JP2017183973A - Image reading apparatus and image processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately cut out an original main body and a circumference part thereof from reading image data of a laminate original.SOLUTION: An image reading apparatus detects a first region corresponding to an original in reading image data in the original, compares a lateral size of the first region with a predetermined reference lateral size, and determines whether or not the original is a laminate original. The image reading apparatus generates edge image data by applying edge detection processing to the reading image data in the case where it is determined that the original is the laminate original, and detects a second region corresponding to a main body of the original in the reading image data and the circumference part thereof on the basis of the edge image data.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an image reading apparatus and an image processing method.

  Laminating is known in which films having high light transmittance are bonded to the front and back surfaces of printed matter such as paper. The printed material to be laminated is, for example, an identification card, a membership card, an advertisement, a price list, or the like. Lamination can prevent discoloration and wear of the sandwiched printed material. Patent Document 1 discloses a technique for transporting a laminated medium.

JP 2011-032021 A

  A film of a laminated original (laminated original) is likely to be dusty or scratched. Therefore, when an image reading device such as a scanner cuts out an area corresponding to the original body from the read image data of the laminated original, it determines that a scratch on the film around the original body is the original body and cuts out an erroneous area. Sometimes. In addition, the shape and size of the cutout region change depending on the position and size of a scratch or the like on the film. For example, when an OCR (Optical Character Recognition) process is performed on a laminated document, if the cutout area is erroneously determined, the OCR process is not performed on a desired range in which characters are to be recognized.

  SUMMARY OF THE INVENTION An object of the present invention is to accurately cut out a document main body and its peripheral portion from read image data of a laminate document.

  One aspect of the present invention that solves the above-described problem is an image reading apparatus that scans a document to generate read image data, an image acquisition unit that acquires the read image data, and the read image. A first area detecting unit that detects a first area corresponding to the document in the data and a vertical and horizontal size of the first area and a predetermined reference vertical and horizontal size are compared, and the original is a laminated original. A document type determination unit that determines whether or not the document is a laminate document, and performs edge detection processing on the read image data to generate edge image data, and based on the edge image data, A second area detecting unit for detecting a second area corresponding to the main body of the original document and its peripheral portion in the read image data; and when the original is determined to be a laminate original, the read image And a cutout portion from over data cut out image data of the second region. As a result, the image reading apparatus can accurately determine the type of document (normal document or laminate document). Further, when the read original is a laminated original, the image reading apparatus can accurately cut out the original body and the surrounding portion included in the laminated original.

  The image reading apparatus includes an automatic paper feeding device that sends the document to the reading unit and detects a start and end of the document, and the first area detection unit is configured to detect the detected document. The vertical size may be determined based on the start and end points, and the horizontal size may be determined based on the read image data. As a result, the image reading apparatus can specify the vertical and horizontal sizes of the document in a shorter time than when specifying the vertical and horizontal sizes by image processing.

  The image reading apparatus may be able to select either the normal mode or the laminate original mode. When the normal mode is selected, the first area detection unit detects the first area in the read image data, and the cutout unit detects the first area from the read image data. Cut out image data. When the laminate document mode is selected, the first area detection unit detects the first area in the read image data, and the document type determination unit determines whether the document is a laminate document. When the document is determined to be a laminate document, the second area detection unit detects the second area in the read image data, and the document is determined to be a laminate document. In this case, the cutout unit cuts out the image data of the second area from the read image data, and when it is determined that the document is not a laminate document, the cutout unit extracts the first data from the read image data. The image data of the area is cut out. Thus, the image reading apparatus can appropriately cut out the image data regardless of whether a normal document is set or a laminate document is set by the user.

  In the image reading apparatus, the first region detection unit generates image data obtained by performing threshold determination processing on the read image data, and performs angle detection processing and rectangle detection processing on the image data. Thus, the first region is detected, and the second region detection unit detects the second region by performing an angle detection process and a rectangle detection process on the edge image data. Good. As a result, the image reading apparatus can extract image data by image processing with a smaller processing amount than the edge detection processing for a normal document, and can execute highly accurate image processing for area detection for a laminate document.

