JP6677209B2 - Image processing apparatus, processing method, and program - Google Patents

Description

  The present invention relates to an image processing device, a processing method, and a program.

  2. Description of the Related Art There is an image input device including a pedestal and an image capturing unit that captures an object to be read such as a sheet placed in a reading area of the pedestal. Such an image input device outputs image data. 2. Description of the Related Art A technology for inputting image data and removing a shadow appearing in an image obtained by photographing an object to be read is used for an image processing apparatus. A related technique is disclosed in Patent Document 1.

JP-A-2006-140993

  In the image input device as described above, a technique for removing an unexpected shadow from an image has been required.

  Therefore, an object of the present invention is to provide an image processing device, a processing method, and a program that solve the above-described problems.

According to a first aspect of the present invention, there is provided an image processing apparatus for processing image data output from an image input device having a pedestal and a photographing unit for photographing an object to be read placed on the pedestal region, Based on a comparison of the luminance values of the images generated in each of the plurality of photographing operations, a portion where the difference in the luminance value is equal to or greater than a predetermined threshold is shaded based on a photograph of the object to be read placed at a position shifted from the photographing unit. A shadow area determination unit that determines an area, a brightness correction table generation unit that generates a brightness correction table holding a brightness correction coefficient by which the brightness value is multiplied based on the brightness value of the pixel in the shadow area , and shadow reduction processor for multiplying the luminance correction coefficient for the corresponding pixel is recorded on the luminance correction table to each pixel in the shadow region of the image, characterized in that it comprises a.

According to a second aspect of the present invention, there is provided a processing method of an image processing apparatus for processing image data output from an image input device having a pedestal and a photographing unit for photographing an object to be read placed in the pedestal region. The difference between the luminance values is equal to or greater than a predetermined threshold value based on a comparison of the luminance values of the images generated in each of the plurality of photographings by photographing the reading target placed at a position shifted from the relative position with respect to the photographing unit. Determining the location as a shadow area , generating a brightness correction table holding a brightness correction coefficient for multiplying the brightness value based on the brightness value of the pixel in the shadow area, and generating a brightness correction table for each pixel in the shadow area of the image generated by the shooting; characterized in that said multiplying the luminance correction coefficient for the corresponding pixel is recorded in the brightness correction table.

According to a third aspect of the present invention, a program is a computer for an image processing apparatus that processes image data output from an image input device that has a pedestal and an imaging unit that captures an object to be read placed on the pedestal region. The difference between the brightness values is equal to or greater than a predetermined threshold based on the comparison of the brightness values of the images generated by each of the plurality of shootings by shooting a reading target placed with the relative position shifted from the shooting unit. A shadow area determining means for determining a location as a shadow area; a brightness correction table generating means for generating a brightness correction table holding a brightness correction coefficient for multiplying the brightness value based on the brightness value of the pixel in the shadow area; and characterized in that the shadow reduction processing unit functions as, for multiplying the luminance correction coefficient for the corresponding pixel is recorded on the luminance correction table to each pixel in the shadow region of the image That.

  ADVANTAGE OF THE INVENTION According to this invention, the presence or absence of the shadow reflected in the image produced | generated by image | photographing the paper in the reader can be detected more accurately, and this can be removed more accurately.

1 is a schematic diagram of an image processing system including an image input device and an image processing device. FIG. 3 is a first diagram illustrating a shadow reflected on a sheet as a reading target object. FIG. 8 is a second diagram illustrating a shadow reflected on a sheet as a reading target object. FIG. 4 is a diagram illustrating an image of a range of a sheet in first image data and an image of a range of a sheet in second image data. FIG. 3 is a diagram illustrating an example of a hardware configuration of an image processing apparatus. FIG. 2 is a functional block diagram of the image processing apparatus according to the first embodiment. FIG. 3 is a diagram illustrating a processing flow of the image processing apparatus according to the first embodiment. It is a functional block diagram of an image processing device by a second embodiment. It is a functional block diagram of an image processing device by a third embodiment. FIG. 11 is a diagram illustrating different states in which a sheet is placed on a pedestal while being shifted relative to a photographing unit, in a single figure. FIG. 2 is a diagram illustrating a minimum configuration of the image processing apparatus.

<First embodiment>
Hereinafter, an image processing apparatus according to a first embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a schematic diagram of an image processing system including an image input device and an image processing device according to the embodiment.
As shown in this figure, the image processing system 100 includes an image processing device 1 and an image input device 2. The image input device 2 includes a pedestal 21, a photographing unit 22 that photographs a sheet placed in a pedestal region indicating a reading region of the pedestal 21, an arm unit 23 that supports the photographing unit 22 above the pedestal 21, and an arm unit. And a base 24 supporting the base 23. The sheet 3 is placed on the pedestal 21 as an example. The object to be read placed on the pedestal 21 may be an object other than paper. The image processing apparatus 1 outputs image data generated by optically reading the object to be read to the image processing apparatus 1. The image data is image data of the entire pedestal region. The image processing apparatus 1 detects the area of the sheet 3 from the image data of the entire pedestal area by a technique such as edge detection. The image processing apparatus 1 recognizes a pedestal coordinate system whose origin is the upper left corner in the pedestal image of the entire pedestal region indicated by the image data, and a paper coordinate system whose origin is the upper left corner in the paper image included in the pedestal image. The relationship between the corresponding pixels in the coordinates is stored.

