Automatic mark recognition device, image processing device, and information processing device

Abstract

To provide an automatic mark recognition device that, even when streaks are generated in an image due to a failure of the device, can prevent output of a wrong mark recognition result, and provide an image processing apparatus, and an information processing apparatus.SOLUTION: An automatic mark recognition device comprises: an image acquisition unit that acquires an image; a check box detection unit that detects a check box from the image; a streak detection unit that detects streaks due to a failure of the device from the image; a mark recognition execution determination unit that determines whether to execute recognition of a mark in the image according to the presence or absence of overlapping of the check box and the streaks based on a result of detection of the check box and a result of detection of the streaks; and a mark recognition unit that, when it is determined that the recognition of the mark in the image is to be executed, determines the presence or absence of the mark in the check box.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to an automatic mark recognition device, an image processing device, and an information processing device. [Background technology]

[0002] There are systems that allow ordering and invoicing of various goods and services by handwriting check marks or other marks on a form formatted with check boxes, and then sending and receiving faxes, scanning, etc. A technology called OMR (Optical Mark Recognition) has been developed for this system in which the receiving device automatically determines whether or not each check box is checked and outputs the determination result.

[0003] Patent Document 1 discloses a technology that detects line segments around a check box and invalidates the mark if the line segment length is equal to or greater than a certain value. Patent Document 2 also discloses a technology that scans a printed document when an abnormal noise occurs and controls the continuation of image formation based on the presence or absence of defects in the scanned image. Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned techniques may not be able to correctly recognize marks depending on the location of the image quality defect. For example, with the technique described in Patent Document 1, if a streak caused by a malfunction of the reading device or output device overlaps with a check box, it is difficult to correctly recognize the mark. Also, with the technique described in Patent Document 2, for example, if a streak caused by a malfunction of the reading device or output device appears in a position unrelated to the check box, the technique may uniformly stop mark recognition processing even if it does not affect mark recognition.

[0005] The present invention has been made in consideration of the above, and aims to provide an automatic mark recognition device, an image processing device, and an information processing device that can suppress the output of erroneous mark recognition results even if streaks occur in an image due to a device malfunction. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, the present invention comprises an image acquisition unit that acquires an image, a check box detection unit that detects check boxes within the image, a streak detection unit that detects streaks within the image caused by device malfunctions, a mark recognition implementation determination unit that determines whether or not to recognize a mark within the image depending on the check box detection results and whether or not the check box and the streak overlap based on the streak detection results, and a mark recognition unit that determines whether or not there is a mark within the check box when it is determined that recognition of the mark within the image is to be performed. [Effects of the Invention]

[0007] According to the present invention, even if a streak occurs in an image due to a device malfunction, it is possible to suppress the output of an erroneous mark recognition result. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 illustrates an example of a configuration of an information processing system according to the first embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of the image processing apparatus according to the first embodiment. [Figure 3] FIG. 3 illustrates an example of a hardware configuration of a PC according to the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a functional configuration of the image processing device included in the information processing system according to the first embodiment. [Figure 5] FIG. 5 is a flowchart showing an example of the flow of mark recognition processing in the image processing device included in the information processing system according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a detection result of check boxes by the image processing apparatus according to the first embodiment. [Figure 7] FIG. 7 is a diagram for explaining an example of a streak that occurs due to a fault in a reading device. [Figure 8] FIG. 8 is a diagram illustrating an example of a streak that occurs due to a defect in an output device. [Figure 9] FIG. 9 is a diagram illustrating an example of a result of streak detection performed by the image processing device according to the first embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of streaks included in an image acquired by the image processing apparatus according to the first embodiment. [Figure 11] FIG. 11 is a flowchart showing an example of the flow of a process for determining whether or not a check box and a streak overlap in the image processing device included in the information processing system according to the first embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of a process of determining whether or not a check box and a streak overlap in the image processing apparatus according to the first embodiment. [Figure 13] FIG. 13 is a diagram illustrating an example of validation of a check box detected by the image processing device included in the information processing system according to the first embodiment. [Figure 14] FIG. 14 illustrates an example of a functional configuration of an image processing apparatus included in an information processing system according to the second embodiment. [Figure 15] FIG. 15 is a flowchart illustrating an example of the flow of mark recognition processing in the image processing device included in the information processing system according to the second embodiment. [Figure 16] FIG. 16 illustrates an example of a functional configuration of an information processing system according to the third embodiment. [Figure 17] FIG. 17 is a flowchart illustrating an example of the flow of an image transmission process in the information processing system according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of an automatic mark recognition device, an image processing device, and an information processing device will be described in detail with reference to the accompanying drawings.