  Another aspect of the present invention that solves the above-described problem is an image reading apparatus, a reading unit that scans a document to generate read image data, an image acquisition unit that acquires the read image data, and the reading A first region detecting unit for detecting a first region corresponding to the document in the image data; and edge detection processing is performed on the read image data to generate edge image data. Based on the edge image data, A second area detecting unit for detecting a second area corresponding to the main body of the document and its peripheral portion in the read image data; a vertical and horizontal size of the first area; a vertical and horizontal size of the second area; And a document type determination unit that determines whether or not the document is a laminate document, and the image data of the second area from the read image data when the document is determined to be a laminate document. And a cut-out portion to be cut out. Thus, the image reading apparatus can accurately determine the type of document (normal document or laminated document) based on the image characteristics of the read image data without using the reference vertical and horizontal sizes. Further, when the read original is a laminated original, the image reading apparatus can accurately cut out the original body and the surrounding portion included in the laminated original.

  Still another aspect of the present invention for solving the above problem is an image processing method of an image reading apparatus, the step of scanning a document to generate read image data, the step of acquiring the read image data, The step of detecting a first area corresponding to the original in the read image data is compared with the vertical and horizontal sizes of the first area and a predetermined reference vertical and horizontal size to determine whether the original is a laminated original. And when the original is determined to be a laminate original, the read image data is subjected to edge detection processing to generate edge image data, and based on the edge image data, A step of detecting a second area corresponding to a main body of the original and a peripheral portion thereof; and when the original is determined to be a laminated original, the read image From over data and a step of cutting out the image data of the second region. As a result, the image reading apparatus can accurately determine the type of document (normal document or laminate document). Further, when the read original is a laminated original, the image reading apparatus can accurately cut out the original body and the surrounding portion included in the laminated original.

  Still another aspect of the present invention for solving the above problem is an image processing method of an image reading apparatus, the step of scanning a document to generate read image data, the step of acquiring the read image data, Detecting a first area corresponding to the original in the read image data; and performing edge detection processing on the read image data to generate edge image data; and based on the edge image data, the read image The step of detecting a second area corresponding to the main body of the document in the data and the peripheral portion thereof is compared with the vertical and horizontal size of the first area and the vertical and horizontal size of the second area, and the original is A step of determining whether or not the original is a laminate original; and when the original is determined to be a laminate original, the image data of the second area is obtained from the read image data. Ri issues and a step. Thus, the image reading apparatus can accurately determine the type of document (normal document or laminated document) based on the image characteristics of the read image data without using the reference vertical and horizontal sizes. Further, when the read original is a laminated original, the image reading apparatus can accurately cut out the original body and the surrounding portion included in the laminated original.

1 is a block diagram illustrating a configuration example of an image reading apparatus according to a first embodiment of the present invention. It is a flowchart which shows an example of an image reading process. It is a figure explaining the cutting-out of a lamination original. It is a flowchart which shows an example of the image reading apparatus which concerns on 2nd Embodiment of this invention.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[First Embodiment]
FIG. 1 is a block diagram illustrating a configuration example of an image reading apparatus according to the first embodiment of the present invention. The image reading apparatus 1 is a scanner or an MFP (Multifunction Printer), for example, and has a scan function and the like.

  The image reading apparatus 1 includes a control unit 2, a reading unit 3, a display unit 4, an input unit 5, and a communication unit 6. The control unit 2 includes an image acquisition unit 21, an image processing unit 22, and an image output unit 23.

  The control unit 2 controls the operation of the image reading apparatus 1 in an integrated manner. The control unit 2 includes, for example, an arithmetic device such as a CPU (Central Processing Unit), a volatile storage device such as a RAM (Random Access Memory), a non-volatile storage device such as a ROM (Read Only Memory), and the control unit 2 It can be realized by a computer including an interface circuit for connecting other units, a bus for connecting these units to each other, and the like. The control unit 2 may include various processing circuits such as an image processing circuit. The control unit 2 may be realized by an ASIC (Application Specific Integrated Circuit) or the like.