  The image processing device 1 is connected to the image input device 2 via a communication cable. The image processing apparatus 1 acquires image data, detects the presence or absence of a shadow from a paper image indicated by the image data, and performs processing for removing the shadow.

There is a possibility that an unexpected shadow may enter the pedestal 21 on which the object to be read is placed.
If the shadow enters a predetermined position in the pedestal region and the shadow is fixed, the luminance correction coefficient corresponding to each pixel for adjusting the luminance value of the pixel corresponding to the predetermined position is determined by the luminance. What is necessary is just to record on a correction table. However, for example, a shadow of the furniture 4 placed beside the image input device 2 may enter unexpectedly. Due to this influence, the shadow of the furniture 4 may be reflected on the paper image indicated by the image data acquired by the image processing apparatus 1. In the image processing apparatus 1, it is desirable to accurately detect the presence or absence of a shadow unexpectedly reflected in a sheet image, and to remove this accurately. A case where shadows disappear due to unexpected removal of the furniture 4, that is, a case where brightness is unexpectedly increased in a region where the shadow of the furniture 4 is reflected can be similarly considered.

FIG. 2 is a first diagram showing a shadow reflected on a sheet to be read.
As shown in FIG. 2, an unexpected shadow may enter the sheet 3 placed on the pedestal 21. The image input device 2 outputs first image data generated by photographing the sheet 3 shown in FIG. Alternatively, as shown in FIG. 2, as shown in FIG. 2, the sheet 3 placed on the pedestal 21 usually has a shadow. However, there is a possibility that the shadow does not enter when an object that covers the shadow is unexpectedly removed.

Hereinafter, the image processing apparatus according to the present embodiment will be described using an example in which a shadow is unexpectedly reflected.
FIG. 3 is a second diagram illustrating a shadow reflected on a sheet to be read.
FIG. 3 shows a state where the position of the sheet 3 on the pedestal 21 is shifted. The user may shift the position of the sheet 3. Alternatively, the pedestal 21 itself has a sliding mechanism, and the position of the pedestal 21 itself is moved in the horizontal direction by the sliding mechanism, so that the relative position with respect to the photographing unit 22 is shifted, and the sheet 3 is placed on the pedestal 21. May be set. Then, the position of the shadow does not move, but the position at which the shadow enters the sheet 3 differs from the position at which the shadow enters the sheet 3 shown in FIG. The image input device 2 outputs to the image processing device 1 second image data generated by photographing the sheet 3 whose position is shifted as shown in FIG.

FIG. 4 is a diagram showing an image of a paper range in the first image data and an image of a paper range in the second image data.
Here, the image in the range of the paper 3 in the first image data and the image in the range of the paper 3 in the second image data are referred to as a first paper image 31 and a second paper image 32, respectively. These are cut out from the image data of the entire pedestal region, and perform skew correction (distortion correction) and the like in some cases. This skew correction may use a known technique.
The image processing apparatus 1 compares the first paper image 31 indicated by the first image data with the second paper image 32 indicated by the second image data, and determines the brightness value of the first paper image 31 with the second paper image 32. A location where the difference is equal to or greater than a predetermined threshold (a location where the difference in luminance value is large) is determined as a shadow area candidate. Alternatively, the image processing apparatus 1 compares the first sheet image 31 indicated by the first image data with the second sheet image 32 indicated by the second image data, and determines the brightness value of the second sheet image 32 with the first sheet image 31. Is determined as a shadow area candidate.
The position where the shadow appears is different between the first paper image 31 and the second paper image 32. Therefore, the image processing apparatus 1 compares the luminance values of the corresponding pixels of the first paper image 31 and the second paper image 32.

More specifically, the image processing apparatus 1 determines that the brightness value of the pixel of the second paper image 32 in the first paper image 31 is higher than or equal to the predetermined value by more than a predetermined value. Area 41-2 is determined as a shadow area candidate.
Similarly, in the second paper image 32, the image processing apparatus 1 increases the brightness value of the pixel of the first paper image 31 by more than a predetermined value and increases the brightness of the area 42-1 and the brightness of the area 42-1. -2 is determined as a shadow region candidate.

  The image processing apparatus 1 compares the shape, position, and position in the pedestal region of the shadow region candidate 41 in the first paper image 31 with the shape, position, and position in the pedestal region of the shadow region candidate 42 in the second paper image 32. Alternatively, if it is determined that they match, the shadow area candidate in the first paper image 31 or the second paper image 32 may be specified as a shadow area that unexpectedly enters.

