Image processing apparatus and image processing system
The image processing device addresses the challenge of determining document scan status and user-specific background processing by employing boundary detection and customizable correction processes, ensuring accurate image output for optical character recognition.
Patent Information
- Application Number
- JP2023073327
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-04-27
- Publication Date
- 2024-11-08
AI Technical Summary
Conventional image processing systems struggle to determine whether a document is scanned unfolded or with bent corners, and fixed background colors complicate user-specific processing requests.
An image processing device that includes boundary detection to differentiate between document and background areas, allowing selection from multiple background correction processes based on user settings and work content.
Enables determination of appropriate background area correction processes, outputting images tailored to user preferences and facilitating accurate optical character recognition.
Smart Images

Figure 2024158267000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an image processing device and an image processing system. [Background technology]
[0002] Document scanners scan a large number of documents at once and digitize the information. Some document scanners have a black background for the reading area to make it easier to identify the location of the document. Others have a white background to make the boundary between the document and the background less noticeable. Some document scanners also allow users to switch between black and white background colors.
[0003] In the prior art, there is a technology that can complement the rectangle of a document even when the document has a folded corner. By performing this process, the upper left corner of the document in the image can be easily detected, and optical character recognition (hereinafter referred to as "OCR") can be performed on a specific position on the document starting from the detected upper left corner. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2001-144946 A Summary of the Invention [Problem to be solved by the invention]
[0005] On the other hand, conventional technology complements the rectangle of the document and corrects the folds, making it impossible to distinguish between images scanned without folds and images scanned with folded corners. In particular, if you want to remove images scanned from folded documents, you have to check the images one by one.
[0006] Furthermore, if the background color is fixed, it becomes difficult to provide suitable processing for each system or each user's request.
[0007] The present invention has a plurality of background region correction processes, and outputs and provides an image suited to the user's desires. [Means for solving the problem]
[0008] In view of the above, the image processing device according to the present invention comprises: The image data read from the document by the image reading device is composed of a document area and a background area, a boundary detection means for detecting a boundary between the document area and the background area; an image processing means for selecting a background color replacement process for the background area detected by the boundary detection means from a plurality of background area correction processes; a correction determination means for determining which of the plurality of background region correction processes is to be used, The image processing means corrects the background area by the background area correction process selected in response to the determination by the correction determination means. Effect of the Invention
[0009] According to the image processing device of the present invention, it is possible to determine which of a number of background area correction processes to use based on the user's settings and the work to be done after scanning, and to output an image suited to the user's wishes. [Brief description of the drawings]
[0010] [Figure 1] FIG. 1 is a diagram showing an example of an image processing system to which an image processing apparatus according to an embodiment of the present invention can be applied. [Diagram 2] FIG. 1 is a diagram showing an example of the configuration of a sheet-feed scanner that is an embodiment of an image processing apparatus. [Diagram 3] FIG. 1 is a block diagram showing an example of the configuration of an image processing apparatus. [Figure 4] FIG. 4 is a diagram showing an example of a UI of a scan application in the embodiment. [Diagram 5] 11A and 11B are diagrams showing examples of image data, a background blackening processed image, and a non-rectangular area blackening processed image. [Figure 6] 6 is a flowchart showing a process for detecting a boundary between a document and a background. [Figure 7] 11 is a flowchart showing a blackening process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0011] Hereinafter, an image processing system including an image processing device and an information processing device connectable to the image processing device will be described with reference to the drawings.
[0012] Fig. 1 is a diagram showing an example of an image processing system according to an embodiment of the present invention. The image processing system in Fig. 1 is composed of a scanner 100, which is an example of an image processing device, and a personal computer (PC) 200, which is an example of an information processing device.
[0013] In Fig. 1, scanner 100 is an image reading device that reads image data from a document. Scanner 100 is communicably connected to a personal computer (PC) 200. Scanner 100 and PC 200 may be connected via a USB interface or the like, or may be connected via a network. The network may be either wired or wireless. Personal computer (PC) 200 controls scanner 100 from the outside.
