JP2023017562A - Image processing device, control method, and program - Google Patents

Abstract

To provide an image processing device, etc. capable of properly executing processing based on a document conveyed obliquely when it is conveyed.SOLUTION: The device comprises: an image input unit for reading a document and inputting an image of the document, and a control unit. In a case where the document inputted by the image input unit is oblique, the control unit executes processing on the image on the basis of the distribution of the pixel values of pixels included in a rectangular region whose one edge is made of pixels constituting an edge in each edge of the image.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to an image processing device and the like.

Traditionally, MFPs (Multi-Function Peripherals/Printers) have been widely used to read documents placed on an automatic document feeder (ADF) and output or save the images of the scanned documents. It is Techniques for determining whether or not a read document is plain (blank) have also been proposed.

For example, a technique has been proposed in which the area of the document read to determine whether the document is plain is an area inside the area of the entire document (see, for example, Patent Documents 1 and 2). ). Further, image data obtained by reading a document is divided into a plurality of regions, a luminance variance value included in the image data of each divided region is obtained, and the variance value is used for each region. A technique has been proposed for determining whether or not content is included in a document, and determining whether or not a document includes content based on the determination result of each area (see, for example, Patent Document 3).

JP 2006-279094 A JP 2015-128288 A JP 2014-215775 A

Here, in the methods described in Patent Literature 1 and Patent Literature 2, even though characters and figures are described outside the area of the document that is read to determine whether the document is blank, , there is a possibility that the document is erroneously determined to be blank when there is no description in the area.

Also, when the color of the member positioned under the document is different from the color of the paper of the document, when the plain document is conveyed obliquely, the multifunction device obtains an image as shown in FIG. 27(a). do. In this case, as shown in FIG. 27(b), a change in luminance occurs between the edge portion of the document and the portion other than the edge. Here, if the technology described in Patent Document 3 is used, as shown in FIG. be done. As a result, there is a risk that the document will be determined to contain content even though the document is blank.

SUMMARY An advantage of some aspects of the disclosure is to provide an image processing apparatus and the like capable of appropriately executing processing based on an image of a document when the document is conveyed obliquely.

In order to solve the above-described problems, an image processing apparatus according to the present disclosure includes an image input unit that reads a document and inputs an image of the document, and a control unit. characterized in that, when an input document is oblique, processing is performed on each side of the image based on the distribution of pixel values of pixels included in a rectangular area having pixels constituting the side as one side. and

A control method according to the present disclosure is a control method for an image processing apparatus for reading a document and inputting an image of the document, wherein when the document is oblique, pixels forming each side of the image are The method is characterized by including a step of performing processing on the image based on a distribution of pixel values of pixels included in a rectangular area with one side.

A program according to the present disclosure reads a document and inputs an image of the document into a computer of an image processing apparatus. It is characterized by realizing a function of executing processing on the image based on the distribution of pixel values of pixels included in the area.

According to the present disclosure, when a document is conveyed obliquely, it is possible to appropriately execute processing based on the image of the document.

1 is an external perspective view of an image processing apparatus according to a first embodiment; FIG. 2 is a diagram for explaining the functional configuration of the image processing apparatus according to the first embodiment; FIG. FIG. 2 is a flowchart for explaining the flow of main processing executed by the image processing apparatus according to the first embodiment; FIG. 5 is a flowchart for explaining the flow of document color/background color determination processing in the first embodiment; FIG. 7 is a diagram for explaining document color/background color determination processing in the first embodiment; FIG. 7 is a diagram for explaining document color/background color determination processing in the first embodiment; FIG. 7 is a diagram for explaining document color/background color determination processing in the first embodiment; FIG. 7 is a diagram for explaining document color/background color determination processing in the first embodiment; FIG. 7 is a diagram for explaining document color/background color determination processing in the first embodiment; FIG. 7 is a diagram for explaining document color/background color determination processing in the first embodiment; FIG. 5 is a flowchart for explaining the flow of edge detection/edge cancellation processing in the first embodiment; FIG. 4 is a diagram for explaining edge detection/edge cancellation processing in the first embodiment; FIG. 5 is a flow chart for explaining the flow of blank area determination processing in the first embodiment; FIG. 7 is a diagram for explaining blank area determination processing in the first embodiment; FIG. 5 is a flow chart for explaining the flow of skew correction processing in the first embodiment; FIG. 5 is a diagram for explaining skew correction processing in the first embodiment; It is a figure for explaining an example of operation in a 1st embodiment. It is a figure for explaining an example of operation in a 1st embodiment. It is a figure for explaining an example of operation in a 1st embodiment. It is a figure for explaining an example of operation in a 1st embodiment. It is a figure for demonstrating the outline|summary in 2nd Embodiment. It is a figure for demonstrating the outline|summary in 2nd Embodiment. FIG. 11 is a flowchart for explaining the flow of main processing executed by an image processing apparatus according to the second embodiment; FIG. 11 is a flowchart for explaining the flow of document color/background color determination processing in the second embodiment; FIG. 11 is a flowchart for explaining the flow of main processing executed by an image processing apparatus according to the third embodiment; FIG. 11 is a flow chart for explaining the flow of second blank area determination processing in the third embodiment; It is a figure for demonstrating the conventional example.

An embodiment for carrying out the present disclosure will be described below with reference to the drawings. The following embodiments are examples for explaining the present disclosure, and the technical scope of the invention described in the claims is not limited to the following descriptions.

[1. First Embodiment]
[1.1 Functional configuration]
A first embodiment will be described with reference to the drawings. FIG. 1 is an external perspective view of an image processing apparatus 10 according to the first embodiment, and FIG. 2 is a block diagram showing the functional configuration of the image processing apparatus 10. As shown in FIG.

The image processing apparatus 10 is a digital multifunction peripheral (MFP: Multi-Function Peripheral/Printer) having a copy function, a print function, a scan function, an e-mail transmission function, and the like. Further, the image processing apparatus 10 may be an image forming apparatus capable of forming an image on recording paper. As shown in FIG. 2, the image processing apparatus 10 according to the present embodiment includes a control unit 100, an image input unit 120, an image forming unit 130, a display unit 140, an operation unit 150, a storage unit 160, and a communication unit. 190 .

The control unit 100 is a functional unit for controlling the image processing apparatus 10 as a whole. The control unit 100 implements various functions by reading and executing various programs stored in the storage unit 160, and is configured by, for example, one or more arithmetic units (CPU (Central Processing Unit)). . Also, the control unit 100 may be configured as an SoC (System on a Chip) having a plurality of functions among the functions described below.