  At least some of the functions of the control unit 2 (the image acquisition unit 21, the image processing unit 22, and the image output unit 23) are performed by, for example, the CPU reading a predetermined program stored in the ROM and executing the program. Can be realized. For example, the predetermined program can be read from a portable storage medium and installed in the image reading apparatus 1, or can be downloaded from a server on the network and installed in the image reading apparatus 1. At least a part of the functions of the control unit 2 may be realized by a processing circuit such as an image processing circuit, for example. At least a part of the function of the control unit 2 may be realized by both the CPU and the processing circuit, for example.

  The reading unit 3 reads an original according to an instruction from the control unit 2 to generate image data, and outputs the image data to the control unit 2. The reading unit 3 is a scan engine using an image sensor, for example, and includes a mechanical part, a sensor, a motor, a drive circuit, a control circuit, and the like. The reading unit 3 of the present embodiment can output a color image or a gray scale image, for example. The reading unit 3 can output image data having a predetermined resolution such as 200 dpi, 300 dpi, 600 dpi, or the resolution selected by the user.

  The image reading apparatus 1 of the present embodiment includes an ADF 31 (Auto Document Feeder) in addition to a document table (not shown). For example, according to an instruction from the control unit 2 or the reading unit 3, the ADF 31 conveys a document to be read in a predetermined conveyance direction so as to pass through a reading region (for example, above the image sensor) of the reading unit 3. The ADF 31 includes mechanical parts, sensors, motors, drive circuits, control circuits, and the like. In addition, the ADF 31 includes, for example, a sensor (not shown, for example, an optical sensor) that detects the start and end of a document, and an encoder that detects the rotation angle of a motor for transporting the document. For example, the control unit 2 can specify the vertical size of the document based on the output of these sensors and the output of the encoder. The transport direction corresponds to the sub-scanning direction and the longitudinal direction of the document, and the direction orthogonal to the transport direction corresponds to the main scanning direction and the lateral direction of the document.

  The display unit 4 displays the processing results of the control unit 2 as characters, graphs, tables, animations, and other images. The display unit 4 is an output device such as an LCD (Liquid Crystal Display) or an OLED (Organic Electroluminescence Display).

  The input unit 5 receives a user operation input and outputs an operation signal corresponding to the operation to the control unit 2. The input unit 5 is an input device such as a key, a touch sensor, or a touch panel, for example.

  The communication unit 6 transmits / receives information to / from an external device. The communication unit 6 is a communication module compliant with, for example, a wireless LAN (Local Area Network). The image reading apparatus 1 may include a communication unit compliant with a wired LAN instead of or in addition to the communication unit 6.

  In the following, a description will be given centering on a case where the image reading apparatus 1 reads an ordinary document (for example, a standard document such as A4 or B5) or a laminated document (laminate document) using the ADF 31. Lamination (also referred to as pouching) is a process in which a highly light-transmitting film is bonded to the front and back surfaces of a document (printed material) such as paper. The document to be laminated is, for example, an identification card, a membership card, an advertisement, a price list, or the like.

  The image acquisition unit 21 acquires read image data from the reading unit 3. When a normal original is read, the read image data includes an area corresponding to the normal original and an area corresponding to the background (for example, a platen that holds down the original). When a laminated original is read, the read image data includes an area corresponding to the laminated original (original body and surrounding film) and an area corresponding to the background (for example, a platen that holds down the original).

  The image processing unit 22 performs a process of cutting out image data of an area corresponding to an original (an area corresponding to a normal original or a laminated original) from the read image data. The image processing unit 22 includes a first region detection unit 221, a second region detection unit 222, a document type determination unit 223, and a cutout unit 224.

  The first area detection unit 221 specifies the vertical size of the document based on the sensor output and encoder output output from the ADF 31. Further, the first area detection unit 221 specifies the horizontal size of the area corresponding to the document from the read image data output from the image acquisition unit 21. The first area detector 221 identifies the inclination of the document area with respect to the main scanning direction or the sub-scanning direction. Further, the first area detection unit 221 specifies a rectangular area (corresponding to the “first area” in the present invention) corresponding to the original by using the vertical and horizontal sizes and inclinations of the specified original area. Note that the rectangle includes a square.