[0014] The configuration and operation of the scanner 100 will be described below with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of a sheet-feed scanner showing one embodiment of the scanner 100. In this embodiment, a sheet-feed scanner that sequentially scans stacked documents (sheets) will be used for explanation.
[0015] As shown in FIG. 2, the scanner 100 includes an automatic document feeder (hereinafter referred to as "ADF") 101. A plurality of sheets are stacked on a sheet stacking tray 1, which is configured to be freely raised and lowered. A sheet stacking tray drive motor (not shown) raises and lowers the sheet stacking tray 1. A sheet detection sensor 3 detects that a sheet stacked on the sheet stacking tray 1 is at a sheet input position. A sheet stacking detection sensor 12 detects that a sheet is stacked on the sheet stacking surface 1a of the sheet stacking tray 1.
[0016] Further, the document jump-up detection sensor 35 includes a plurality of sensors arranged in a direction perpendicular to the sheet stacking surface 1a, and detects the jump-up of sheets stacked on the sheet stacking tray 1. For example, the document jump-up detection sensor 35 can detect the jump-up of a document that occurs when a stapled document or the like is stacked on the sheet stacking tray 1 and fed. This makes it possible to perform control such as stopping the feeding of the stapled document or the like.
[0017] The pickup roller 4, which is an example of a sheet pickup section, sends out a sheet on the sheet stacking table 1 from the sheet stacking table 1. A pickup roller drive motor (not shown) rotates the pickup roller 4 in a direction in which the pickup roller 4 picks up the sheet.
[0018] The pickup roller 4 can move to a sheet intake position and a retracted position above the sheet intake position, and is moved to the sheet intake position when taking in a sheet and is moved to the retracted position when taking in a sheet. The pickup roller 4 plays an auxiliary role in ensuring that separation and feeding by a separation roller pair 42, which will be described later, is performed. If the sheet on the sheet stacking table 1 is sent to the nip portion of the separation roller pair 42 by the pickup roller 4, separation and feeding by the separation roller pair 42 can be performed reliably.
[0019] In the separation roller pair 42, the feed roller 6 is driven by a feed motor (not shown) to rotate in a direction (feed direction) to feed the sheet downstream in the conveying direction. The separation roller 7 constantly receives a rotational force from the separation motor (not shown) via a torque limiter (slip clutch) (not shown) to rotate in a direction (separation direction) to push back the sheet upstream in the conveying direction.
[0020] When one sheet is present between the feed roller 6 and the separation roller 7, the torque in the direction in which the sheet is fed downstream in the conveying direction due to the frictional force between the sheet fed downstream in the conveying direction by the feed roller 6 and the separation roller 7 exceeds the upper limit of the torque in the direction in which the separation roller 7 pushes the sheet back upstream in the conveying direction, which is transmitted by the torque limiter described above. Therefore, the separation roller 7 rotates following the feed roller 6.
[0021] On the other hand, when there are multiple sheets between the feed roller 6 and the separation roller 7, the separation roller 7 receives rotation from the roller shaft in a direction to push the sheets back upstream in the conveying direction, so that sheets other than the topmost sheet are not conveyed downstream in the conveying direction.
[0022] In this way, due to the action of the feed roller 6 to feed the sheet downstream in the conveying direction and the action of the separation roller 7 to prevent the sheet from being conveyed downstream in the conveying direction, even if the sheets are overlapped and fed into the nip portion (contact portion between the feed roller 6 and the separation roller 7) formed between the feed roller 6 and the separation roller 7, only the topmost sheet is fed downstream in the conveying direction and the other sheets are not conveyed downstream in the conveying direction. As a result, the overlapping sheets are separated and fed.
[0023] The feed roller 6 and the separation roller 7 constitute a pair of separation rollers 42 (sheet separation section). In this embodiment, the separation roller pair 42 is used, but instead of the separation roller pair 42, a separation belt roller pair (not shown) in which either the feed roller 6 or the separation roller 7 is a belt may be used. Also, the separation roller 7 may be replaced with a separation pad that abuts against the sheet to prevent multiple sheets from being transported downstream. Alternatively, the separation roller 7 may be used to abut against the sheet like a separation pad without rotating.