The control unit 100 also functions as an image processing unit 102 by executing a program stored in the storage unit 160 . The image processing unit 102 performs processing related to various images. For example, the image processing unit 102 executes sharpening processing and gradation conversion processing on the image read by the image input unit 120 .

The image input unit 120 inputs image data to the image processing apparatus 10 . For example, the image input unit 120 is configured by a scanner device or the like capable of reading an image of a document, generating image data of the document, and inputting the data to the image processing apparatus 10 . The scanner device converts an image into an electrical signal using an image sensor such as a CCD (Charge Coupled Device) or CIS (Contact Image Sensor), and quantizes and encodes the electrical signal to generate digital data.

The image forming unit 130 forms (prints) an image on a recording medium such as recording paper. The image forming unit 130 is configured by, for example, a printing device such as a laser printer using an electrophotographic method. For example, the image forming unit 130 feeds recording paper from the paper feed tray 132 in FIG. 1, forms an image on the surface of the recording paper, and discharges the recording paper from the paper discharge tray 134 .

The display unit 140 displays various information. The display unit 140 is configured by a display device such as an LCD (Liquid crystal display), an organic EL (electro-luminescence) display, a micro LED (Light Emitting Diode) display, or the like.

The operation unit 150 receives operation instructions from the user. The operation unit 150 includes input devices such as various key switches and touch sensors that detect input by contact (touch). A general detection method such as a resistive film method, an infrared method, an electromagnetic induction method, or an electrostatic capacitance method may be used as a method for detecting an input in the touch sensor. Note that the image processing apparatus 10 may be equipped with a touch panel in which the display unit 140 and the operation unit 150 are integrally formed.

The storage unit 160 stores various programs and data necessary for the operation of the image processing apparatus 10 . The storage unit 160 is configured by, for example, a storage device such as an SSD (Solid State Drive), which is a semiconductor memory, or an HDD (Hard Disk Drive).

The communication unit 190 communicates with an external device via a LAN (Local Area Network) or a WAN (Wide Area Network). The communication unit 190 is configured by, for example, a communication device such as a NIC (Network Interface Card) used in a wired/wireless LAN, and a communication module.

[1.2 Flow of processing]
Main processing executed by the control unit 100 of the image processing apparatus 10 in this embodiment will be described with reference to FIG. The processing shown in FIG. 3 is executed by the control unit 100 reading out a program stored in the storage unit 160, for example.

In particular, the processing shown in FIG. 3 is executed when a function such as a copy function, a scan function, or an e-mail transmission function that reads an original and outputs the image of the read original to print paper or a file is used. be done.

First, the control unit 100 acquires an input image (step S100). An input image is an image input to the image processing apparatus 10, for example, a scanned image of a document. In step S100, control unit 100 acquires an image of one of the documents sent to image input unit 120 by an automatic document feeder (ADF) and read by image input unit 120. .

Subsequently, the control unit 100 determines whether or not the document has been conveyed obliquely (step S102). As a method of determining whether a document is conveyed obliquely, for example, a plurality of document detection sensors are arranged in the image processing apparatus 10 along the document width direction forming a right angle to the document conveyance direction, and each document detection sensor can be used to determine whether or not the document has been detected. For example, in the case where two document detection sensors are arranged, the control unit 100 controls that the document is conveyed obliquely when one of the document detection sensors detects the document and the other document detection sensor does not detect the document. It is determined that It should be noted that existing methods other than the method described above may be used as a method for determining whether or not the document has been conveyed obliquely. For example, the method described in JP-A-2009-51585 can be used. .

If the document is not conveyed obliquely, the control unit 100 performs blank determination by a predetermined method (step S102; No). On the other hand, if the document is fed at an angle, whether the color of the document (document color, background color of the document) differs from the color of the material on the back of the document (background color) when the document is read (document color/background color determination process) is executed (step S102; Yes→step S104). In this embodiment, the color of the document is referred to as the document color, and the color of the member behind the document is referred to as the background color. The document color/background color determination process will be described with reference to FIG.

First, the control unit 100 converts an input image into a monochrome image (grayscale image), and selects one of the top edge (top edge), right edge (right edge), bottom edge (bottom edge), and left edge (left edge) of the converted input image. A pixel value histogram of the side is generated (step S120). A pixel value histogram of one side is a histogram based on pixel values of pixels forming a side portion of one of the top edge, right edge, bottom edge, and left edge of the input image.

For example, the control unit 100 calculates the length (region width) obtained by multiplying the length of the long side of the document (input image) by a predetermined ratio α (eg, α=3%). Subsequently, the control unit 100 sets a side of interest and a rectangular area surrounding pixels included up to a position separated from the side by the area width. Furthermore, the control unit 100 acquires pixel values (for example, luminance values) of pixels included in the set rectangular area, and generates a histogram indicating the number of pixels for each pixel value.

For example, if the document is an A4 sheet, the control unit 100 sets the area width to 0.89 cm, which is 3% of the length of the long side (29.7 cm). Further, for example, if the document is an A3 sheet, the control unit 100 sets the region width to 1.26 cm, which is 3% of the length of the long side (42.0 cm).

Furthermore, the control unit 100 calculates the number of pixels corresponding to the area width. For example, if the document is A4 paper and the resolution of the input image is 300 dpi (dots per inch), the area width of 0.89 cm corresponds to about 105 pixels. In this case, the control unit 100 sets, for each side of the input image after conversion into a monochrome image, a rectangular area surrounding pixels included up to a position 105 pixels away from the side.

The processing of step S120 described above will be specifically described with reference to FIGS. 5 and 6. FIG. FIG. 5A is a diagram showing an example of an input image when the background color and the document color are different. Note that the case where the background color and the document color are different means the case where the density levels of the document color and the background color cannot be said to be the same level.

The input image shown in FIG. 5A is an image of a document conveyed obliquely, and includes an area E100 where the document is read, an area E101 (upper left) and an area E102 (upper right) where the member on the back of the document is read. ), area E103 (lower left), and area E104 (lower right).

FIG. 5(b) is a diagram showing a rectangular area surrounding pixels included up to a position separated by the number of pixels corresponding to the area width from each side of the input image after conversion into a monochrome image.

FIG. 5B shows, as rectangular areas, an upper rectangular area E110 set based on the upper edge, a left rectangular area E111 set based on the left edge, and a right edge rectangular area E111 set based on the right edge. FIG. 11 is a diagram showing E112 and a bottom rectangular area E113 set based on the bottom side;

Let r be the number of pixels in the vertical direction of the input image, c be the number of pixels in the horizontal direction, and α be the ratio of the length of the long side to be multiplied. In the case of FIG. 5B, since the input image is horizontally long, the long side is the horizontal direction. Therefore, the rectangular area corresponding to each side corresponds to the area surrounding each side and a position separated by c×α pixels obtained by multiplying c, which is the number of pixels in the horizontal direction of the long side, by a predetermined ratio α. .

