feature amount in association with one feature amount in the case of having the amount ;
A step of accepting an instruction for selecting a divided area in which a registered image for determining similarity to an input image is registered, or an instruction regarding registration conditions for a registered image for determining similarity to an input image;
Determining a similarity with the input image for a registered image in which feature amounts and identification information are stored in a divided region corresponding to the selection instruction or a divided region corresponding to the instruction related to the registration condition;
Displaying a list of registered images or thumbnail images determined to be similar to the input image;
And a step of erasing the identification information of the registered image selected by the user from the displayed list or the thumbnail image from the divided area . A program for operating an image processing apparatus according to any one of claims 1 to 14, a program for causing a computer to function as the registration control unit. A computer-readable recording medium on which the program according to claim 20 is recorded.