[0024] The sheets stacked on the sheet stacking tray 1 are separated one by one and taken into the scanner 100 by the sheet pickup section composed of the pickup roller 4, the feeding roller 6, the separation roller 7, and the like thus configured.
[0025] Furthermore, by providing the double-feed detection sensor 30 at a position where the separated sheets pass (that is, downstream of the pair of separation rollers 42), it is possible to detect whether the sheets have been separated one by one by the sheet separation section.
[0026] A conveying motor (not shown) drives a sheet conveying section to convey the separated sheet to an image reading position where the image on the sheet is read by image reading sensors 14 and 15, and further to a discharge position.
[0027] The conveying motor also drives each roller so that the sheet conveying speed can be changed according to the optimum speed for reading the sheet and image reading settings such as the sheet resolution.
[0028] A nip gap adjustment motor (not shown) adjusts the gap between the feeding roller 6 and the separation roller 7, or the pressure (nip pressure) with which the feeding roller 6 presses against the separation roller 7 via the sheet. This allows the gap or pressure to be adjusted to suit the thickness of the sheet, allowing the sheet to be separated.
[0029] A registration clutch (not shown) transmits or blocks the rotational driving force of the conveying motor to registration rollers 18 (sheet conveying section). By stopping the rotation of the first registration roller pair consisting of registration rollers 17 and 18, the leading edge of the fed sheet is abutted against the nip portion of the registration roller pair to correct the skew of the sheet.
[0030] The second registration roller pair consisting of registration rollers 20 and 21, the conveying roller pair consisting of conveying rollers 22 and 23, the conveying roller pair consisting of conveying rollers 24 and 25, and the discharge roller pair consisting of discharge rollers 26 and 27 convey the sheet, and finally convey it to the discharge stacking section 44. The discharge sensor 16 detects the passage of the conveyed sheet. The two guide plates, the upper guide plate 40 and the lower guide plate 41, guide the sheet conveyed by the separation roller pair, the registration roller pair, each conveying roller pair, and the discharge roller pair.
[0031] The pre-registration sensor 32 is disposed upstream of the first registration roller pair and detects the sheet being fed. The post-registration sensor 34 is disposed downstream of the second registration roller pair and detects the sheet being transported. Furthermore, the registration sensor 33 is disposed downstream of the first registration roller pair and upstream of the second registration roller pair and detects the sheet being transported.
[0032] When the post-registration sensor 34 detects the sheet, a control unit (CPU 306 described later) issues an instruction to read the image to the image reading sensors 14, 15, and the image on the conveyed sheet is read according to the image reading setting. The image reading sensors 14, 15 are provided with platen rollers 14a, 15a, respectively, and reading can be performed while the sheet is in close contact with the image reading sensors 14, 15. The platen rollers 14a, 15a form the background of the image reading sensors 14, 15, and are colored white in this embodiment.
[0033] The images of the sheets read by the image reading sensors 14 and 15 are transmitted to an external device such as an information processing device via an interface unit (not shown).
[0034] FIG. 3 is a block diagram showing an example of a control configuration of the scanner 100. As shown in FIG.
[0035] A / D converters (ADC) 301a and 301b perform analog processing such as amplification and black level clamping on the output signals of image reading sensors (line image sensors) 14 and 15, and then convert the signals into digital data (image data).
[0036] The image processing unit 302 controls the image reading sensors 14 and 15 and the A / D conversion units 301a and 301b, and performs various image processing operations on the image data output from the A / D conversion units 301a and 301b. The image processing unit 302 also has an image processing buffer that stores image data therein.
[0037] The I / F 304 is an interface for communicating with an external host device (such as the PC 200) and is connected to an external host device such as a PC via a signal cable 305. For example, it is a USB interface, and may be a wired interface such as a USB interface or a wired LAN interface, or may be a wireless interface such as a wireless LAN, wireless USB, BLUETOOTH (registered trademark), or NFC.