A rectangular area E110 corresponding to the upper end (upper side) of the input image and a rectangular area E113 corresponding to the lower end (lower side) of the input image are c×α pixels long and c pixels wide. The number of pixels included in the rectangular regions E110 and E113 is c×c×α. On the other hand, a rectangular area E111 corresponding to the left edge (left side) and a rectangular area E112 corresponding to the right edge (right side) of the input image are rectangular areas of r pixels in the vertical direction and c×α pixels in the horizontal direction. The number of pixels included in the rectangular regions E111 and E112 is r×c×α. Note that the value of α may be determined in advance or may be set by the user.

FIG. 5(c) is a histogram generated based on pixel values of pixels included in one of the rectangular regions E110, E111, E112, and E113 shown in FIG. 5(b). It is a figure which shows. As shown in FIG. 5C, the histogram has the pixel value on the horizontal axis and the number of pixels on the vertical axis.

For example, the control unit 100 generates a histogram indicating the distribution of luminance values of pixels forming the edge of the input image. In the example of the histogram shown in FIG. 5(c), the number of pixels is large in the middle luminance value portion E120 and the high luminance value portion E121. In this case, it indicates that the peripheral portion of the input image is mainly composed of pixels with medium luminance values and pixels with high luminance values.

FIG. 6A shows a case where a rectangular area is set in the same manner as in FIG. , and each rectangular area (E130, E131, E132, E133). FIG. 6B is based on pixel values (luminance values) of pixels included in one of the rectangular regions E130, E131, E132, and E133 shown in FIG. 6A. FIG. 10 is a diagram showing a histogram generated by In the example of the histogram shown in FIG. 6B, the number of pixels is large in the portion E140 with high luminance values. In this case, the peripheral portion of the input image is mainly composed of pixels with high luminance values.

Returning to FIG. 4, the control unit 100 determines whether or not there is an interval (bin) including a pixel value having a maximum value equal to or greater than a threshold from the histogram of the side portion generated in step S120 (step S122). A threshold is, for example, a value of the number of pixels obtained by multiplying the number of pixels included in a rectangular area corresponding to each histogram by a predetermined ratio.

For example, let r be the number of pixels in the vertical direction of the input image, c be the number of pixels in the horizontal direction, and let α be a predetermined ratio to the length of the long side of the document (input image). Let β1 be a predetermined ratio to the number of pixels included in the upper and lower rectangular areas, and β2 be a predetermined ratio to the number of pixels included in the rectangular areas corresponding to the right and left sides. When the direction of the long side is the horizontal direction, the control unit 100 sets a threshold value TH1 for the upper rectangular area and the lower rectangular area or a threshold value TH2 for the right rectangular area and the left rectangular area by the following calculation. demand.
TH1=c×c×α×β1
TH2=r×c×α×β2

Here, β1 and β2 are values such as β1=10% and β2=10%, for example. Note that β1 and β2 may be set in advance, or may be set by the user. Also, β1 and β2 may be different values.

When there is a section including a pixel value having a maximum value equal to or greater than the threshold, the control unit 100 selects a section of several pixels (for example, 5 pixels) before and after the pixel value corresponding to the section from the histogram generated in step S120. Remove the value (step S122; Yes→step S124). For example, if the maximum pixel value that is equal to or greater than the threshold value is 128, the control unit 100 sets the value of any interval between 123 and 133 to zero.

Subsequently, the control unit 100 determines whether or not there is a number of sections including a pixel value having a maximum value equal to or greater than the threshold value in the histogram from which the values of several pixels before and after the pixel value having the maximum value are removed. Determine (step S126). When there is a section including a pixel value having a maximum value equal to or greater than the threshold value, the control unit 100 judges that the document color and the background color are different because there are multiple peaks in the histogram (step S126; Yes→step S128). In other words, the control unit 100 determines that the document color and the background color are different if there is even one histogram determined to have multiple peaks at the top, bottom, left, and right ends.

On the other hand, if the control unit 100 determines in step S122 or step S126 that there is no section including a pixel value having a maximum pixel value equal to or greater than the threshold value, it determines whether all four sides of the input image have a plurality of peaks. (step S122; No→step S130, step S126; No→step S130). If all four sides are determined, the control unit 100 determines that the document color and the background color are not different (step S130; Yes→step S132). On the other hand, if the controller 100 has not determined any of the four sides, it returns to step S120 (step S130; No→step S120). In this case, the control unit 100 selects one of the undetermined sides and generates a pixel value histogram.

In this way, the control unit 100 determines whether or not there is a histogram with multiple peaks (mountains) by executing the processes from step S120 to step S132 described above.

Here, in step S122, the control unit 100 can determine that there is no peak in the histogram by determining that there is no section containing a pixel value that is the maximum value equal to or greater than the threshold. Also, in step S126, the control unit 100 can determine that there is only one peak in the histogram by determining that there is no section including a pixel value having a maximum value equal to or greater than the threshold value. Thus, when the number of peaks in the histogram is 1 or less, the control unit 100 determines that the document color and the background color do not differ on the side corresponding to the histogram. Furthermore, when the number of peaks is 1 or less on all sides, the control unit 100 determines that the document color and the background color of the input image are not different.

The processing from step S122 to step S132 described above will be specifically described with reference to FIGS. 7 and 8. FIG. FIG. 7(a) is the same diagram as the histogram shown in FIG. 5(c). T150 in FIG. 7A is the threshold (the number of pixels) for the histogram shown in FIG. 7A. Further, E150 in FIG. 7A indicates the range of the section of the pixel value having the maximum value and the section of several pixels before and after the section. Here, since the pixel value having the maximum value is equal to or greater than the threshold value T150, the histogram shown in FIG. 7A is a histogram including pixel values having the maximum value equal to or greater than the threshold value.

FIG. 7(b) is a histogram after removing the values included in E150 from the histogram shown in FIG. 7(a). Note that the threshold T152 in FIG. 7B is the same value as the threshold T150 in FIG. 7A. In FIG. 7B, the pixel value indicated by the arrow A152 is the pixel value having the maximum value equal to or greater than the threshold value in the histogram shown in FIG. 7B. That is, the histogram shown in FIG. 7(a) has two peaks. In this case, the control unit 100 determines that the document color and the background color of the input image are different.

FIG. 8(a) is the same diagram as the histogram shown in FIG. 6(b). T160 in FIG. 8A is the threshold (the number of pixels) for the histogram shown in FIG. 8A. Further, E160 in FIG. 7A indicates the range of the pixel value section having the maximum value and the section of several pixels before and after the section. Here, since the pixel value having the maximum value is equal to or greater than the threshold value T160, the histogram shown in FIG. 8A is a histogram including pixel values having the maximum value equal to or greater than the threshold value.