  The second region detection unit 222 executes processing when the document type determination unit 223 described later determines that the read document is a laminate document. The second area detection unit 222 performs edge detection processing on the read image data output from the image acquisition unit 21 to generate edge image data. Further, the second area detection unit 222 specifies the vertical size and the horizontal size of the area corresponding to the laminated document based on the edge image data. The second area detection unit 222 identifies the inclination of the laminate document area with respect to the main scanning direction or the sub-scanning direction. Further, the second area detection unit 222 identifies a rectangular area (corresponding to a “second area” in the present invention) corresponding to the laminated document by using the vertical and horizontal sizes and inclinations of the identified laminated document area.

  The document type determination unit 223 compares the vertical and horizontal sizes of the document detected by the first region detection unit 221 with a predetermined reference vertical and horizontal size. The image reading apparatus 1 according to the present embodiment targets a laminate original smaller than the minimum standard size that can be read by the reading unit 3. The reference vertical / horizontal size is, for example, smaller than the size of the smallest standard document that can be read by the reading unit 3 and larger than the size of the largest laminated document that can be read by the reading unit 3. When the detected vertical and horizontal size of the document is smaller than the reference vertical and horizontal size, the document type determination unit 223 determines that the read document is a laminate document. If the detected vertical and horizontal size of the document is equal to or larger than the reference vertical and horizontal size, the document type determination unit 223 determines that the read document is a normal document.

  When it is determined that the read original is a normal original, the cutout unit 224 cuts out a rectangular area corresponding to the original detected by the first area detection unit 221 from the read image data. When it is determined that the read original is a laminate original, the cutout unit 224 cuts out a rectangular area corresponding to the laminate original detected by the second area detection unit 221 from the read image data.

  The image output unit 23 outputs the image data of the normal document or the laminate document cut out by the cutout unit 224 to, for example, a storage unit such as a RAM or a ROM, an external device that can communicate via the communication unit 6, and the like. When the image reading apparatus 1 includes a printing unit, the image output unit 23 may output the image data to the printing unit and print it.

  An example of the operation of the image reading apparatus 1 will be described below.

  FIG. 2 is a flowchart illustrating an example of the image reading process. For example, when receiving a reading start instruction from the user via the input unit 5 or the communication unit 6, the control unit 2 starts the process illustrated in the flowchart of FIG. 2. The control unit 2 causes the ADF 31 to transport a document (normal document or laminate document) and causes the reading unit 3 to read the document.

  First, the image acquisition unit 21 acquires read image data from the reading unit 3 (step S1). Further, the image acquisition unit 21 acquires the sensor output and encoder output output from the ADF 31.

  Then, the first area detection unit 221 performs threshold determination on the read image data acquired by the image acquisition unit 21 (step S2). For example, the first area detection unit 221 determines whether or not the gradation value of each pixel of the read image data exceeds a predetermined threshold, and an area larger than a predetermined area composed of pixels exceeding the predetermined threshold. Is specified as a pixel area constituting the document. Of course, the threshold determination method is not limited to the above method, and other existing algorithms can be used.

  In step S2, the first area detection unit 221 specifies the horizontal size of the document based on the specified document area. The first area detection unit 221 may specify, for example, the maximum width in the main scanning direction on the document area as the horizontal size. Further, the first region detection unit 221 specifies the vertical size of the document based on the sensor output (start and end of the document) and encoder output (rotation angle) acquired by the image acquisition unit 21. For example, the first area detection unit 221 may obtain the vertical size of the document from the rotation angle from the start to the end of the document and the document movement distance per unit rotation angle.

  Then, the first area detection unit 221 performs angle detection (step S3). For example, the first area detection unit 221 may identify a side that forms a corner of the document from the document region identified in step S2, and identify an inclination angle of the side with respect to the main scanning direction or the sub-scanning direction. In this way, the inclination of the document area is detected. Of course, the method of angle detection is not limited to the above method, and other existing algorithms can be used.