[0010] (First embodiment) 1 is a diagram showing an example of the configuration of an information processing system according to a first embodiment. In the information processing system according to this embodiment, an image receiving device 112 owned by a user 100 who uses the information processing system and an image delivery device 113 owned by a customer 101 can communicate with each other via a public line 120, the Internet 130, etc. The image receiving device 112 and the image delivery device 113 may be various devices capable of transmitting and receiving images using various communication paths, such as a standalone fax machine, an MFP (Multi-Function Peripheral), a standalone scanner, etc.

[0011] The user 100 also has a PC (Personal Computer) 110 and an image processing device 111 connected to the Internet 130. In recent years, fax transmission and reception over the Internet has become common, and the PC 110 can receive images attached to emails from the image distribution device 113 or images sent via a fax server. When an image is output onto a recording medium from the image receiving device 112, the image processing device 111 reads the output document (recording medium) and converts it into image data. Here, the image receiving device 112 and the image processing device 111 are separate devices, but a single device may fulfill both roles as long as it is an MFP capable of receiving, outputting, and reading images. The database 114 is connected to the Internet 130, can send and receive data via the Internet 130, and is used to store various data such as images.

[0012] 2 is a diagram showing an example of the hardware configuration of the image processing device according to the first embodiment. The image processing device 111 according to the present embodiment includes a control unit 201, an operation unit 212, a printer 213, a scanner 214, a finisher 215, and a modem 216.

[0013] The control unit 201 controls the overall operation of the image processing device (multifunction peripheral) 111. The control unit 201 has a CPU (Central Processing Unit) 202, a ROM (Read Only Memory) 203, a RAM (Random Access Memory) 204, an HDD (Hard Disk Drive) 205, an operation unit I / F 206, a printer I / F 207, a scanner I / F 208, an accessory I / F 209, a modem I / F 210, and a network I / F 211.

[0014] The CPU 202 reads and executes a control program (computer program) stored in the ROM 203 to perform various controls, such as reading control of a recording medium and transmission control of various information such as images. The RAM 204 is used as a temporary storage area such as the main memory and work area of the CPU 202. The HDD 205 stores image data and various programs, or various information tables.

[0015] The operation unit I / F 206 is an interface that connects the operation unit 212 and the control unit 201. The operation unit 212 is provided with a liquid crystal display unit having a touch panel function, a keyboard, and the like.

[0016] The printer I / F 207 is an interface that connects the printer 213 and the control unit 201. Image data to be printed by the printer 213 is transferred from the control unit 201 via the printer I / F 207 and printed on a recording medium by the printer 213.

[0017] The scanner I / F 208 is an interface that connects the scanner 214 and the control unit 201. The scanner 214 reads an image on a document to generate image data, and inputs the image data to the control unit 201 via the scanner I / F 208.

[0018] The accessory I / F 209 is an interface that connects the finisher 215 and the control unit 201. In this embodiment, the finisher 215 is shown as a representative accessory that connects to the control unit 201, but it is also possible to connect one or more other accessories. Accessories include a puncher that punches holes, a stapler that staples, a bookbinding unit that binds books, a sorter that sorts output materials, and the like.

[0019] The modem I / F 210 is an interface that connects the modem 216 and the control unit 201 (image processing device 111). The modem 216 is connected to the public line 120, and receives and transmits FAXes from and to external devices.