FIG. 8(b) is a histogram after removing the values included in E160 from the histogram shown in FIG. 8(a). Note that the threshold T162 in FIG. 8B is the same value as the threshold T160 in FIG. 8A. Here, among the pixel values included in FIG. 8B, there is no threshold having a value equal to or greater than the threshold T162. That is, the histogram shown in FIG. 8A does not have two peaks. In this case, the control unit 100 determines that the document color and the background color do not differ for the sides corresponding to this histogram.

FIG. 9 shows (a) a rectangular area corresponding to the input image and each side, (b) a histogram of the upper rectangular area, and (c) a histogram of the lower rectangular area when the document color and the background color are different. , (d) a histogram of the rectangular area at the left end, and (e) a histogram of the rectangular area at the right end. Here, TH1 is the threshold for the upper rectangular area and the lower rectangular area, and TH2 is the threshold for the left rectangular area and the right rectangular area. As shown in (b) to (e) of FIG. 9, when the document color and the background color are different, the histogram of the rectangular area corresponding to each side has a plurality of peaks.

FIG. 10 shows (a) the rectangular area corresponding to the input image and each side, (b) the histogram of the upper rectangular area, (c) the histogram of the lower rectangular area, when the document color and the background color do not differ. (d) A histogram of the rectangular area at the left end, and (e) a histogram of the rectangular area at the right end. Here, TH1 is the threshold for the upper rectangular area and the lower rectangular area, and TH2 is the threshold for the left rectangular area and the right rectangular area. As shown in (b) to (e) of FIG. 10, when the document color and the background color are not different, the histogram of the rectangular area corresponding to each side has only one peak.

Returning to FIG. 3, the control unit 100 determines whether or not the determination result in step S104 indicates that the document color and the background color are different (step S106).

If the determination result in step S104 is that the document color and the background color are different, the control unit 100 performs processing (edge detection/edge cancellation processing) for deleting edges generated on the boundary line of the document from the input image. Execute (step S106; Yes→step S108). Edge detection/edge cancellation processing will be described with reference to FIG.

First, the control unit 100 acquires an image (edge-extracted image, differential image) in which edges are detected from the input image (step S140). For example, the control unit 100 acquires an image in which edges are detected as follows.

(1) The control unit 100 converts the input image into a monochrome image (grayscale image).
(2) The control unit 100 applies an edge detection operator to the monochrome image (grayscale image) of the input image.
(3) The control unit 100 executes binarization processing on the image to which the edge detection operator is applied.

In (2), the control unit 100 uses, for example, a Prewitt edge detection operator or a Sobel edge detection operator as the edge detection operator. Also, the control unit 100 uses, for example, a 3×3 matrix size as the size of the edge detection operator. By performing the processing of (2), an image in which the edge portion of the input image is expressed in white can be obtained.

Furthermore, in (3), the control unit 100 executes binarization processing (for example, simple binarization processing) on the image obtained by executing the processing of (2). Thereby, the control unit 100 converts the image acquired by executing the process (2) into an image having either white (pixel value is 1) or black (pixel value is 0) pixels. can be done. The control unit 100 thus acquires an image containing only white or black obtained by executing the processes (1) to (3) described above as an edge extraction image (differential image).

Subsequently, the control unit 100 initializes the variable R by substituting 1 (step S142). The variable R is a variable indicating the vertical position of the pixel of interest in the differential image, and takes a value of 1≤R≤R_MAX. However, R_MAX is the height of the input image (the number of pixels in the vertical direction of the input image).

Further, the control unit 100 assigns 1 to the variable C and 0 to the variable count, thereby initializing each variable (step S144). A variable C is a variable indicating the horizontal position of the pixel of interest in the differential image, and takes a value of 1≦C≦C_MAX. However, C_MAX is the width of the input image (the number of pixels in the horizontal direction of the input image).

Subsequently, the control unit 100 accesses the Rth row of the differential image (step S146). That is, the vertical position (row) of the differential image that the control unit 100 pays attention to is the R-th row. Further, the control unit 100 accesses the R-th row and the C-th column of the differential image (step S148). That is, the horizontal position (row) of the differential image that the control unit 100 pays attention to is the C-th row. As a result, the control unit 100 sets the pixel located in the R-th row and the C-th column among the pixels forming the differential image as the pixel of interest.

Subsequently, the control unit 100 determines whether or not the pixel value of the pixel of interest is 1 (the pixel of interest is white) (step S150). If the pixel value is not 1, the control unit 100 transitions to step S160, which will be described later (step S150; No). On the other hand, when the pixel value is 1, the control unit 100 sets the value of the variable count to count+1 (increments the variable count) (step S150; Yes→step S152).

Furthermore, if the value of the variable count is 1, the control unit 100 temporarily stores the current pixel position in the storage unit 160 as the position of the one end pixel (step S154; Yes→step S156). If the value of the variable count is not 1, the control unit 100 temporarily stores the current pixel position in the storage unit 160 as the other end pixel position (step S154; No→step S158). . That is, the control unit 100 updates the position of the other edge each time a pixel with a pixel value of 1 is detected.

Subsequently, the control unit 100 increments the variable C by setting the value of the variable C to C+1 (step S160), and determines whether or not the value of the variable C matches C_MAX (step S162). If the value of variable C does not match C_MAX, control unit 100 returns to step S148 (step S162; No→step S148).

By repeating the processing from step S148 to step S162 in this way, the position of the pixel at one end is stored and the position of the pixel at the other end is updated.

On the other hand, when the value of the variable C matches C_MAX, the control unit 100 deletes (cancels) the edge (step S162; Yes→step S164). Edge deletion processing is processing for replacing edge pixels with pixels similar to surrounding pixels. Thereby, the control unit 100 can prevent the edge from being recognized by the user.

Note that the control unit 100 may provide a condition for deleting edges. For example, when the position of the pixel on the one end side in the R-th row is adjacent to the position of the pixel on the one end side in the R-1-th row, the control unit 100 deletes the edge on the one end side in the R-th row. You may Similarly, when the position of the pixel on the other end side in the R-th row is adjacent to the position of the pixel on the other end side in the (R−1)-th row, the control unit 100 edge can be deleted. In this way, the control unit 100 can delete the closest edge group (adjacent edges) from each side of the rectangular reading range.