FIG. 5 is a diagram illustrating an example of a hardware configuration of the image processing apparatus.
As shown in FIG. 5, the image processing apparatus 1 includes a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a HDD (Hard Disk Drive) 104, a user interface 105, a communication module Each hardware configuration of 106 is provided as an example. The user interface 105 is, for example, a liquid crystal touch panel or a button. The image processing apparatus 1 may be configured to further include other hardware.

FIG. 6 is a functional block diagram of the image processing apparatus according to the first embodiment.
The CPU 101 of the image processing apparatus 1 starts an image processing program stored in advance. Thus, the image processing apparatus 1 has the functions of the control unit 111, the shadow area determination unit 112, the brightness correction table generation unit 113, and the shadow reduction processing unit 114.
The control unit 111 controls other function units.
The shadow area determination unit 112 captures an object to be read placed at a position shifted from the image capturing unit 22 and calculates a difference between the brightness values based on a comparison of the brightness values of the images generated in each of the multiple times of capturing. Are determined as shadow region candidates. The shadow area determination unit 112 specifies a shadow area from among shadow area candidates.

The luminance correction table generation unit 113 generates a luminance correction coefficient for multiplying the luminance value based on the luminance value of the pixel in the shadow area. Specifically, the brightness correction table generating unit 113 calculates a brightness correction coefficient for multiplying the brightness value of each pixel in the shadow area to reduce the shadow by using the brightness correction coefficient of the image in the specific shooting in any of the multiple shootings. A luminance correction table held for each pixel is generated. To briefly explain, the brightness correction coefficient is, for example, such that the brightness value of a pixel determined to be a shadow area in a certain sheet image is X, and the brightness value of the above-described brightness value X in another sheet image whose position is shifted in the pedestal coordinate system. Assuming that the luminance value of a pixel that is not a shadow area at the same position in the paper coordinate system corresponding to the pixel is Y, the luminance value is represented by Y ÷ X. This luminance correction coefficient is a value assigned to each pixel in the pedestal coordinate system, and its initial value is 1. If it is determined that the area is a shadow area, the initial value is rewritten to a luminance correction coefficient such as Y ÷ X. By multiplying the luminance value X of the pixel determined as the shadow area by a luminance correction coefficient represented by Y ÷ X, the luminance value of the pixel determined as the shadow area becomes X × (Y ÷ X) = Y, and Is multiplied by a shadow correction coefficient using the value of X affected by the image and the value of Y not affected by the shadow as a reference value, the effect of the shadow can be reduced. By similarly setting the pixel value X ′ of the image captured at another occasion to X ′ × (Y ÷ X), the influence of the shadow can be reduced. When updating the luminance correction table, the value of the luminance correction coefficient before the update is multiplied by the above-described value of Y ÷ X to obtain the luminance correction coefficient after the update.
The shadow reduction processing unit 114 multiplies each pixel in the shadow area of the image generated by the specific shooting by a luminance correction coefficient for the corresponding pixel recorded in the luminance correction table.

FIG. 7 is a diagram illustrating a processing flow of the image processing apparatus according to the first embodiment.
Next, the processing flow of the image processing apparatus will be described step by step.
The image processing apparatus 1 acquires the first image data (Step S101). Further, the image processing apparatus 1 acquires the second image data (Step S102). The first image data and the second image data are image data obtained by photographing a sheet placed on the pedestal 21 while shifting the relative position with respect to the photographing unit 22. The shadow area determination unit 112 extracts the first paper image 31 from the first image data. Further, the shadow area determination unit 112 extracts the second paper image 32 from the second image data.

  The shadow area determination unit 112 compares the pixel of the first paper image 31 and the pixel of the second paper image 32 at the position corresponding to the pixel in order, and determines a pixel having a luminance difference of a predetermined value or more. Pixels having a difference equal to or more than a predetermined value that is considered to be affected by the shadow are identified as shadow region candidates 41-1 and 41-2 in the first paper image 31 (step S103). The shadow area determination unit 112 compares the pixel of the first paper image 31 and the pixel of the second paper image 32 at the position corresponding to the pixel in order, and determines a pixel having a luminance difference of a predetermined value or more. Pixels having a difference equal to or greater than a predetermined value that should be affected by the shadow are identified as shadow area candidates 42-1 and 42-2 in the second paper image 32 (step S104).

  The shadow area determination unit 112 determines the imaging area candidates 41-1 and 41-2 specified in the first paper image 31 and the shadow area candidates 42-1 and 42-2 specified in the second paper image 32 from the shadow area candidates. A process to specify a region to be excluded and to exclude the region from the shadow region candidate may be performed. For example, if the shapes of the shadow region candidates 41-1 and 41-2 do not match the shapes of the shadow region candidates 42-1 and 42-2, even if the regions that do not match are excluded from the shadow region candidates. Good. Alternatively, by comparing the identified shadow region candidates in a plurality of pieces of image data of the entire pedestal coordinate system obtained by different photographing, a portion where the shape or position of the region indicated by the shadow region candidate does not match as described above is determined. It may be excluded from the region candidates.