[0020] The network I / F 211 is an interface that connects the control unit 201 (image processing device 111) to a LAN (Local Area Network). The network I / F 211 transmits various types of information such as image data to external devices connected via the LAN and the Internet, and receives various types of information from the external devices. In this embodiment, the image receiving device 112 and the image distribution device 113 also have the same hardware configuration as the image processing device 111.

[0021] 3 is a diagram showing an example of a hardware configuration of a PC according to the first embodiment. In this embodiment, the PC 110 includes a control unit 301, a mouse 308, and a keyboard 309, as shown in FIG.

[0022] The control unit 301 controls the overall operation of the PC 110. The CPU 302 reads out a control program (computer program) stored in the ROM 303 and executes various control processes. The RAM 304 is used as a temporary storage area such as the main memory and work area of the CPU 302. The HDD 305 stores image data, various programs, or various information tables, which will be described later.

[0023] The operation unit I / F 307 is an interface that connects a mouse 308 and a keyboard 309 to the control unit 301. The mouse 308 is used to move the cursor and select various files. The keyboard 309 is used to input characters. The network I / F 306 is an interface that connects the control unit 301 to a LAN, and transmits and receives various information to and from other devices via the LAN or the Internet.

[0024] Fig. 4 is a diagram showing an example of the functional configuration of an image processing device included in the information processing system according to the first embodiment. As shown in Fig. 4, the image processing device 111 (an example of an automatic mark recognition device) according to the present embodiment includes an image acquisition unit 401, a check box detection unit 402, a streak detection unit 403, a mark recognition execution determination unit 404, and a mark recognition unit 405.

[0025] The image acquisition unit 401 acquires an image to be subjected to mark recognition processing. The image to be acquired may be an image received by the image receiving device 112 as is, an image received by the image receiving device 112 and then stored in the PC 110, the image receiving device 112, or the database 114, or an image read from a recording medium such as paper by the scanner 214 (an example of a reading unit) of the image processing device 111.

[0026] Check box detection unit 402 detects check boxes from within the image acquired by image acquisition unit 401. In this embodiment, check box detection unit 402 detects the position and size of check boxes within the acquired image.

[0027] The streak detection unit 403 detects streaks caused by device defects from within the acquired image. In this embodiment, the streak detection unit 403 detects the position and thickness of streaks caused by device defects (e.g., device defects such as the printer 213 and the scanner 214) from within the acquired image. Here, the streaks include both black streaks and white streaks.

[0028] The mark recognition execution determination unit 404 determines whether or not to recognize marks in the acquired image, depending on whether or not check boxes and streaks overlap based on the check box detection results and streak detection results. That is, the mark recognition execution determination unit 404 determines the effect of streaks on mark recognition processing for check boxes based on the check box detection results and streak detection results, and determines whether or not to perform mark recognition processing.

[0029] In this embodiment, the mark recognition implementation determination unit 404 calculates the area of the region where the checkbox and the stripe overlap based on the position and size of the checkbox and the position and thickness of the stripe, and if this area is equal to or smaller than a threshold, determines to implement mark recognition within the image. On the other hand, if this area is greater than the threshold, the mark recognition implementation determination unit 404 determines not to implement mark recognition within the image. This makes it possible to stop implementation of mark recognition only when a thick stripe that affects mark recognition overlaps the checkbox.

[0030] In this case, the mark recognition execution determination unit 404 may switch the threshold value depending on the type of mark in the image (in other words, the type of mark for which recognition processing is to be performed). This allows mark recognition to be performed after determining whether accurate mark recognition is possible.

[0031] When the mark recognition execution determination unit 404 determines that recognition of a mark in an image should be performed, the mark recognition unit 405 executes mark recognition processing to determine whether or not a mark is present in the detected check box. That is, the mark recognition unit 405 executes recognition processing of the mark in the detected check box based on the determination result of the mark recognition execution determination unit 404. This makes it possible to control the execution of mark recognition according to the positional relationship between the location where the streak occurs and the check box, thereby increasing the possibility of outputting a correct mark recognition result.