For example, the control unit 100 acquires the position of the pixel at one end and the position of the pixel at the other end from the storage unit 160, and converts the pixel at the corresponding position in the input image to the color of the pixels surrounding the pixel ( For example, the average pixel value of 8 pixels in the surrounding top, bottom, left, right, and diagonal). Furthermore, the control unit 100 sets the pixel values of pixels at positions corresponding to the position of the pixel at one end and the position of the pixel at the other end in the differential image to 0 (black pixels). By doing so, the control unit 100 can cancel edges with the smallest and largest column numbers among the rows in which edges exist in the input image.

Note that the control unit 100 may omit the process in step S164 when the pixel value of 1 is 0 or 1 in the row of interest (R-th row).

Subsequently, the control unit 100 increments the variable R by setting the value of the variable R to R+1 (step S166), and determines whether or not the value of the variable R matches R_MAX (step S168). If the value of the variable R does not match R_MAX, the controller 100 returns to step S144 (step S168; No→step S144). On the other hand, when the value of R matches R_MAX, the control unit 100 ends the edge detection/edge cancellation processing (step S168; Yes).

The processing from step S148 to step S168 will be specifically described with reference to FIG. FIG. 12A is a diagram showing an input image and an area R180 for three lines in the input image. FIG. 12(b) is an enlarged view of the region R180 shown in FIG. 12(a). In the processing from step S148 to step S162, the pixels of the input image are acquired column by column in the row of interest as indicated by the horizontal arrows in the region E181 in FIG. This is the process of obtaining the position of the outermost edge in the row. The outermost edges are the leftmost edge and the rightmost edge in the row. In this embodiment, when obtaining the position of the outermost edge, a differential image is used instead of the input image.

FIG. 12(c) is a diagram showing a differential image of the input image and a region R182 for three lines in the differential image. Moreover, FIG.12(d) is the figure which expanded area|region R182 shown in FIG.12(c). In the differential image, edge pixels in the input image are shown as white pixels (pixels with a pixel value of 1), and pixels other than the edge in the input image are shown as black pixels (pixels with a pixel value of 0).

The control unit 100 acquires the pixels of the row of interest one by one, as indicated by the horizontal arrows in the area E183 of FIG. Get position. For example, the control unit 100 sequentially moves the pixel of interest from the first column of the r-th row to the C_MAX-th column of the r-th row, and determines whether the pixel value of the pixel of interest is 1 or not.

In FIG. 12D, the r-th row, fourth column is the edge pixel. Therefore, the control unit 100 stores the position of the r-th row and the fourth column as the position of the pixel at one end. In FIG. 12D, the r-th row (C_MAX−3)-th column is the edge pixel detected last in the r-th row. Therefore, the control unit 100 stores the position of the r-th row (C_MAX−3)-th column as the position of the pixel at the other end. Then, the control unit 100 deletes (cancels) only the edges located in the r-th row, the fourth column and the r-th row (C_MAX−3)-th column, that is, the outermost edge among the edges in the input image. do.

Further, the control unit 100 deletes the outermost edges for all rows of the input image and the differential image by performing similar processing on the r+1th row, the r+2th row, and other rows. .

If the determination result in step S104 in FIG. 3 is that the document color and the background color do not differ, the control unit 100 omits (does not execute) the edge detection/edge cancellation process in step S108 (step S106; No).

Returning to FIG. 3, the control unit 100 executes processing for determining whether or not the document is plain (blank determination processing) (step S110). The blank area determination processing will be described with reference to FIG. 13 .

First, the control unit 100 counts the number of edges (step S180). For example, the control unit 100 counts the number of edges by counting the number of white pixels included in the differential image.

Here, when edge detection/edge cancellation processing is being performed in step S108, the control unit 100 counts white pixels (pixels with a pixel value of 1) included in the differential image after edge cancellation. On the other hand, when the edge detection/edge cancellation processing is not executed, the control unit 100 acquires a differential image based on the input image, and counts white pixels (pixels with a pixel value of 1) included in the differential image.

Subsequently, the control unit 100 determines whether or not the number of edges is equal to or less than a predetermined threshold (step S182). The threshold for the number of edges may be a predetermined value, or may be the number of pixels corresponding to the number of pixels of the input image (for example, 1% of the number of pixels of the input image). Also, the threshold for the number of edges may be configurable by the user.

If the number of edges is equal to or less than the threshold, the controller 100 determines that the input document is a plain document (step S182; Yes→step S184). On the other hand, if the number of edges is greater than the threshold, the control unit 100 determines that the input document includes content (document not plain) (step S182; No→step S186).

The processing from step S180 to step S186 will be specifically described with reference to FIG. FIG. 14(a) is a diagram showing a differential image of an input image when the document color is different from the background color and the document is plain. In this embodiment, the outermost edge is deleted by edge detection/edge cancellation processing. Therefore, in this embodiment, the edges are calculated based on the differential image shown in FIG. As shown in FIG. 14(b), almost no edges remain in the differential image after the edges have been removed. Therefore, when the document color and the background color of the document are different and the document is plain, there is a high possibility that the control unit 100 determines that the read document is plain.

FIG. 14(c) is a diagram showing a differential image of the input image when the document color is different from the background color and the document contains content. FIG. 14(d) is a diagram showing a differential image obtained by deleting the outermost edge from the differential image shown in FIG. 14(c). As shown in FIG. 14(d), even if the outermost edge is removed, the edge of the content remains. Therefore, in the case where the document color and the background color are different and the document contains the content, the control unit 100 is more likely to determine that the read document is the document containing the content.

Returning to FIG. 3, when the determination result in step S110 indicates that the document is plain, the control unit 100 omits the skew correction process (step S112; Yes). On the other hand, when the determination result in step S110 indicates that the document includes content, the control unit 100 executes skew correction processing (step S112; No→step S114). The skew correction process is a process of correcting the skew of the document appearing in the input image. The skew correction processing will be described with reference to FIG.

The control unit 100 acquires a differential image before deleting the outermost edge (step S190). For example, when the differential image is acquired in step S140 of FIG. 11 or step S180 of FIG. 13, the control unit 100 may acquire the acquired differential image again. Note that the control unit 100 may obtain a differential image by applying the edge detection operator to the input image again.

Subsequently, the control unit 100 sets a rectangle such that the top edge, the bottom edge, the left edge, and the right edge of the edges included in the differential image are in contact, and based on the position of the rectangle, the input image is cropped (step S192).

Furthermore, the control unit 100 performs skew correction on the cropped input image (step S192). For example, the control unit 100 detects an edge forming a straight line from the edges included in the differential image, and obtains the angle formed by the straight line and the main scanning direction or the sub-scanning direction, thereby determining the angle of the conveyed document. Ask for Further, the control unit 100 rotates the document by the angle of the document in the direction opposite to the direction in which the document is tilted so that the document is tilted at 0°. As a result, the image of the document becomes an image of an angle along the direction of the main scanning direction or the sub-scanning direction.