  Then, the first area detection unit 221 performs rectangle detection (step S4). For example, the first area detection unit 221 specifies a rectangular area corresponding to the original based on the vertical and horizontal sizes of the original area specified in step S2 and the inclination of the original area specified in step S3. In this way, the document area as a rectangular area is detected. Of course, the rectangle detection method is not limited to the above method, and other existing algorithms can be used.

  Then, the document type determination unit 223 performs document size determination (step S5). For example, the document type determination unit 223 compares the vertical and horizontal size of the document detected in step S2 with a predetermined reference vertical and horizontal size.

  If the vertical / horizontal size of the document is smaller than the reference vertical / horizontal size (step S5: laminate original), the second area detection unit 222 performs edge detection on the read image data output from the image acquisition unit 21 (step S5). S6). For example, the second area detection unit 222 performs, for each pixel of the read image data, a main scanning direction filter (for example, vertical and horizontal N × N pixels) and a sub-scanning direction filter (for example, vertical and horizontal N × N pixels). Is used to obtain the edge amount in the main scanning direction and the edge amount in the sub-scanning direction of each pixel. Further, the second region detection unit 222 compares the edge amount in the main scanning direction and the edge amount in the sub scanning direction for each pixel, and when the edge amount in the main scanning direction is larger than the sub scanning direction, The edge amount in the main scanning direction is output, and when the edge amount in the main scanning direction is equal to or less than the edge amount in the sub scanning direction, the edge amount in the sub scanning direction is output. In this way, edge image data including the edge amount of each pixel is generated. Of course, the edge detection method is not limited to the above method, and other existing algorithms such as a Sobel filter can be used.

  In step S6, the second region detection unit 222 executes binarization processing on the edge image data, and generates binary edge image data. In this binary edge image data, edge pixels appear in white. By such edge detection, in addition to the edge of the original body of the laminated document, the edge of the surrounding film can also be detected as edge pixels.

  In step S <b> 6, the second area detection unit 222 identifies an area corresponding to the laminate document from the binary edge image data. The second area detection unit 222 may specify, for example, the widest edge area of the rectangular closed edge areas as the outer edge of the laminate document in the area inside the outer edge of the edge image data. Further, the second area detection unit 222 specifies the vertical and horizontal sizes of the document based on the area corresponding to the specified laminate document. The second area detection unit 222 may specify, for example, the maximum width in the main scanning direction of the laminate document area as the horizontal size and the maximum width in the sub-scanning direction as the vertical size.

  Then, the second area detection unit 222 performs angle detection (step S7). For example, the second area detection unit 222 identifies the side that forms the corner of the laminate document from the laminate document area in the edge image data identified in step S6, and identifies the inclination angle of this side with respect to the main scanning direction or the sub-scanning direction. do it. In this way, the inclination of the laminate document area is detected. Of course, the method of angle detection is not limited to the above method, and other existing algorithms can be used.

  Then, the second area detection unit 222 performs rectangle detection (step S8). For example, the second area detection unit 222 identifies a rectangular area corresponding to the laminate document based on the vertical and horizontal sizes of the laminate document area identified in step S6 and the inclination of the laminate document area identified in step S7. In this way, a laminate document area as a rectangular area is detected. Of course, the rectangle detection method is not limited to the above method, and other existing algorithms can be used.

  When the vertical / horizontal size of the document is equal to or larger than the reference vertical / horizontal size (step S5: normal document) or after step S8, the clipping unit 224 performs inclination correction and clipping (steps S9 to S10).

  When the read original is a normal original, the cutout unit 224 rotates the read image data so that, for example, the two sides forming the corner of the rectangular area detected in step S4 coincide with the main scanning direction and the sub-scanning direction. Let Further, the cutout unit 224 cuts out image data of the rectangular area from the rotated read image data. The image output unit 23 outputs the image data of the normal document cut out by the cutout unit 224.

  When the read original is a laminate original, the cutout unit 224 rotates the read image data so that, for example, the two sides forming the corner of the rectangular area detected in step S8 coincide with the main scanning direction and the sub-scanning direction. Let Further, the cutout unit 224 cuts out image data of the rectangular area from the rotated read image data. The image output unit 23 outputs the image data of the laminate document cut out by the cutout unit 224.