[0038] The CPU 306 is a control unit that controls the scanner 100. The image processing unit 302 and the CPU 306 are connected via a bus 307. The image processing unit 302 accesses the RAM 303 and the ROM 310. The CPU 306 also functions as a correction determination unit, which will be described later.
[0039] The ROM 310 stores programs and various data. The RAM 303 functions as a work memory for the CPU 306.
[0040] The driving unit 309 is a motor or the like for driving various loads such as the pickup roller 4, the feeding roller 6, and the separation roller 7. The motor driver 308 is a control circuit for controlling the driving unit 309 based on instructions from the CPU 306.
[0041] FIG. 4 is a diagram showing an example of an OCR processing application according to the present embodiment.
[0042] This application may be provided inside the scanner 100 and executed under the control of the CPU 306, or may be provided in the PC 200 and adjustment values may be set via the I / F 304. The user can specify the range to be processed when performing OCR processing, and set the OCR processing to stop when a fold in the document is detected. Note that this OCR setting is a part of the image reading setting.
[0043] To specify a range, check the checkbox labeled "Specify area" in the figure, and enter the X and Y coordinates starting from the upper left corner of the document (0,0), as well as the width and height of the range in pixels.
[0044] If you want to set the OCR process to stop when a fold is detected, check the checkbox labeled "Stop when a fold is detected" in the figure.
[0045] By pressing the scan button after setting, the OCR processing application sets the image processing unit 302 to replace the background color in the image data according to the above setting and starts scanning. Then, the application receives the image data processed by the image processing unit 302, performs OCR processing, and outputs text data.
[0046] FIG. 5 is an example of an image that has undergone background color replacement processing.
[0047] Image data is composed of an original area, which is the area of the scanned original, and a background area, which is the background (background color). The background color replacement process is performed by image processing unit 302, which functions as an image processing means, and includes a "background blackening" process and an "outside rectangle blackening" process as background area correction processes. The "outside rectangle blackening" process (a) is a process in which the outside of the rectangular area containing the original is replaced with black in the background area. The "background blackening" process (b) is a process in which all background areas outside the original area are replaced with black. The "outside rectangle blackening + background blackening" process (c) is a process in which both the "background blackening" process and the "outside rectangle blackening" process are performed.
[0048] In this embodiment, the OCR processing application is set to perform "blackening outside rectangle" processing if the checkbox "Specify area" shown in Figure 4 is checked, and to perform "blackening background" processing if the checkbox "Stop when a crease is detected" is checked.
[0049] The image data is an image obtained by scanning a wide area so that sufficient margins are added to the top, bottom, left and right sides in addition to the document area. The surface facing the image reading sensors 14 and 15, which is the background area, is white, so the margin area added around the document area is white. The boundary between the document area and the background area is detected from this image data, and the background color is replaced based on the detected boundary.
[0050] In the case of (a) outer rectangle blackening process, the rectangle including the document is blackened and the folded parts are left white, so that the position of the upper left corner of the document, which is the origin of the OCR process, can be identified.
[0051] In the case of the background blackening process (b), the parts missing due to the fold are blackened, making it clear that the document was read in a folded state.
[0052] When both the background blackening process (c) and the rectangle blackening process are performed, the outermost part is left white to outline the part missing due to the fold, and the inside of that and the rectangle including the document are blackened.
[0053] FIG. 6 is a flowchart showing a process executed under the control of the CPU 306 as boundary detection means for detecting the boundary between the document area and the background area.
[0054] In this embodiment, the image data is described as an 8-bit grayscale image, but it may also be a full-color image. When a full-color image is input, an 8-bit grayscale image is generated from the full-color image within the image processing unit 302, and the processing of this flowchart is executed using the 8-bit grayscale image as image data.