The processing from step S190 to step S194 will be specifically described with reference to FIG. FIG. 16A is a diagram showing a differential image of the input image before removing the outermost edge. FIG. 16(b) is an input image after cropping the input image based on the differential image shown in FIG. 16(a). A dotted line E190 shown in FIG. 16(b) indicates a rectangle in which the top edge, the bottom edge, the left edge, and the right edge of the differential image shown in FIG. 16(a) are in contact. FIG. 16(c) is an image obtained by correcting the tilt of the cropped input image shown in FIG. 16(b). Thus, the control unit 100 can correct the skew of the image of the document.

Note that the above-described processing is executed for each document conveyed by the automatic document feeder. Therefore, even when a blank document or a document containing content is conveyed obliquely by the automatic document feeder, blank determination and skew correction processing are executed for each document.

[1.3 Operation example]
Next, an operation example in this embodiment will be described with reference to FIGS. 17 to 20. FIG. 17A and 17B are diagrams showing an operation example when a blank document conveyed obliquely is read when the color of the document and the background color are different.

FIG. 17A is a diagram showing an input image. As shown in FIG. 17A, when the original color and the background color are different, the input image includes an area E1000 where the original color appears, an area E1001 where the background color appears, an area E1001 where the background color appears (upper left), an area E1002 (upper right), and an area E1003 (bottom left) and area E1004 (bottom right) are included.

FIG. 17B is a diagram (differential image) when edges are detected from the input image. When the document color and the background color are different, the boundary portion between the document color and the background color is detected as an edge, as shown in FIG. 17(b). FIG. 17C is a diagram showing a differential image obtained by canceling (deleting) the outermost edge from the differential image. Based on the differential image shown in FIG. 17(c), it is determined whether or not the document is plain.

Comparing the number of edge pixels, the differential image shown in FIG. 17(c) has fewer pixels than the differential image shown in FIG. 17(b). By determining whether or not the document is plain based on the differential image shown in FIG. become more sexual.

18A and 18B are diagrams showing an operation example when a document including content conveyed obliquely is read when the color of the document and the background color are different.

FIG. 18(a) is a diagram showing an input image. As shown in FIG. 18A, when the original color and the background color are different, the input image includes an area E1010 where the original color appears, an area E1011 where the background color appears (upper left), an area E1012 (upper right), and an area E1012 (upper right). E1013 (bottom left) and area E1014 (bottom right) are included.

FIG. 18(b) is a diagram showing a differential image of the input image shown in FIG. 18(a). FIG. 18(c) is a differential image obtained by deleting the outermost edge from the differential image shown in FIG. 18(b). Based on the differential image according to FIG. 18(c), it is determined whether the document is plain or not, but as shown in FIG. Includes edges. By determining whether or not the document is plain based on the differentiated image shown in FIG. more likely to

FIG. 18(d) is an input image after cropping the input image shown in FIG. 18(a). A dotted line L1010 in FIG. 18D indicates a rectangle in which the top edge, the bottom edge, the left edge, and the right edge are in contact with each other in the differential image before edge deletion. Further, by subjecting the input image after cropping shown in FIG. 18D to the skew correction process, the input image shown in FIG. output.

19A and 19B are diagrams showing an operation example when a blank document conveyed obliquely is read when the color of the document and the background color are the same. FIG. 19(a) is a diagram showing an input image. L1020 in FIG. 19A indicates the range where the document was placed. As shown in FIG. 19A, the position of L1020 of the input image hardly includes lines corresponding to edges (boundary lines) of the document.

FIG. 19(b) is a diagram showing a differential image of the input image shown in FIG. 19(a). If the document color and the background color do not differ, since the outermost edge is not deleted from the differential image, it is determined whether or not it is solid based on the differential image shown in FIG. 19(b). Since the differential image shown in FIG. 19B contains almost no edges, there is a high possibility that the read document is correctly determined to be a blank document.

FIG. 20 is a diagram showing an operation example when a document containing content conveyed obliquely is read when the color of the document and the background color do not differ. FIG. 20(a) is a diagram showing an input image. FIG. 20(b) is a diagram showing a differential image of the input image shown in FIG. 20(a). If the document color and the background color do not differ, since the outermost edge is not deleted from the differential image, it is determined whether or not it is plain based on the differential image shown in FIG. 20(b). Since the differential image shown in FIG. 20(b) includes the edge of the content portion, there is a high possibility that the read document is correctly determined as the document containing the content.

FIG. 20(c) is the input image after cropping the input image shown in FIG. 20(a). A dotted line L1030 in FIG. 20(c) indicates a rectangle in which the upper edge, the lower edge, the left edge, and the right edge touch in the differential image shown in FIG. 20(b). Further, by subjecting the input image after cropping shown in FIG. 20C to skew correction processing, the input image shown in FIG. An input image after skew correction processing is output.

In addition to the above description, the order of steps may be changed within a consistent range, and conditions for executing processing may be added.

For example, the edge detection/edge cancellation processing shown in FIG. 11 is shown as processing for deleting edges row by row, but the control unit 100 determines the positions of the pixels at one end and the pixels at the other end for all rows. After detecting the position, the process of deleting edges may be performed. By doing so, the control unit 100 can determine the edge that is the outermost edge and has continuity with respect to the entire input image, and delete the group of the edge.

Further, the edge detection/edge cancellation processing shown in FIG. 11 is shown as processing for deleting edges row by row, but may be processing for deleting edges column by column. In this case, the control unit 100 cancels the edges with the minimum and maximum row numbers among the columns in which the edges of the input image exist.

As described above, according to the image processing apparatus of the present embodiment, when the document color and the background color are different, the process of deleting the edge of the input image is executed, and when the document color and the background color are not different, Do not remove edges from the input image. Further, according to the image processing apparatus of the present embodiment, it is possible to switch whether or not to execute processing for deleting edges of an input image depending on whether or not the document color and the background color are different. Thus, it is possible to appropriately determine whether or not the input document is blank.

[2. Second Embodiment]
Next, a second embodiment will be described. Unlike the first embodiment, the second embodiment suppresses erroneous detection of blank determination by reading an extra range outside the range in which the document is arranged when reading the document. form. In this embodiment, FIG. 3 of the first embodiment is replaced with FIG. 23, and FIG. 4 of the first embodiment is replaced with FIG. Note that the same processes are denoted by the same reference numerals, and the description thereof is omitted.

Generally, when a document is read, the size of the document and the area where the document is placed are detected by an image processing device, and the detected area is read. However, when the document is conveyed obliquely, the size of the document and the area where the document is placed may not be detected correctly.