  As described above, the image reading apparatus 1 can determine whether the original is a normal original or a laminated original from the read image data, and can cut out an area corresponding to the normal original or the laminated original.

  The image reading apparatus 1 may have a “normal mode” for reading a normal document and a “laminate document mode” for reading both a normal document and a laminate document as operation modes. The image reading apparatus 1 may operate in an operation mode selected by the user, for example. The image reading apparatus 1 executes the flowchart shown in FIG. 2 when “laminate document mode” is selected. On the other hand, when the “normal mode” is selected, the image reading apparatus 1 may omit steps S5 to S8 and execute the processes of steps S1 to S4, S9, and S10.

  FIG. 3 is a diagram for explaining cutting out of a laminated document.

  FIG. 3A shows read image data 100 when a laminated original is read. The read image data 100 includes an area 120 corresponding to the original body of the laminated original, an area 130 corresponding to the film around the original body, and an area 140 corresponding to the background. Since the region 130 has high light transmittance, it is read with almost the same color as the background. Therefore, the threshold value determination process in step S2 of FIG. 2 cannot detect the area including the area 120 and the area 130 as the document area, and detects the area 120 as the document area.

  FIG. 3B shows binary edge image data 100 </ b> E of the read image data 100. The edge image data 100E includes an edge region 120E of the region 120 and an edge region 130E of the region 130. At the outer edge of the region 130, for example, a shadow of the film is generated, and a change in luminance with the background appears sharply. Therefore, the edge detection process in step S6 in FIG. 2 can detect the outer edge of the region 130 as an edge. In addition, the rectangle detection process in step S8 of FIG. 2 can specify a rectangular region including the edge region 130E.

  FIG. 3C shows image data 150 corresponding to a laminate document cut out from the read image data 100. The image data 150 includes an area 120 corresponding to the original body of the laminated original and an area 130 corresponding to the film around the original body. The cutout process in step S10 of FIG. 2 can cut out the image data 150 from the read image data 100 based on the rectangular area (edge area 130E) specified using the edge detection result.

  The first embodiment of the present invention has been described above. For example, the image reading apparatus 1 according to the present embodiment determines whether the read original is a normal original or a laminated original in a first area corresponding to the detected original (normal original or laminated original body). The size is determined by comparing the size and the reference vertical / horizontal size. In addition, when the read original is a laminated original, the image reading apparatus 1 sets the area corresponding to the original body and the peripheral portion thereof as the second area (the original body of the laminated original and the peripheral portion) by the edge detection process. Detect as. As a result, the image reading apparatus 1 can accurately determine the type of document (normal document or laminate document). Further, when the read original is a laminated original, the image reading apparatus 1 can accurately cut out the original body and the surrounding portion included in the laminated original. It is possible to prevent an erroneous area from being cut out by cutting out an area including a peripheral portion instead of cutting out only the original body of the laminated original.

  Further, for example, the image reading apparatus 1 specifies the vertical size of the document using the sensor output of the ADF 31, and specifies the horizontal size of the document by image processing. As a result, the image reading apparatus 1 can specify the vertical and horizontal sizes of the document in a shorter time than when specifying the vertical and horizontal sizes by image processing.

  Further, for example, the image reading apparatus 1 has “normal mode” and “laminate original mode”, and when “laminate original mode” is selected, the type of the read original (normal original or laminated original) Process according to the. The image reading apparatus 1 can appropriately cut out image data regardless of whether a normal document is set or a laminate document is set by a user.

  Further, for example, the image reading apparatus 1 detects the first area by the threshold determination process and detects the second area by the edge detection process. As a result, the image reading apparatus 1 can cut out image data for a normal document by image processing with a smaller processing amount than edge detection processing. Further, the image reading apparatus 1 can execute high-precision image processing for area detection on a laminated document.

[Second Embodiment]
The image reading apparatus 1 according to the second embodiment cuts out a document from the read image data by a processing procedure different from that of the first embodiment. Hereinafter, a description will be given focusing on differences from the first embodiment.

  FIG. 4 is a flowchart showing an example of an image reading apparatus according to the second embodiment of the present invention.