[0055] In S401, the brightness of the "pixel of interest" which is the pixel to be processed is referenced. First, the brightness of the pixel at the edge of the image is referenced. At this time, when detecting the upper boundary of the border between the document region and the background region, the top edge of the image is referenced; when detecting the lower boundary, the bottom edge of the image is referenced; when detecting the left boundary, the left edge of the image is referenced; and when detecting the right boundary, the right edge of the image is referenced. Note that the brightness at coordinates (x, y) is represented as B(x, y).
[0056] Next, in S402, it is determined whether the absolute value of the difference between the brightness B(x, y) acquired in S401 and a predetermined brightness value Bbase is greater than a predetermined threshold value th, that is, it is determined whether the following formula (1) is satisfied.
number
[0057] If the formula (1) is satisfied, that is, if the absolute value of the difference is greater than the threshold value th, the current coordinates (x, y) are stored in S403.
[0058] If formula (1) is not satisfied, in S404 it is checked whether there is an adjacent pixel for the coordinate (x, y). The "adjacent pixel" here is determined by which boundary is to be detected. For coordinate (x, y), to detect the upper boundary, the pixel at coordinate (x, y+1) can be referenced; to detect the lower boundary, the pixel at coordinate (x, y-1) can be referenced; to detect the left boundary, the pixel at coordinate (x+1, y) can be referenced; and to detect the right boundary, the pixel at coordinate (x-1, y) can be referenced.
[0059] If the adjacent pixel can be confirmed, the pixel of interest is changed to the adjacent pixel, the brightness value is referenced in S401, and the obtained brightness value is judged in S402. If there is no adjacent pixel, it is judged in S405 that there is no document on that line. Then, the pixel of interest is moved to the next line, and the same process is carried out. If it is judged that there is no pixel on the next line, the process ends.
[0060] The CPU 306 performs the above process as boundary detection means for each x coordinate at the upper and lower boundaries and for each y coordinate at the left and right boundaries, thereby obtaining the boundaries between the document region and the background region in the image.
[0061] Next, the determination of the background color replacement processing method and the replacement processing method executed under the control of the CPU 306 will be described with reference to FIG.
[0062] In S501, the CPU 306 functions as a correction determination unit and determines whether or not to perform the rectangle blackening process. If the check box "specify area" shown in Fig. 4 is checked, the rectangle blackening process is performed. If the check box is not checked, a determination is made in S505 (to be described later) as to whether or not to perform the background blackening process.
[0063] When performing the rectangle outside blackening process, first in S502, the inclination is detected from the boundary between the document and the background, which will be described later. Next, in S503, a rectangle including the document is obtained from the boundary between the document and the background, which will be described later, and the inclination. Then, in S504, the image processing unit 302 performs a process of filling in the area outside the rectangle, based on the boundary between the document and the background, which will be described later, the obtained inclination, and the rectangle information.
[0064] After performing blackening processing on the area outside the rectangle in S504, in S505 the CPU 306 functions as a correction determination means and determines whether or not to perform background blackening processing. If the check box "Stop when crease is detected" shown in FIG. 4 is checked, the image processing unit 302 performs background blackening processing. If background blackening processing is to be performed, processing is performed in S506 to fill in the background area, which can be seen from the boundary between the document and the background, which will be described later. The processing result in this case is shown in FIG. 5(c). If the check box is not checked, the replacement processing ends as it is. The processing result in this case is shown in FIG. 5(a).
[0065] In S501, the outside rectangle blackening process is not performed, and in S505, it is determined whether or not to perform background blackening process. If background blackening process is to be performed, the background area that can be seen from the boundary between the document and the background is filled in in S506 in the same manner as above. The processing result in this case is shown in Fig. 5(b). If background blackening process is not to be performed, the process ends as it is.
[0066] In this embodiment, the determination as to whether to perform the outside-rectangle blackening process is made first, but this is not limited thereto, and the determination as to whether to perform the background blackening process may be made first.
[0067] Next, a method for detecting the inclination from the boundary between the document and the background, which is performed in S502, will be described.
[0068] When the boundary coordinates for each x coordinate at the upper boundary between the document and the background are (x, T(x)) and a predetermined value is L, the slope vector V(n) for each n is as follows:
number
[0069] However, if there is no corresponding boundary coordinate for the coordinate, it is not defined. The tilt vector V(n) obtained here is converted into a unit vector, and the document tilt α can be obtained by averaging them.