A specific example will be described with reference to FIG. FIG. 21(a) is a diagram showing a case where a portion of the document containing the framed content C200 is not read. A line L200 in FIG. 21A indicates the range read by the image input unit 120, that is, the range of the input image. A line L201 in FIG. 21A indicates the edge of the document. Here, there may be an area of the document outside the read range (line L200), such as area E200 in FIG. 21(a). However, an area such as the area E200 is not included in the input image, and as a result, part of the edge L201 of the document is not included in the input image.

FIG. 21(b) shows the input image in the state shown in FIG. 21(a). Moreover, FIG.21(c) shows the differential image of the input image shown in FIG.21(b). A range (A) shown in FIG. 21(c) indicates a range that includes the framed content C200 shown in FIG. 21(a).

Here, as shown in FIG. 21(c), when the frame line content C200 is detected as an edge pixel and the frame line content C200 is the outermost edge in the differential image. There is In such a case, the edges forming the content C200 of the frame line are deleted as shown in FIG. Become. As a result, even a document containing content C200 with a frame line may be determined to be a blank document.

Therefore, in the present embodiment, when reading a document, the range further outside the range in which the document is arranged is also read. An overview of this embodiment will be described with reference to FIG. FIG. 22(a) shows an input image in the state shown in FIG. 21(a) when a range outside the range where the document is arranged is read. An image of the entire document is included in the input image by reading a range outside the range in which the document is arranged.

FIG. 22(b) shows a differential image of the input image shown in FIG. 22(a). FIG. 22(c) shows a differential image after deleting the outermost edge of the differential image shown in FIG. 22(b).

In the differential image shown in FIG. 22B, the outermost edge is an edge based on the edge of the document (edge generated at the boundary line of the document). Therefore, even if the outermost edge is removed, the edge due to the content of the border is not removed, as shown in FIG. 22(c). Therefore, it is less likely that the document is determined to be a blank document.

In this manner, the image processing apparatus 10 can suppress erroneous detection of blank determination by additionally scanning (reading) the range outside the range in which the document is arranged.

Processing executed by the image processing apparatus 10 according to the present embodiment will be described with reference to FIGS. 23 and 24. FIG. First, main processing executed by the control unit 100 of the image processing apparatus 10 according to the present embodiment will be described with reference to FIG.

In this embodiment, the control unit 100 of the image processing apparatus 10 acquires an input image after extending the reading range of the document to the outside of the document (step S200→step S100). For example, the control unit 100 detects the size of the document conveyed to the image input unit 120 and the area where the document is placed, and sets the reading range of the document based on the detection result. Furthermore, the control unit 100 expands the set reading range of the document to the outside of the reading range (for example, about 5 mm outside). This allows the control unit 100 to cause the image input unit 120 to additionally read the periphery of the document (outer portion of the document).

Next, document color/background color determination processing in this embodiment will be described with reference to FIG. In this embodiment, the control unit 100 obtains an image obtained by clipping the input image, and generates a pixel value histogram of one side of the clipped image (step S220→step S222). 4, the control unit 100 converts the input image into a monochrome image (grayscale image), and converts the input image into one of the upper edge, right edge, lower edge, and left edge of the clipped image. A histogram is generated based on the pixel values of the pixels forming the side portions of .

In this embodiment, since the reading range of the document is expanded in step S200, the sides of the input image mainly include pixels of the background color. Therefore, even if the pixel value histogram is generated in this state, there is a possibility that the pixel values of the original color pixels are hardly included in the histogram.

Therefore, the control unit 100 cuts out the input image and generates a histogram based on the cut out input image so that the pixel values of the document colors are included in the histogram. For example, the control unit 100 cuts out the input image in step S220 so that the input image excludes the area expanded in step S200. As a specific example, if the control unit 100 has set a reading range that is 5 mm wider than the initial reading range in step S200, then in step S220 an image obtained by cutting out a 5 mm periphery of the input image is acquired. As in the first embodiment, the control unit 100 determines whether or not the generated histogram has multiple peaks.

Further, in the edge detection/edge cancellation processing in step S108 of FIG. 23, the control unit 100 scans an extra input image including a range outside the range in which the document is arranged (for example, FIG. 22(a) ) is to be processed. Since the input image includes all the edges of the document, the control unit 100 can delete edge pixels of the document in the edge detection/edge cancellation processing in step S108. Thereby, the control unit 100 can avoid deleting the content. Also, in the skew correction processing in step S114, the control unit 100 crops the input image based on the edge pixels of the edge of the document. This allows the control unit 100 to appropriately crop the input image based on the edge of the document.

As described above, according to the present embodiment, by additionally scanning the periphery of the document, it is possible to appropriately perform blank determination even for a document containing content including a frame line.

[3. Third Embodiment]
Next, a third embodiment will be described. The third embodiment is an embodiment using a blank area determination method different from that of the first embodiment. This embodiment replaces FIG. 3 of the first embodiment with FIG. Note that the same processes are denoted by the same reference numerals, and the description thereof is omitted.

The flow of processing in this embodiment will be described with reference to FIGS. 25 and 26. FIG. First, with reference to FIG. 25, main processing executed by the control unit 100 of the image processing apparatus 10 in this embodiment will be described.

In this embodiment, the control unit 100 determines whether or not the document color and the background color are different in step S106. Processing is executed (step S106; No→step S110).

On the other hand, when the control unit 100 determines that the document color and the background color are different, it executes a second plain color determination process (step S106; Yes→step S300). The second blank area determination process will be described with reference to FIG.

First, the control unit 100 acquires an image (edge-extracted image, differential image) in which edges are detected from the input image (step S320). The process in step S320 is the same process as step S140 in FIG.

Subsequently, the control unit 100 assigns 1 to the variable R indicating the vertical position of the pixel of interest in the differential image for initialization, and assigns 0 to the variable contents_tmp for counting rows containing content. Initialize (step S322). The control unit 100 also assigns 1 to a variable C indicating the horizontal position of the pixel of interest in the differential image for initialization, and assigns 0 to a variable count (step S324). The possible ranges of the variable R and the variable C are the same as those of the variable R and the variable C in the first embodiment.

Subsequently, the control unit 100 accesses the Rth row of the differential image (step S326), and further accesses the Cth column of the Rth row (step S328).

Subsequently, the control unit 100 determines whether the pixel value of the pixel of interest is 1 (step S330). When the pixel value of the target pixel is 1, the control unit 100 sets the value of the variable count to count+1 (increments the variable count) (step S330; Yes→step S332).