  The processes of steps S11 to S14 are the same as steps S1 to S4 of FIG. The rectangular area detected in step S14 is referred to as a “first area”.

  The processes in steps S15 to S17 are the same as steps S6 to S8 in FIG. The rectangular area detected in step S17 is referred to as a “second area”.

  Then, the document type determination unit 223 determines whether or not the size of the second area is larger than the size of the first area (step S18). When the laminate document is read, the size of the second area is larger than the size of the first area. On the other hand, when a normal document is read, the size of the second area is equal to or smaller than the size of the first area.

  When the size of the second area is larger than the size of the first area (step S18: YES), the cutout unit 224 performs processing for the laminate document (step S19). For example, the cutout unit 224 performs predetermined image processing so that the image quality of the image data of the laminated document is improved. The process executed in step S19 is not particularly limited as long as it is a process suitable for a laminate document.

  If the size of the second area is equal to or smaller than the size of the first area (step S18: NO), the setting for the normal document is performed (step S20). For example, the cutout unit 224 executes predetermined image processing so that the image quality of the image data of the normal document is improved. The process executed in step S20 is not particularly limited as long as it is a process suitable for a normal document.

  After step S19 or step S20, the cutout unit 224 performs inclination correction and cutout (steps S21 to S22). The processes in steps S21 to S22 are the same as the processes in steps S9 to S10 in FIG.

  Note that the image reading apparatus 1 may have the above-described “normal mode” and “laminate document mode” as operation modes. The image reading apparatus 1 executes the flowchart shown in FIG. 4 when the “laminate document mode” is selected. On the other hand, when the “normal mode” is selected, the image reading apparatus 1 may omit steps S15 to S19 and execute the processes of steps S11 to S14 and S20 to S22.

  The second embodiment of the present invention has been described above. For example, the image reading apparatus 1 according to the present embodiment determines whether the read original is a normal original or a laminated original in a first area corresponding to the detected original (normal original or laminated original body). And the size of the second area corresponding to the laminate document detected by the edge detection process (the document body of the laminate document and its surroundings). As a result, the image reading apparatus 1 can accurately determine the type of document (normal document or laminated document) based on the image characteristics of the read image data without using the reference vertical and horizontal sizes. Further, when the read original is a laminated original, the image reading apparatus 1 can accurately cut out the original body and the surrounding portion included in the laminated original. It is possible to prevent an erroneous area from being cut out by cutting out an area including a peripheral portion instead of cutting out only the original body of the laminated original.

  The present invention is not limited to the above-described embodiment, and can be implemented in various modes without departing from the scope of the invention. For example, the following modifications may be added to the above embodiments. Moreover, you may combine 2 or more suitably for embodiment and each modification.

  For example, the image reading apparatus 1 may read a normal document or a laminate document placed on a document table. In this case, the first area detection unit 221 may specify the vertical size of the document based on, for example, the result of executing the threshold determination process on the read image data.

  The configuration of the image reading apparatus 1 described in the above-described embodiment is classified according to main processing contents in order to make the configuration easy to understand. The present invention is not limited by the way of classification and names of the constituent elements. The configuration of the image reading apparatus 1 can be classified into more components according to the processing content. Moreover, it can also classify | categorize so that one component may perform more processes. Further, the processing of each component may be executed by one hardware or may be executed by a plurality of hardware. Further, the processing or function sharing of each component is not limited to the above as long as the object and effect of the present invention can be achieved.

  The processing unit described in the above embodiment is divided according to the main processing contents in order to facilitate understanding of the processing of the image reading apparatus 1. The present invention is not limited by the way of dividing the processing unit or the name. The processing of the image reading apparatus 1 can be divided into more processing units according to the processing content. Moreover, it can also divide | segment so that one process unit may contain many processes. Further, the above processing order is not limited to the illustrated example.

  The present invention can be provided not only as an image reading apparatus but also in other forms such as an image processing method, an image processing program, a recording medium storing the image processing program, and an image reading system.