  When the shadow region candidate is specified, the shadow region determination unit 112 specifies a shadow region from among the shadow region candidates that have been left last by the above-described shadow region candidate determination process (step S105). The shadow area determination unit 112 specifies a shadow area from among shadow area candidates in the paper image based on one of the first paper image 31 and the second paper image 32.

  As a specific example of the process of specifying a shadow area from among shadow area candidates, the image processing apparatus 1 holds a data table that stores the number of shadow determination flags for each pixel in the pedestal coordinate system. Then, the shadow area determination unit 112 specifies a pixel in the pedestal coordinate system corresponding to the paper coordinate system of the pixel specified as the shadow area candidate 41-1, and casts one shadow determination flag for the pixel. Record on the table. Similarly, the shadow area determination unit 112 specifies a pixel in the pedestal coordinate system corresponding to the paper coordinate system of each pixel specified as the shadow area candidate 41-2, the shadow area candidate 42-2, and the shadow area candidate 42-1. One shadow determination flag is voted for each pixel, and one shadow determination flag for each pixel recorded in the data table is added. The shadow area determination unit 112 determines whether the number of shadow determination flags voted for each pixel in the pedestal coordinate system is based on the paper images (first paper image 31 and second paper image 32) used in the above-described shadow area candidate determination processing. Each pixel of the pedestal coordinate system having the number (in the present embodiment, the shadow determination flag = 2) is specified as a pixel corresponding to the shadow area. In addition, if a pixel forming a shadow area in each pixel in the pedestal coordinate system can be specified, a pixel forming a shadow area in each pixel in the paper coordinate system corresponding to the pixel can also be specified. The number of shadow determination flags, which is an evaluation condition when specifying a pixel corresponding to a shadow area, is not limited to the number equal to the number of used paper images as described above. Alternatively, the value may be any value less than the number of used paper images. After this processing, the updated shadow correction table may be applied to captured image data, and the above processing may be repeatedly performed using the image data. In this case, the number of shadow determination flags serving as evaluation conditions is set to an arbitrary value at first, and the evaluation conditions are set so as to match the number of images or to match an arbitrary value as the above-described repeated processing proceeds. The threshold may be increased.

  The control unit 111 of the image processing apparatus 1 may output an alarm to the user when the shadow area determination unit 112 specifies the shadow area. The alarm may be given by, for example, a sound or a character display.

  The luminance correction table generation unit 113 calculates a luminance correction coefficient by which the luminance value of each pixel included in the shadow area in the pedestal coordinate system is multiplied. As an example, the luminance correction table generation unit 113 determines that the luminance value of a pixel included in the shadow area of the pedestal coordinate system is x in a certain paper image, and that the luminance value of another pixel image is shifted in the pedestal coordinate system. Assuming that the luminance value of a pixel that does not become a shadow area at the same position in the paper coordinate system corresponding to the X pixel is y, a luminance correction coefficient indicating a value of y ÷ x is calculated. The luminance correction table generation unit 113 generates a luminance correction table indicating the correspondence between the identification number of the pixel in the pedestal coordinate system and the luminance correction coefficient (step S106). In the above-described processing, the shadow area determination unit 112 determines a location where the difference in luminance value of the corresponding pixel is equal to or more than a predetermined threshold as a shadow area candidate based on the comparison of the respective sheet images, and The pixels in the pedestal coordinate system when the number of paper images determined as shadow area candidates is equal to or greater than a predetermined value are determined as shadow areas. Then, the luminance correction table generation unit 113 determines whether the first pixel (for example, FIG. 4) determined as a shadow area in the reading target in one of the sheet images obtained from the images placed on the pedestal 21 while being shifted. The brightness value of the lower right corner of the shadow area 41-2 of the No. 4 is determined by the corresponding second pixel (pixel at the position corresponding to the first pixel) which is not determined to be the shadow area in the reading target in the other sheet image. Thus, a brightness correction table is generated which holds a brightness correction coefficient to be converted into a brightness value of, for example, the pixel at the lower right corner of the shadow area 42-1 in FIG. 4 for all pixels in the shadow area.

  Then, the shadow reduction processing unit 114 performs a shadow reduction process of multiplying the luminance value of each pixel included in the shadow area by a luminance correction coefficient for the corresponding pixel (step S107). Thereby, the brightness value of each pixel of the paper coordinate system corresponding to each pixel of the pedestal coordinate system of the shadow area is adjusted, and the shadow area in the first paper image 31 and the second paper image 32 is reduced. For example, if the luminance value x of the pixel included in the shadow area is multiplied by a luminance correction coefficient represented by y ÷ x, the luminance value of the pixel included in the shadow area becomes y, and the influence of the shadow is reduced. Thereafter, even when the image of the sheet 3 is taken at another occasion, if the position of the shadow does not move, the shadow area can be reduced using the generated luminance correction table.