Subsequently, the control unit 100 determines whether or not the value of the variable count is 3 (step S334). A case where the value of the variable count is 3 is a case in which it is considered that there are edge pixels due to content in addition to edge pixels based on the edge of the document in the R-th row of the differential image. The fact that the value of the variable count is 3 corresponds to the fact that the R-th row of the input image includes 3 or more edges (3 or more edge pixels).

If the value of the variable count is not 3, the value of the variable C is set to C+1 to increment the variable C (step S334; No → step S336), and it is determined whether the value of the variable C matches C_MAX. (step S338). Even if the control unit 100 determines in step S330 that the pixel value is not 1, it also executes the processing in steps S336 and S338 (step S330; No→step S336→step S338).

If the value of variable C does not match C_MAX, control unit 100 returns to step S328 (step S338; No→step S328). On the other hand, when the value of the variable C matches C_MAX, the control unit 100 increments the variable R by setting the value of the variable R to R+1 (step S338; Yes→step S344), and the value of the variable R becomes R_MAX. (step S346). If the value of the variable R does not match R_MAX, the control unit 100 returns to step S324 (step S346; No→step S324). On the other hand, when the value of R matches R_MAX, the control unit 100 determines that the document is a blank document (step S346; Yes→step S348).

When determining that the value of the variable count is 3 in step S334, the control unit 100 sets the value of the variable contents_tmp to contents_tmp+1, thereby incrementing the variable contents_tmp (step S334; Yes→step S340). Furthermore, the control unit 100 determines whether or not the variable contents_tmp matches the predetermined variable contents (step S342).

The variable contents is a predetermined threshold that satisfies 0<=contents<=R_MAX. For example, the value of the variable contents is automatically calculated from the value of R_MAX and the document size (for example, the control unit 100 sets the variable contents to the value of R_MAX×0.1). Note that the variable contents may be determined in advance by an administrator or the like of the image processing apparatus 10 . Also, the variable contents may be settable by the user of the image processing apparatus 10 .

If the variable contents_tmp matches the variable contents, the control unit 100 determines that the document contains content (step S342; Yes→step S350). On the other hand, when the variable contents_tmp does not match the variable contents, the control unit 100 executes the process in step S344 (step S342; No → step S344). With such processing, the control unit 100 can shift to the processing of the next line at the stage of determining that there is an edge other than the edge based on the edge of the document in the R-th line. As a result, the control unit 100 can reduce the number of processing steps and processing time.

As described above, the image processing apparatus according to the present embodiment switches the process of determining whether or not the document is plain depending on whether or not the color of the document and the background color are different. In particular, the second plain color determination process in the present embodiment counts the number of edge pixels included in the line of interest in the differential image without deleting the edges, and determines whether the document is a plain document. This is the process of determining whether or not. Since the process of deleting edges is not executed, the processing amount of the image processing apparatus and the blank area determination can be suppressed. Therefore, the user can reduce the performance required for the image forming apparatus.

[4. Modification]
The present invention is not limited to the embodiments described above, and various modifications are possible. That is, the technical scope of the present invention also includes embodiments obtained by combining technical means appropriately modified within the scope of the present invention.

In addition, although the above-described embodiments are described separately for convenience of explanation, it is of course possible to combine them within the technically possible range. For example, the second embodiment and the third embodiment may be combined. In this case, it is possible to determine whether or not the document is blank without reading the periphery of the document in excess and without executing the process of deleting the edges.

Further, in the above-described embodiment, when setting the rectangular area used for calculating the histogram, the area surrounding each side and the position obtained by multiplying the length of the long side by the predetermined ratio α has been described. As a result, a histogram is generated based on the pixel values of the pixels present at positions where the distance from the side is up to a predetermined ratio α to the length of the long side. Note that the distance from the side when setting the rectangular area may be calculated based on the length of each of the long side and the short side. In this case, as a rectangular area corresponding to the side of interest, an area surrounding the side of interest and a position obtained by multiplying the length of the side of interest by a predetermined ratio α is set.

In addition, the program that operates in each device in the embodiment is a program that controls the CPU and the like (a program that causes the computer to function) so as to implement the functions of the above-described embodiments. Information handled by these devices is temporarily stored in a temporary storage device (for example, RAM) during processing, and then stored in storage devices such as various ROMs (Read Only Memory) and HDDs. The data is read, corrected, and written by the CPU.

Examples of recording media for storing programs include semiconductor media (eg, ROM, non-volatile memory cards, etc.), optical recording media/magneto-optical recording media (eg, DVD (Digital Versatile Disc), MO (Magneto Optical Disc), MD (Mini Disc), CD (Compact Disc), BD (Blu-ray (registered trademark) Disc), etc.), magnetic recording media (e.g., magnetic tape, flexible disc, etc.), etc. . By executing the loaded program, the functions of the above-described embodiments are realized. In some cases, inventive features are realized.

When distributed to the market, the program can be stored in a portable recording medium for distribution, or transferred to a server computer connected via a network such as the Internet. In this case, of course, the storage device of the server computer is also included in the present invention.

10 image processing apparatus 100 control unit 102 image processing unit 120 image input unit 130 image forming unit 140 display unit 150 operation unit 160 storage unit 190 communication unit

Claims (8)

An image input unit for reading a document and inputting an image of the document, and a control unit,
The control unit
When the document input by the image input unit is oblique, processing is performed on each side of the image based on the distribution of pixel values of pixels included in a rectangular area having pixels constituting the side as one side. An image processing device characterized by: The control unit
determining whether the color of the document differs from the color of the member on the back of the document when the document is read, based on the distribution;
2. The image processing apparatus according to claim 1, wherein the processing is executed when the color of the document and the color of the member on the back surface are different. 3. The image processing apparatus according to claim 2, wherein the control unit does not execute the processing when the color of the document and the color of the back member do not differ. The image input unit reads the document including the outer portion,
The control unit is characterized in that the distribution is a distribution of pixel values of pixels included in a rectangular area of which one side is a pixel composing each side of an image obtained by cutting out an outer portion of the document. The image processing apparatus according to any one of claims 1 to 3. 5. The image processing apparatus according to any one of claims 1 to 4, wherein the process is a process of deleting an edge generated on a boundary line of the document from the image. 5. The processing according to any one of claims 1 to 4, wherein the processing determines whether or not the document is plain based on the number of lines in which edges appear in three or more pixels in the image. The image processing device according to . A control method for an image processing device that reads an original and inputs an image of the original, comprising:
performing processing on each side of the image based on a distribution of pixel values of pixels included in a rectangular area having pixels constituting the side as one side when the document is slanted. Characterized control method. In the computer of the image processing device that reads the document and inputs the image of the document,
When the document is slanted, each side of the image is processed on the basis of the pixel value distribution of the pixels included in the rectangular area with the pixels forming the side as one side. A program characterized by

Images