[0032] 5 is a flowchart showing an example of the flow of mark recognition processing in the image processing device of the information processing system according to the first embodiment. First, when the image receiving device 112 receives an image, the image acquiring unit 401 acquires the received image (step S501). In this embodiment, the image acquiring unit 401 may not only directly acquire the received image, but also poll specific folders in the PC 110 and database 114, etc., to acquire newly added images.

[0033] Next, the check box detection unit 402 detects check boxes from the acquired image (step S502). For example, the check box detection unit 402 repeats a process of ANDing an image obtained by shifting the original image down by one dot with the original image multiple times, and then repeats a process of ORing an image obtained by shifting the processed image up by one dot with the processed image the same number of times, thereby extracting only vertical lines that are equal to or longer than a certain length. The check box detection unit 402 similarly applies these processes horizontally to extract horizontal lines that are equal to or longer than a certain length. Thereafter, the check box detection unit 402 detects the area surrounded by the lines as a check box by leaving only lines whose ends are separated by a threshold.

[0034] Furthermore, for example, the check box detection unit 402 can also detect check boxes using a Hough transform. Specifically, the check box detection unit 402 extracts line segments in an image using a Hough transform. Next, the check box detection unit 402 calculates the distance between the endpoints of each line segment and the angle between the line segments from the dot product, and detects, as a check box, an area surrounded by only line segments whose distance and angle are both within a threshold. Furthermore, for example, the check box detection unit 402 can calculate the area of the area using information about the endpoints, so it may also detect check boxes by adding an area threshold. Furthermore, since the Hough transform can also extract circles, even round check boxes can be detected.

[0035] 6 is a diagram showing an example of the check box detection result by the image processing device according to the first embodiment. Then, as shown in FIG. 6, the check box detection unit 402 stores the position (e.g., starting point) and size of the detected check box in association with the ID of the check box.

[0036] Returning to FIG. 5, the streak detection unit 403 detects streaks from the acquired image (step S503). Streaks that appear in an image can be caused by the reading device or the output device. FIG. 7 is a diagram illustrating an example of streaks that appear due to a faulty reading device. As shown in FIG. 7(a), the image reading unit 500 (e.g., the scanner 214) of the image delivery device 113 has a lamp 501 that irradiates an original document and a sensor 502 that reads reflected light from the original document. An image is read by scanning the original document or the sensor. During this process, color material from the original document or paper fragments may adhere to the image reading unit 500 as dust 510, as shown in FIG. 8(b). If an image is read with dust 510 adhering to it, a streak L1 appears on the read image.

[0037] 8A and 8B are diagrams illustrating an example of streaks that occur due to a malfunction of an output device. As shown in FIG. 8A, the image forming unit 600 (e.g., the printer 213) of the image receiving device 112 includes a photosensitive drum 601, a charging device (charging roller) 602, an optical writing unit (semiconductor laser) 603, a developing device 604, an intermediate transfer belt 605, and a cleaning device 606. During image formation, the image forming unit 600 uniformly charges the outer circumferential surface of the photosensitive drum 601 using the charging device 602, and emits laser light from the optical writing unit 603 toward the uniformly charged outer circumferential surface of the photosensitive drum 601, corresponding to image data that has been image-processed by an image processing unit, to form an electrostatic latent image on the outer circumferential surface of the photosensitive drum 601. The image forming unit 600 then develops the electrostatic latent image with toner from the developing device 604 to form a toner image, and primarily transfers the toner image to the intermediate transfer belt 605. Thereafter, the image forming unit 600 performs a second transfer of the toner image onto a recording medium, and the cleaning device 606 neutralizes the charge on the photosensitive drum 601 and removes any remaining toner in preparation for the next image formation.