  The image processing apparatus 1 performs a predetermined process using the first paper image 31 and the second paper image 32 in which the shadow area has been reduced. The predetermined process may be, for example, a character recognition process or an image storage process.

  According to the above processing, even if an unexpected shadow enters the reading target, the shadow area can be deleted from the paper image obtained by photographing the reading target. Also, if the same processing (shadow reduction processing) is performed each time on the image data of the entire pedestal coordinate system from the next shooting, the shadow area can be permanently deleted unless it is affected by a new unexpected shadow. it can.

  Note that the image processing apparatus 1 may reduce the shadow area from each sheet 3 using n or more sheets 3. In this case, the image processing apparatus 1 scans the n sheets 3 to obtain n view images. However, it is assumed that n ≧ 2. The visual field image is an image obtained by scanning the entire visual field of the photographing unit 22 and is defined as image data of the entire pedestal region. The image processing apparatus 1 corrects and extracts the distortion of the specified sheet 3 from the n sheets of the visual field images, and obtains n sheet images of the nth sheet image from the first sheet image.

  The shadow area determination unit 112 of the image processing apparatus 1 determines, for each set of n−1 of the first paper image 31 and the other paper images 32, 33,. Is calculated. The coordinate system of each sheet image is a unified coordinate system with a corner of the sheet as the origin. The shadow area determination unit 112 specifies a pixel in the pedestal coordinate system corresponding to a pixel in the paper coordinate system in which the difference in luminance value is equal to or greater than a predetermined value, votes one shadow determination flag for the pixel, and enters the shadow determination flag in the data table. Record. The shadow area determination unit 112 votes for the same shadow determination flag for each of the n-1 sets. More specifically, in this process, first, based on the paper image 31, a paper image 31 and a set other than the paper image 31 (that is, from the paper image 32 to the paper image 3n), and n-1 sets, In the set, when the difference between the pixel values at the same position in the paper coordinate system is viewed, and when the difference is large, the pixel of the pedestal coordinate system corresponding to the position of the paper image 31 is specified, and for that pixel, One shadow determination flag is voted and recorded in the data table. This is based on the paper image 3n, such as a paper image 32 based on the paper image 32 and a group other than the paper image 32, and a paper image 33 based on the paper image 33 and a group other than the paper image 33. The process is repeated for the sheet image 3n and a group other than the sheet image 3n. The shadow area determination unit 112 specifies, as a shadow area, an area of a pixel for which n shadow determination flags have been voted among the pixels in the pedestal coordinate system. The shadow reduction process for the shadow area is the same as described above. The number of shadow determination flags, which is an evaluation condition when specifying a pixel corresponding to a shadow area, is set to a number equal to the number n of used paper images as described above, and is set to be equal to or more than the number of used paper images. Alternatively, it may be set to any value less than the number of used paper images or more. After this processing, the updated shadow correction table may be applied to captured image data, and the above processing may be repeated using the image data. In this case, the number of shadow determination flags serving as evaluation conditions is set to an arbitrary value at first, and the evaluation conditions are set so as to match the number of images or to match an arbitrary value as the above-described repeated processing proceeds. The threshold may be increased. In addition, the present process is performed on all of the n images, but may be performed by selecting an arbitrary two-image set.

  Note that the image processing apparatus 1 may perform the correction necessity determination processing of the luminance correction coefficient as described below, and delete the shadow area from the paper image obtained by photographing the reading target. Note that an alarm may be output to the user when it is determined that the correction is required by this process. The alarm may be given by, for example, a sound or a character display.

  First, the image processing apparatus 1 scans n original sheets to obtain n view images (n ≧ 2). The image processing apparatus 1 corrects and extracts the distortion of the specified original paper portion from each of the n sheets of the visual field image, and obtains n sheets of paper images. The image processing apparatus 1 specifies two sets of the n sheet images, calculates the difference between the pixel values at the same pixel position in all the two sets, and sets the difference to be large even in one set. In some cases, it is determined that the luminance correction coefficient needs to be corrected.

  More specifically, the image processing apparatus 1 sets the first sheet n and the set n-1 other than the first sheet (that is, each sheet image from the second sheet to the n-th sheet) among the n sheet images. , The difference between the pixel values at the same position in the paper coordinate system in each set n−1 is calculated. When there is at least one set having a large difference in luminance of the corresponding pixel among the sets n−1, the image processing apparatus 1 determines each pixel having a large difference in luminance as a shadow region candidate, and It is determined that a brightness correction coefficient needs to be generated or corrected for the shadow region identified from the region candidate.