[0070] A method for determining a rectangle including the document in step S503 from the boundary and inclination between the document and the background will be described below.
[0071] At each coordinate of the boundary between the document and the background, the maximum and minimum intercepts of a line passing through said coordinate with a slope of α and a line passing through said coordinate with a slope of -1 / α are obtained.
[0072] In other words, when the maximum intercept value at the slope α is βM and the minimum value is βm, and the maximum intercept value at the slope -1 / α is γM and the minimum value is γm, the rectangle enclosed by the following four straight lines will be the rectangle containing the original.
number
[0073] However, when α is 0, it is only necessary to find the maximum and minimum values of the X and Y coordinates from the coordinates of the boundary between the document and the background.
[0074] Next, a process of painting the outside of the document rectangle in the image with a specified color will be described, which is performed by the image processing unit 302. At any coordinate (x, y) in the image, β and γ are calculated from the above-mentioned inclination α as follows.
number
[0075] It is determined whether or not these β and γ satisfy the formula (2).
number
[0076] If the coordinates (x, y) satisfy both of the conditions in formula (2), it is determined to be inside the document rectangle and no processing is performed.If either of the conditions in formula (2) is not satisfied, it is determined to be outside the document rectangle and is replaced with the specified color.
[0077] By performing this process on all pixels of the image, the area outside the document rectangle can be filled with the specified color.
[0078] Next, a process of painting the outside of the boundary between the document and the background in the image (background area) with a specified color, which is performed by the image processing unit 302, will be described.
[0079] At the boundary between the document and the background, if the coordinates of the upper boundary at each x coordinate are (x, T(x)), the coordinates of the lower boundary at each y coordinate are (x, U(x)), the coordinates of the left boundary at each y coordinate are (L(y), y), and the coordinates of the right boundary at each y coordinate are (R(y), y), then it is determined whether the following formula (3) is satisfied at any coordinate (x, y) in the image.
number
[0080] If the coordinates (x, y) satisfy both of the conditions in formula (3), they are determined to be within the document boundary (document area) and no processing is performed.If either of the conditions in formula (3) is not satisfied, they are determined to be outside the document boundary (background area) and are replaced with the specified color.
[0081] This allows the background color to be replaced according to the user's settings.
[0082] After completing the image processing in each step described above in accordance with instructions from the CPU 306, the image processing unit 302 outputs the image to the OCR application. When the OCR application receives the image, it processes it according to the settings.
[0083] When detecting creases in an image, the coordinates of all non-black pixels in the image are detected, and the top and bottom Y coordinates and left and right X coordinates of the document in the image are calculated. Then, the pixels around the upper left, upper right, lower left, and lower right corner positions are referenced from the top and bottom Y coordinates and left and right X coordinates, respectively, and if there are any pixels other than black pixels, it is determined that there is no crease. If there are no pixels other than black pixels around the corner positions, it is determined that there is a crease, and the process ends.
[0084] When specifying an area, first scan the image from the top left to the right for non-black pixels. When a non-black pixel is found, that pixel is the top left pixel, so you can perform OCR processing on the range from a position shifted the starting point from the calculated coordinates.
[0085] By switching the background color replacement process, an appropriate image can be output for the next image processing step.
[0086] In this embodiment, correction processing is not performed on areas other than the background area, but a process of correcting the inclination of the document based on the inclination calculated from the boundary may be performed. Since OCR processing may not be able to properly recognize characters in an inclined image, correcting the inclination can improve the accuracy of character recognition.
[0087] Also, in this embodiment, the background color replacement process is switched according to the settings of the OCR application, but this may also be switched directly by the user so that the background color is replaced according to the user's selection.
[0088] For example, as detailed settings for the background color replacement process, a choice between "outside rectangle blackening" process and "background blackening" process may be presented to the user, and the selected process may be executed.