[0038] However, as shown in Figure 8(b), if a sticky substance 610 such as glue that was on the recording medium adheres to the photosensitive drum 601, the laser will not hit that area, and toner will continue to be deposited there. This will also cause streaks L2 in the output image. Conversely, if the photosensitive drum 601 malfunctions and a specific area can no longer be charged, toner will not be deposited in that area, and white streaks may occur.

[0039] To detect streaks in an image, the same AND or OR operations for each pixel used in the checkbox detection method and extraction using the Hough transform, etc. can be applied. White streaks can also be extracted by inverting the acquired image and performing streak detection.

[0040] FIG. 9 is a diagram illustrating an example of a streak detection result obtained by the image processing device according to the first embodiment. FIG. 10 is a diagram illustrating an example of a streak included in an image acquired by the image processing device according to the first embodiment. As shown in FIG. 9, the streak detection unit 403 stores the position (starting point) and size of the detected streak in association with the ID of the streak, similar to the detection of check boxes. IDs 1, 2, and 3 shown in FIG. 10 are the IDs of streaks A, B, and C shown in FIG. 10, respectively. Lines drawn by the user to cancel, such as streak C, and vertical lines in the document are also extracted, but such short lines are excluded from the mark recognition process. For example, a setting may be made to exclude lines less than three times the height of a check box from the mark recognition process.

[0041] 5, the mark recognition execution determination unit 404 determines whether the checkbox and the line overlap (step S504). If the checkbox and the line do not overlap and it is determined that recognition of the mark in the image is to be executed (step S504: No), the mark recognition unit 405 executes mark recognition processing to determine whether or not there is a mark in the checkbox (step S505).

[0042] The mark recognition process may involve obtaining the pixel values within the checkbox frame based on information such as the position and size of the detected checkbox, counting the number of black pixels, and determining that a mark is present if the ratio of black pixels is equal to or greater than a threshold. Since black pixels may occur due to noise or other factors other than those entered by the customer, it is preferable to set a slightly offset threshold. For images input in multi-value format, the mark recognition unit 405 may first binarize the image before counting the black pixels.

[0043] On the other hand, if it is determined that the check box and the streak overlap and that mark recognition within the image is not to be performed (step S504: Yes), the mark recognition unit 405 ends the process without performing mark recognition.

[0044] Fig. 11 is a flowchart showing an example of the flow of a process for determining whether or not a check box and a line overlap in the image processing device included in the information processing system according to the first embodiment. Fig. 12 is a diagram for explaining an example of the process for determining whether or not a check box and a line overlap in the image processing device according to the first embodiment. First, the mark recognition implementation determination unit 404 acquires information such as the position (e.g., start point) and size of the check box detected by the check box detection unit 402 (step S1001).

[0045] Furthermore, the mark recognition implementation determination unit 404 acquires information such as the position and thickness of the streaks detected by the streak detection unit 403 (step S1002). Next, the mark recognition implementation determination unit 404 sets the pixel values of pixels within the area of the detected check box to 1 (step S1003). For example, for the check box with ID: 1 shown in FIG. 6, the mark recognition implementation determination unit 404 generates the image shown in FIG. 12(a). For the check box with ID: 3 shown in FIG. 6, the mark recognition implementation determination unit 404 generates the image shown in FIG. 12(b).

[0046] The mark recognition implementation determination unit 404 also sets the pixel values of pixels in the area of the detected streak to 1 (step S1004). Similarly, for example, for the streak with ID: 1 in Fig. 9, the mark recognition implementation determination unit 404 generates the image shown in Fig. 12(c). For the streak with ID: 2 in Fig. 9, the mark recognition implementation determination unit 404 generates the image shown in Fig. 12(d).

[0047] Next, the mark recognition implementation determination unit 404 performs an OR operation (step S1005) on the image generated in step S1003 (i.e., the image in which the pixel values of the pixels in the checkbox area are set to 1) and the image generated in step S1104 (i.e., the image in which the pixel values of the pixels in the streak area are set to 1). As a result, the mark recognition implementation determination unit 404 generates images of (a)×(c), (b)×(c), (a)×(d), and (b)×(d), as shown in FIG.