In the description of each process of the image processing apparatus 1 described above, the image processing apparatus 1 generates a paper image on which distortion correction has been performed. It suffices if the relationship between the corresponding pixels of the paper image can be specified, and the difference in luminance value between the pixels can be determined.
Further, the image processing apparatus 1 determines the difference in luminance value for each pixel of each sheet image in the above-described luminance correction coefficient correction necessity determination process. It may be calculated between images. Alternatively, the image processing apparatus 1 may calculate the difference between the corresponding pixels of each corresponding sheet image and the difference between the average values in the vicinity of the pixel of interest after performing the blurring process, the reduction process, and the like of the sheet image.

  The image processing apparatus 1 calculates the difference between the luminance values of the pixels between the paper images in the above-described luminance correction coefficient correction necessity determination process. It may be determined whether or not the luminance correction coefficient needs to be corrected based on.

  Further, in order to cope with the overall change in illuminance in the paper image, the image processing apparatus 1 focuses on a region corresponding to the background of the original in the paper image (a portion having a high luminance distribution) so that the luminance distribution becomes substantially equal. After the conversion, the necessity determination processing of the luminance correction coefficient may be performed.

  If the image processing apparatus 1 performs the correction necessity determination process of the luminance correction coefficient using the unknown document, the pixel having a significantly small luminance value (a pixel assumed to be black printing) or the pixel having a small luminance value is determined. A continuous area (pixels assumed to be preprints such as ruled lines or entry components) may be excluded from the shadow area candidates. This makes it possible to exclude a region that is not the original background region, and improve the reliability of the determination.

  When the image processing apparatus 1 performs the correction necessity determination processing of the luminance correction coefficient using a known document, the image processing apparatus 1 may use format information registered in advance. In this case, the image processing apparatus 1 may exclude areas such as the preprint area and the entry column from the shadow area candidates based on the format information. As a result, the processing of determining whether or not the luminance correction coefficient needs to be corrected may be performed after excluding an area that is not the original background area. As a result, the reliability of the determination is improved as compared with the case where the luminance correction coefficient correction necessity determination process is performed on an unknown document.

  Regardless of whether the document is unknown or known, the image processing apparatus 1 may exclude the portion protruding from the field-of-view image from the shadow region candidates and perform the correction necessity determination processing of the brightness correction coefficient.

  Note that the photographing unit 22 of the image input device 2 may be constituted by a two-dimensional sensor or a line sensor.

  If a large white sheet can be prepared as the document, the image processing apparatus 1 scans only one sheet of paper and treats an arbitrary area reflected in a certain area in the view image as the first document. An arbitrary area reflected in the other area is regarded as a second original (the same original as the first original), and a difference such as a luminance value is calculated, and the above-described luminance correction coefficient correction necessity determination processing is performed. You may do so.

<Second embodiment>
8 is a functional block diagram of the image processing apparatus according to the second embodiment.
The hardware configuration of the image processing device 1 according to the second embodiment is the same as that of the first embodiment. The functions of the image processing apparatus 1 according to the second embodiment are different from those of the first embodiment in that a print portion removing unit 115 is provided in addition to the functions of the image processing apparatus 1 according to the first embodiment.

The print location removing unit 115 specifies a pixel having a luminance value less than a predetermined value representing a print location on the reading target. For example, this pixel is a place where black ink is applied and a place where characters are written. A print location removing unit that corrects the pixel to the luminance of the background other than the print location may be provided. For example, this process is a process of replacing with a luminance value of a background portion near the printing location.
In this case, the shadow area determination unit 112 determines a location where the brightness value does not match that of another paper image as a shadow area based on the comparison of each paper image after correcting the printing location to the luminance of the background other than the printing location. . As a result, it is possible to reduce an event that a print location is erroneously determined as a shadow area.
The print location removing unit 115 performs a process of matching the luminance value of the preprinted area and the area such as the entry column with the luminance of the base other than the print location using the format information recorded in advance. You may do so.

  Further, the shadow area determination unit specifies a pixel having a luminance value less than a predetermined value representing the print location in the paper image, and then excludes the print location from the target of the pixel specifying the shadow area candidate and removes the shadow area candidate other than the print location. May be specified.

<Third embodiment>
FIG. 9 is a functional block diagram of the image processing apparatus according to the third embodiment.
The hardware configuration of the image processing device 1 according to the third embodiment is the same as that of the first embodiment. The functions of the image processing apparatus 1 according to the third embodiment are different from those of the first embodiment in that an overall luminance matching unit 116 is provided in addition to the functions of the image processing apparatus 1 according to the first embodiment.