DESCRIPTION OF SYMBOLS 1 ... Image reading apparatus, 2 ... Control part, 3 ... Reading part, 4 ... Display part, 5 ... Input part, 6 ... Communication part, 21 ... Image acquisition part, 22 ... Image processing part, 23 ... Image output part, 100 ... Reading image data, 100E ... Edge image data, 120 ... Area, 120E ... Edge area, 130 ... Area, 130E ... Edge area, 140 ... Area, 150 ... Image data, 221 ... First area detector, 222 ... No. 2 area detection unit, 223... Document type determination unit, 224.

Claims (7)

A scanning unit that scans a document and generates scanned image data;
An image acquisition unit for acquiring the read image data;
A first area detecting unit for detecting a first area corresponding to the original in the read image data;
A document type determination unit that compares the vertical and horizontal sizes of the first region with a predetermined reference vertical and horizontal size to determine whether the document is a laminate document;
When the original is determined to be a laminate original, the read image data is subjected to edge detection processing to generate edge image data, and based on the edge image data, the main body of the original in the read image data and its A second region detection unit for detecting a second region corresponding to the surrounding portion;
An image reading apparatus comprising: a cutout unit that cuts out image data of the second area from the read image data when the original is determined to be a laminate original. The image reading apparatus according to claim 1,
An automatic paper feeding device that sends the document to the reading unit and detects the start and end of the document;
The first area detection unit is an image reading apparatus that determines the vertical size based on the detected start and end of the document and determines the horizontal size based on the read image data. The image reading apparatus according to claim 1, wherein
Either normal mode or laminate original mode can be selected,
When the normal mode is selected,
The first region detection unit detects the first region in the read image data, and the cutout unit cuts out image data of the first region from the read image data,
When the laminate document mode is selected,
The first area detection unit detects the first area in the read image data, the document type determination unit determines whether the document is a laminate document, and the document is a laminate document. When the determination is made, the second area detection unit detects the second area in the read image data, and when the document is determined to be a laminate document, the cutout unit detects the read image. An image reading apparatus that cuts out image data of the second area from data and cuts out the image data of the first area from the read image data when the original is determined not to be a laminate original. The image reading apparatus according to any one of claims 1 to 3,
The first area detection unit generates image data obtained by performing a threshold determination process on the read image data, and performs an angle detection process and a rectangle detection process on the image data. Detect the area,
The second area detection unit is an image reading apparatus that detects the second area by performing an angle detection process and a rectangle detection process on the edge image data. A scanning unit that scans a document and generates scanned image data;
An image acquisition unit for acquiring the read image data;
A first area detecting unit for detecting a first area corresponding to the original in the read image data;
The read image data is subjected to edge detection processing to generate edge image data, and based on the edge image data, a second region corresponding to the main body of the original and the surrounding portion in the read image data is detected. A second region detection unit;
A document type determination unit that compares the vertical and horizontal sizes of the first area with the vertical and horizontal sizes of the second area and determines whether the document is a laminate document;
An image reading apparatus comprising: a cutout unit that cuts out image data of the second area from the read image data when the original is determined to be a laminate original. An image processing method for an image reading apparatus, comprising:
Scanning the document to generate read image data;
Obtaining the read image data;
Detecting a first area corresponding to the original in the read image data;
Comparing the vertical and horizontal sizes of the first region with a predetermined reference vertical and horizontal size to determine whether or not the original is a laminated original;
When the original is determined to be a laminate original, the read image data is subjected to edge detection processing to generate edge image data, and based on the edge image data, the main body of the original in the read image data and its Detecting a second region corresponding to the surrounding portion;
An image processing method including: cutting out the image data of the second area from the read image data when the original is determined to be a laminate original. An image processing method for an image reading apparatus, comprising:
Scanning the document to generate read image data;
Obtaining the read image data;
Detecting a first area corresponding to the original in the read image data;
The read image data is subjected to edge detection processing to generate edge image data, and based on the edge image data, a second region corresponding to the main body of the original and the surrounding portion in the read image data is detected. Steps,
Comparing the vertical and horizontal sizes of the first region and the vertical and horizontal sizes of the second region to determine whether or not the document is a laminate document;
An image processing method including: cutting out the image data of the second area from the read image data when the original is determined to be a laminate original.

Images