[0048] Next, the mark recognition implementation determination unit 404 determines whether the ratio of pixels with a pixel value of 1 in the checkboxes of the images generated by performing the OR operation is equal to or less than a threshold value (step S1006). For example, for the checkbox with ID:1, the mark recognition implementation determination unit 404 counts the number of pixels with a pixel value of 1 in the images (a)×(c) and (a)×(d), and divides the counted values by the size of the checkbox with ID:1. Also, for example, for the checkbox with ID:3, the mark recognition implementation determination unit 404 counts the number of pixels with a pixel value of 1 in the images (b)×(c) and (b)×(d), and divides the counted values by the size of the checkbox with ID:2.

[0049] If the count value (the ratio of pixels in the checkbox whose pixel value is 1) is determined to be equal to or less than the threshold value (step S1006: Yes), the mark recognition execution determination unit 404 determines that the checkbox and the line do not overlap (step S1007).On the other hand, if the count value is determined to be greater than the threshold value (step S1006: No), the mark recognition execution determination unit 404 determines that the checkbox and the line overlap (step S1008).

[0050] FIG. 13 is a diagram showing an example of checkbox validation detected by the image processing device of the information processing system according to the first embodiment. There are various variations of checkboxes. For example, checkboxes with the shapes shown in FIGS. 13(A) and 13(B) are often used in answer sheets. Also, checkboxes with the shape shown in FIG. 13(C) are often used in questionnaires and the like. For each checkbox, the way in which the checkboxes are filled in can be predicted to some extent from the checkbox shape, but the area filled in by the mark varies depending on the type.

[0051] For example, in the case of a checkbox that is filled in as shown in Fig. 13(A), a large area is filled in, so a thin line does not affect the mark recognition process. On the other hand, in the case of a checkbox that is simply lined as shown in Fig. 13(B), even a thin line will affect the mark recognition process. For this reason, the mark recognition implementation determination unit 404 can obtain more accurate mark recognition results by switching the threshold value used when checking whether the checkbox and line overlap, depending on the shape of the checkbox.

[0052] In this way, according to the image processing device 111 of the first embodiment, the implementation of mark recognition can be controlled depending on the positional relationship between the location where the streak occurs and the check box, thereby increasing the possibility of outputting a correct mark recognition result.

[0053] (Second embodiment) In this embodiment, check box information including the position and size of a check box in an image format corresponding to an acquired image is acquired, and based on the check box information and the streak detection result, it is determined whether or not the check box and the streak overlap. In the following explanation, explanation of the same configuration as in the first embodiment will be omitted.

[0054] Fig. 14 is a diagram showing an example of the functional configuration of an image processing device included in an information processing system according to the second embodiment. As shown in Fig. 14, the image processing device 111 according to this embodiment includes an image acquisition unit 1401, an image format identification unit 1402, a check box information acquisition unit 1403, a streak detection unit 1404, a mark recognition implementation determination unit 1405, and a mark recognition unit 1406. Note that the image acquisition unit 1401, the streak detection unit 1404, and the mark recognition unit 1406 are similar to the image acquisition unit 401, the streak detection unit 403, and the mark recognition unit 405 shown in Fig. 4.

[0055] The image format identification unit 1402 is an example of a format identification unit that identifies an image format corresponding to the acquired image. In this embodiment, the image format identification unit 1402 identifies an image format that matches the acquired image from registered image format data.

[0056] A check box information acquisition unit 1403 acquires check box information such as the position and size of the check box corresponding to the identified image format.

[0057] The mark recognition execution determination unit 1405 determines whether or not the checkbox and the streak overlap based on the checkbox information and the streak detection result. Then, depending on whether or not the checkbox and the streak overlap, the mark recognition execution determination unit 1405 determines whether or not to recognize the mark in the image.

[0058] As a result, if a checkbox can be identified by its image format, the position, size, etc. of the checkbox can be identified simply by obtaining the checkbox information for each image format, without having to perform processing to detect the checkbox from the image. As a result, it is possible to determine whether the checkbox and the streak overlap with higher accuracy than by detecting the checkbox from the image.