  For example, when acquiring a dark image in which the illumination 7 is dark and the influence of the dark illumination 7 is reflected on an object to be read, the overall luminance matching unit 116 corrects the entire image to be bright. Specifically, the overall brightness matching unit 116 compares the brightness of the unprinted area of the other image with the brightness of the unprinted area of the reference image among the images generated in each of the plurality of shootings. Is the same level throughout. For example, the reference image may be the first paper image 31 previously stored as a reference image at a timing when the illuminance of the illumination 7 is appropriate. Another image may be the second paper image 32. The overall brightness matching unit 116 performs a process of matching the brightness of the unprinted area of another sheet image to be compared with the brightness of the unprinted area of the reference paper image to the brightness of the unprinted area of the reference paper image. Do. The overall brightness matching unit 116 may use a histogram of pixel values to adjust the brightness corresponding to the background portion of the paper so as to be substantially equal overall among a plurality of paper images. The luminance correction processing of the sheet image in the overall luminance matching unit 116 may use a known luminance correction technique such as a correction processing using a histogram.

  Then, the shadow area determination unit 112 compares the brightness of the non-printed area of the other paper image with the brightness of the non-printed area of the other paper image based on a comparison of each paper image. A portion where the value difference is equal to or larger than a predetermined threshold is determined as a shadow region.

  By performing such processing, it is possible to specify a shadow area after improving the phenomenon that the entire reading target becomes dark when the illumination 7 is dark, and to specify the shadow area with higher accuracy. .

<Fourth embodiment>
In the above-described processing, the shadow area is specified by comparing each paper image detected from the two image data, but the luminance value of the pixel is compared between each paper image detected from a larger number of image data than that. The shadow area may be specified. For example, in the image input device 2, the sheet 3 is placed on the pedestal 21 with the relative position with respect to the photographing unit 22 shifted five times. Each time, the image is taken and the image data is output. Then, the image processing apparatus 1 may compare the five sheet images to specify the shadow area.

FIG. 10 is a diagram showing different states in which the sheet is placed on the pedestal while being shifted from the relative position with respect to the photographing unit, in a single figure.
Specifically, the shadow area determination unit 112 determines, in each paper image corresponding to the image data generated in each of the plurality of shootings, a pixel having a difference equal to or more than a first threshold from another paper image as a first shadow area candidate. Is determined. The shadow area determination unit 112 determines, as a second imaging area candidate, a pixel in the first shadow area candidate whose difference value from another pixel is equal to or greater than a second threshold value that is even larger than the first threshold value. The shadow area determination unit 112 recognizes a pedestal coordinate system having the upper left corner of the pedestal 21 as the origin 210 and a sheet coordinate system having the upper left corner of the sheet 3 as the origin 310. The control unit 111 of the image processing apparatus 1 stores a correspondence between the pedestal coordinate system and a sheet coordinate system that differs depending on each sheet image. The shadow area determination unit 112 assigns one first shadow determination flag (first shadow determination value) to a pixel in the pedestal coordinate system corresponding to the pixel serving as the first imaging area candidate specified in the paper coordinate system of the paper 3 Vote. Further, the shadow area determination unit 112 sets a second shadow determination flag (second shadow determination value) to a pixel in the pedestal coordinate system corresponding to a pixel that is a second imaging area candidate specified in the paper coordinate system of the paper 3. One vote. Since the second imaging region candidate is also included in the first imaging region candidate, the first determination flag and the second determination flag are respectively voted for the pixel of the pedestal coordinate system corresponding to the pixel that is the second imaging region candidate It will be. The shadow area determination unit 112 performs this processing for all pixels of each of the plurality of paper images.

  The shadow area determination unit 112 immediately specifies a pixel for which the second shadow determination flag has been voted in each pixel indicated by the pedestal coordinate system as a shadow area. In addition, the shadow area determination unit 112 counts the number of pixels for which the second shadow determination flag is not voted and only the first shadow determination flag is voted for each pixel indicated by the pedestal coordinate system. When the counted number of flags is equal to or larger than the threshold value, the shadow area determination unit 112 specifies a pixel of each paper image corresponding to the pixel of the pedestal coordinate system as a shadow area.

  According to the above processing, when the sheet image is compared with the image data when the sheet 3 is placed on the pedestal 21 by shifting the relative position with respect to the photographing unit 22 a plurality of times, when the luminance difference is relatively low, Is determined as a shadow area only on a pixel in the paper coordinate system corresponding to a pixel in the pedestal coordinate system determined to have a difference between many paper pixels. Therefore, the shadow area can be determined with higher accuracy.

FIG. 11 is a diagram illustrating a minimum configuration of the image processing apparatus.
As shown in FIG. 11, the image processing apparatus 1 may include at least the shadow area determination unit.
The photographing area determination unit photographs the object to be read placed at a position shifted from the relative position with respect to the photographing unit, and determines a predetermined difference in the luminance value based on a comparison of the luminance values of the images generated in each of the plurality of photographings. A portion equal to or larger than the threshold value is determined as a shadow region.

  The image processing apparatus described above has a computer system inside. A program for causing the image processing device to perform each of the above-described processes is stored in a computer-readable recording medium of the image processing device, and the computer of the image processing device reads and executes the program. The above processing is performed. Here, the computer-readable recording medium refers to a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, or the like. Alternatively, the computer program may be distributed to a computer via a communication line, and the computer that has received the distribution may execute the program.