[0089] In addition, in this embodiment, the same process is carried out when carrying out both the "outside rectangle blackening" process and the "background blackening" process, but the process may be changed.
[0090] For example, when performing both the "outside rectangle blackening" process and the "background blackening" process, when performing the outside rectangle blackening process and then the background blackening process, a predetermined value δ may be substituted if it satisfies equation (4) in addition to equation (3).
number
[0091] By carrying out the replacement process in this manner, it is possible to obtain the image shown in FIG. 5(c) that has been subjected to "blackening outside the rectangle + blackening background" processing.
[0092] On the other hand, when performing OCR processing, the user's application may always want to detect the upper left corner as the reference position, so when performing both "outside rectangle blackening" processing and "background blackening" processing, it may be possible to stop the "background blackening" processing only at the upper left position of the document.
[0093] Moreover, the processing may be switched according to the background color setting of the image processing device.
[0094] In the case where the image processing device has a function for switching the background color, if the user has set the background color to white, the processing is performed as in this embodiment. If the background color is black, no processing is performed if background blackening is specified, and when performing outside-rectangle blackening processing, the pixels within the document rectangle and outside the boundary between the document and the background are replaced with white.
[0095] The process of determining whether a rectangle in the document is a background region is when both expressions (2) are satisfied and either one of the expressions (3) is not satisfied. In this case, the pixel at the target coordinate is replaced with white.
[0096] Additionally, functions that detect abnormalities during transport and stop scanning are generally known as "double feed detection" and "skew detection." When such functions are turned on, the user operates on the assumption that they will restart the scanning operation if an abnormality occurs, so by performing the "background blackening" process, it becomes easier to detect folds and encourages the user to restart the operation. In this case, if the image reading device has a function that stops scanning when an abnormality is detected during transport turned on, the "background blackening" function can be turned on.
[0097] In view of the above, apart from this embodiment, the background area correction processing to be performed may be determined according to the processing performed by the user after image output, rather than being determined by the user's settings, selection, or switching, or an appropriate correction processing may be automatically selected by a correction determination means. [Explanation of symbols]
[0098] 100 Scanner 200 Personal Computers 302 Image Processing Unit 303 RAM 306 CPU 310 ROM
Claims
1. The image data read from the document by the image reading device is composed of a document area and a background area, a boundary detection means for detecting a boundary between the document area and the background area; an image processing means for selecting a background color replacement process for the background area detected by the boundary detection means from a plurality of background area correction processes; a correction determination means for determining which of the plurality of background region correction processes is to be used, The image processing device according to claim 1, wherein the image processing means corrects the background region by the background region correction process selected in response to a determination made by the correction determination means.
2. 2. The image processing apparatus according to claim 1, wherein the background area correction process replaces a background color based on the boundary between the document area and the background area detected by the boundary detection means.
3. 3. The image processing apparatus according to claim 1, wherein the correction determination unit determines which of the plurality of background area correction processes is to be used to correct the background area in accordance with a user's image reading setting.
4. 3. The image processing apparatus according to claim 1, wherein a user selects which of the plurality of background region correction processes is to be used to correct the background region.
5. 3. The image processing apparatus according to claim 1, wherein the correction determination means automatically selects which of the plurality of background region correction processes is to be used to correct the background region.
6. 3. The image processing apparatus according to claim 1, wherein the correction determination means determines which of the background region correction processes to use in response to a process performed by a user after outputting an image.
7. 3. The image processing apparatus according to claim 1, wherein the correction determination means determines which of the plurality of background area correction processes to use in accordance with a background color setting of the image processing apparatus.
8. The image data consists of a document area and a background area. a boundary detection means for detecting a boundary between the document area and the background area; an image processing means for selecting a background color replacement process for the background area detected by the boundary detection means from a plurality of background area correction processes; a correction determination means for determining which of the plurality of background region correction processes is to be used, The image processing system according to claim 1, wherein the image processing means corrects the background region by the background region correction process selected in response to a determination made by the correction determination means.
Citation Information
Patent Citations
Image editing system and image editing method
JP2001144946A