[0059] 15 is a flowchart showing an example of the flow of mark recognition processing in the image processing device included in the information processing system according to the second embodiment. The processing shown in steps S1501, S1504, and S1506 in FIG. 15 is the same as the processing shown in FIG.

[0060] In this embodiment, when an image is acquired by the image acquisition unit 1401 (step S1501), the image format identification unit 1402 identifies the image format of the acquired image (step S1502). There are various known techniques for identifying image formats. For example, the image format identification unit 1402 can use a method of applying a partial image filter to an area on the image that is effective for identification, converting it into a feature vector, and calculating the distance from the feature vector of each image format registered in a dictionary to identify the image format.

[0061] The check box information acquisition unit 1403 acquires check box information corresponding to the identified image format (step S1503). The acquired check box information is information on the start point and size of the check box shown in FIG. 6 of the first embodiment, and may be checked and registered in advance by the user for each image format. The image format and the corresponding check box information may be acquired from the HDD 205 of the image reception device 112, the PC 110, or the database 114. Thereafter, the mark recognition implementation determination unit 1405 determines whether the check box and the streak overlap based on the check box information and the streak detection result (step S1505).

[0062] In this way, according to the image processing device 111 of the second embodiment, by bringing in check box information that has been registered in advance, the check box information can be used to determine whether or not the check box and the line overlap, making it possible to determine the overlap more accurately than by detecting the check box for each image.

[0063] (Third embodiment) In the present embodiment, whether or not to transmit an image to an image processing device is determined depending on whether or not a check box and a streak overlap. In the following description, the same configuration as in the above embodiment will not be described.

[0064] 16 is a diagram illustrating an example of the functional configuration of an information processing system according to the third embodiment. In this embodiment, the image delivery device 113 (an example of an information processing device) includes an image acquisition unit 1601, a check box detection unit 1602, a streak detection unit 1603, an image transmission determination unit 1604, and an image transmission unit 1605, as shown in FIG.

[0065] An image acquisition unit 1601, a check box detection unit 1602, and a streak detection unit 1603 are the same as the image acquisition unit 401, the check box detection unit 402, and the streak detection unit 403 shown in FIG.

[0066] The image transmission determination unit 1604 determines whether or not the checkboxes and streaks overlap based on the checkbox detection results and streak detection results. Next, the image transmission determination unit 1604 determines whether or not to transmit the image depending on whether or not the checkboxes and streaks overlap. That is, the image transmission determination unit 1604 determines the effect of streaks on mark recognition processing based on the checkbox detection results and streak detection results, and determines whether or not to transmit the image to the recipient.

[0067] When it is determined that the image should be sent to the recipient, the image sending unit 1605 sends the acquired image. As a result, if the image contains streaks that affect the mark recognition process, the image is not sent, and it is possible to prevent unnecessary image output on the image receiving side.

[0068] 17 is a flowchart showing an example of the flow of image transmission processing in the information processing system according to the third embodiment. Steps S1701 to S1704 are the same as steps S501 to S504 in FIG.

[0069] If it is determined that a check box and a streak overlap (step S1704: Yes), the image transmission determination unit 1604 increments the overlap count by 1 (step S1705). Next, the image transmission determination unit 1604 determines whether or not the determination of whether or not a check box and a streak overlap has been completed for all combinations of check boxes and streaks (step S1706).

[0070] If the determination of whether or not the checkboxes and stripes overlap has not been completed for all combinations of checkboxes and stripes (step S1706: No), the process returns to step S1704. On the other hand, if the determination of whether or not the checkboxes and stripes overlap has been completed for all combinations of checkboxes and stripes (step S1706: Yes), the image transmission determination unit 1604 determines whether or not the overlap count is equal to or less than a threshold (step S1707). Here, it is desirable that the threshold be set to an integer value of at least 1, and be changed according to the number of detected checkboxes.