  Further, the program may be for realizing a part of the function of each processing unit described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

DESCRIPTION OF SYMBOLS 1 ... Image processing apparatus 2 ... Image input apparatus 3 ... Paper 4 ... Furniture 21 ... Pedestal 22 ... Imaging part 23 ... Arm part 24 ... Base part 101 ...・ CPU
102 ROM
103 RAM
104 ・ ・ ・ HDD
105 ... User interface 106 ... Communication module 111 ... Control unit 112 ... Shadow area determination unit 113 ... Brightness correction table generation unit 114 ... Shadow reduction processing unit 115 ... Printed portion removal Unit 116: Overall luminance matching unit

Claims (9)

An image processing apparatus for processing image data output from an image input device having a pedestal and an imaging unit that captures an object to be read placed in the pedestal region,
Based on a comparison of the brightness values of the respective images generated in each of the plurality of times of shooting, the location where the difference in brightness value is equal to or greater than a predetermined threshold A shadow area determination unit that determines a shadow area;
A brightness correction table generation unit that generates a brightness correction table that holds a brightness correction coefficient for multiplying the brightness value based on the brightness value of the pixel in the shadow region,
And shadow reduction processor for multiplying the luminance correction coefficient for the corresponding pixel is recorded on the luminance correction table to each pixel in the shadow region of the image generated by the photographing,
An image processing apparatus comprising: A print location removal unit that specifies a pixel having a luminance value less than a predetermined value representing a print location in the read target, and corrects the pixel to the luminance of the background other than the print location,
The shadow area determination unit, the other image and places claim determines a shadow area 1 a does not luminance value match based on a comparison of the image after correcting the print position to the underlying luminance outside the printing position The image processing apparatus according to any one of the preceding claims. A print location removal unit that specifies a pixel having a luminance value less than a predetermined value representing a print location in the read target, and corrects the pixel to the luminance of the background other than the print location,
The image according to claim 1 , wherein the shadow area determination unit specifies a pixel having a luminance value less than a predetermined value representing a print location on the reading target, and removes the print location from a processing target to determine the shadow area. Processing equipment. If the brightness of the unprinted area of the other image is different from the brightness of the unprinted area in the reference image of the images generated in each of the plurality of shootings, the reference and the An overall brightness matching unit that matches the brightness of the unprinted area of the other image with the brightness of the unprinted area of the other image,
The shadow area determination unit, based on the comparison of each image after matching the brightness of the unprinted area of the other image to the brightness of the unprinted area of the reference image, The image processing device according to any one of claims 1 to 3 , wherein a portion where the difference is equal to or greater than a predetermined threshold is determined as a shadow region. The shadow area determination unit assigns a shadow determination value to a pixel in the pedestal coordinate system corresponding to a pixel determined as a shadow area in each image generated in each of the plurality of shootings, and the shadow determination value is assigned. The image processing device according to any one of claims 1 to 3 , wherein the shadow area is determined based on the number of times the brightness value has changed and a brightness difference at a location where the difference between the brightness values is equal to or greater than a predetermined threshold. To any one of claims 1 to 5 for processing the image data the sliding mechanism for shifting the relative position is output from the image input device provided in the pedestal and said object to be read and the imaging unit The image processing apparatus according to any one of the preceding claims. To any one of claims 1 to 5 for processing the image data output of said image input apparatus for photographing a read object placed by shifting the relative position of the imaging unit by a user to the pedestal The image processing apparatus according to any one of the preceding claims. A processing method of an image processing device that processes image data output from an image input device having a pedestal and an imaging unit that captures an object to be read placed in the pedestal region,
Based on a comparison of the brightness values of the respective images generated in each of the plurality of times of shooting, the location where the difference in brightness value is equal to or greater than a predetermined threshold Judge as a shadow area,
Based on the brightness value of the pixel in the shadow area, a brightness correction table that holds a brightness correction coefficient by which the brightness value is multiplied is generated,
Processing method of multiplying the luminance correction coefficient for the corresponding pixel is recorded on the luminance correction table to each pixel in the shadow region of the image generated by the photographing. A computer of an image processing device that processes image data output from an image input device having a pedestal and an imaging unit that captures an object to be read placed in the pedestal region,
Based on a comparison of the brightness values of the respective images generated in each of the plurality of times of shooting, the location where the difference in brightness value is equal to or greater than a predetermined threshold Shadow area determining means for determining a shadow area,
A luminance correction table generating unit that generates a luminance correction table holding a luminance correction coefficient by which the luminance value is multiplied based on a luminance value of a pixel in the shadow area;
Shadow reduction processing means for multiplying the luminance correction coefficient for the corresponding pixel is recorded on the luminance correction table to each pixel in the shadow region of the image generated by the photographing,
A program to function as

Images