[0071] If the duplicate count is equal to or less than the threshold (step S1707: Yes), the image transmission unit 1605 transmits the acquired image (step S1708). On the other hand, if the duplicate count is greater than the threshold (step S1707: No), the image transmission unit 1605 ends the process without transmitting the acquired image.

[0072] In this way, according to the image distribution device 113 of the third embodiment, by determining in advance whether or not the check boxes and lines overlap on the image distribution side, it becomes possible to prevent the image receiving side from outputting recording media such as unnecessary paper.

[0073] In the above embodiment, the image forming apparatus of the present invention is described as being applied to a multifunction peripheral having at least two of the functions of a copy function, a printer function, a scanner function, and a facsimile function, but the present invention can be applied to any image forming apparatus such as a copier, printer, scanner device, or facsimile device. [Explanation of symbols]

[0074] 110 PC 111 Image processing device 112 Image receiving device 113 Image distribution device 201,301 Control section 202,302 CPU 203,303 ROM 204,304 RAM 205,305 HDD 207 Printer I / F 208 Scanner I / F 211,306 Network I / F 213 Printer 214 Scanner 401, 1401, 1601 Image acquisition unit 402,1602 Checkbox detector 403, 1404, 1603 Line detection section 404,1405 Mark recognition execution determination unit 405,1406 Mark Recognition Unit 1402 Image format identification unit 1403 Checkbox information acquisition unit 1604 Image transmission determination unit 1605 Image transmission unit [Prior art documents] [Patent documents]

[0075] [Patent Document 1] Japanese Patent Application Publication No. 7-13984 [Patent Document 2] Japanese Patent Application Laid-Open No. 2016-114778

Claims

1. an image acquisition unit that acquires an image; a check box detection unit that detects check boxes within the image; a streak detection unit that detects streaks caused by device defects in the image; a mark recognition execution determination unit that determines whether or not to recognize a mark in the image depending on whether or not the check box and the streak overlap based on the check box detection result and the streak detection result; a mark recognition unit that determines whether or not a mark exists in the check box when it is determined that recognition of the mark in the image is to be performed; An automatic mark recognition device comprising:

2. an image acquisition unit that acquires an image; a format identification unit for identifying an image format corresponding to the image; a check box information acquisition unit that acquires check box information indicating the position of a check box corresponding to the identified image format; a streak detection unit that detects streaks caused by device defects in the image; a mark recognition execution determination unit that determines whether or not to recognize a mark in the image depending on whether or not the checkbox and the streak overlap based on the checkbox information and the streak detection result; a mark recognition unit that determines whether or not a mark exists in the check box when it is determined that recognition of the mark in the image is to be performed; An automatic mark recognition device comprising:

3. 3. The automatic mark recognition device according to claim 1, wherein the mark recognition execution determination unit calculates the area of the region where the check box and the streak overlap based on the position and size of the check box and the position and thickness of the streak, and if the area is equal to or smaller than a threshold, determines to recognize the mark in the image.

4. The automatic mark recognition device according to claim 3 , wherein the mark recognition implementation determination unit switches the threshold value depending on the type of mark in the image.

5. a reading unit that reads an image from a recording medium; a check box detection unit that detects check boxes within the image; a streak detection unit that detects streaks caused by device defects in the image; a mark recognition execution determination unit that determines whether or not to recognize a mark in the image depending on whether or not the check box and the streak overlap based on the check box detection result and the streak detection result; a mark recognition unit that determines whether or not a mark exists in the check box when it is determined that recognition of the mark in the image is to be performed; An image processing device comprising:

6. an image acquisition unit that acquires an image; a check box detection unit that detects check boxes within the image; a streak detection unit that detects streaks caused by device defects in the image; an image transmission determination unit that determines whether or not to transmit the image depending on whether or not the checkboxes overlap with the streaks based on the checkbox detection result and the streak detection result; an image transmitting unit that transmits the image to an external device when it is determined that the image should be transmitted; An information processing device comprising:

Images