Image reading system, image reading device, image reading method for document reading system, program

Abstract

To provide an image reading device capable of making cropping suitable for a type of an original document when automatically cropping only an original document image from an image that has been read.SOLUTION: The image reading device includes a discriminating unit for discriminating a type of a scanned document, a cropping unit for cropping a partial image corresponding to a document from the scanned image, and a control unit for controlling a method for cropping a partial image from a scanned image by the cropping unit on the basis of the type of the document as discriminated by the discriminating unit. The discriminating unit discriminates whether the document is a photograph or not.SELECTED DRAWING: Figure 10

Description

Technical Field

[0001] The present invention relates to an image reading control technique in an image reading apparatus.

Background Art

[0002] Some image reading apparatuses for reading an image of a document have an automatic size detection function for automatically cutting out only the document image from the read image.

[0003] For the automatic size detection function, there are two types of size detection methods when the document placed on the document table is a non-rectangular quadrilateral. The first method is, as shown in FIG. 6, to detect four points of a non-rectangular quadrilateral and set the circumscribed rectangle including all of the four points as the size of the output image. The second method is, as shown in FIG. 7, to detect four points of a non-rectangular quadrilateral and set the inscribed rectangle inscribed in the document as the size of the output image.

[0004] For example, Patent Document 1 discloses a method of cutting out an image with the circumscribed rectangle of a non-rectangular image and outputting the image, that is, a method of outputting an image by the above-described first method.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] The above-described first method and second method each have advantages and disadvantages. When cutting out an image with a circumscribed rectangle as in the first method, the output image can be obtained without loss of information, which is effective when it is not desired to lose the image information in the peripheral portion. However, when reading a photograph or the like, an extra margin is formed in the output image, and when performing a borderless print or the like, the image may look unpleasant.

[0007] Furthermore, when cropping an image using an inscribed rectangle, as in the second method, there are no margins in the output image, but image information in the peripheral areas is lost.

[0008] In other words, when extracting images, the choice between the first and second methods depends on the type of source material; using one method uniformly will not result in proper image output.

[0009] The present invention has been made in view of the above-mentioned problems, and its objective is to provide an image reading device that can automatically extract only the original document image from the scanned image, and can perform extraction suitable for the type of original document. [Means for solving the problem]

[0010] The image reading system according to the present invention includes a reading means for reading a document as an image, a discrimination means for determining the type of the document, and the reading means for reading the document. The picture Is it a statue? manuscript area One of several cropping methods to extract it as a partial image One cutting method The system includes a cropping means that extracts a partial image from the image, wherein the determination means determines whether the type of the original is a photograph, and the cropping means changes the cropping method based on the determination result of the determination means. The means is such that, when the determination means determines that the type of the document is a photograph, the partial image cut out by the cutting means is a rectangle inscribed within the document area from the image read by the reading means. It is characterized by the following: [Effects of the Invention]

[0011] According to the present invention, when automatically extracting only the original document image from a scanned image, the extraction can be performed in a manner suitable for the type of original document. [Brief explanation of the drawing]

[0012] [Figure 1] A partial cross-sectional view schematically showing the configuration of an image reading device according to one embodiment of the present invention. [Figure 2] Block diagram of the control unit of image reading device A. [Figure 3] Front view of the discharge tray 2 of the image reading device A in the deployed state. [Figure 4] Front view of the discharge tray 2 of the image reading device A in the stored state. [Figure 5] Cross-sectional view of the image reading unit 70 of the image reading device A. [Figure 6] Diagram showing the state of cutting out the circumscribed rectangle of the image. [Figure 7] Diagram showing the state of cutting out the inscribed rectangle of the image. [Figure 8] Flowchart showing the operation of scanning a document in one embodiment. [Figure 9] Diagram showing the arrangement of the light emitting element and the light receiving element inside the image reading unit 70. [Figure 10] Flowchart showing the process of cutting out the image to be output from the read image. [Figure 11] Flowchart showing the method of calculating the rectangle inscribed in the document. [Figure 12] Flowchart showing the method of automatically determining the type of document. [Figure 13] Diagram showing a photographic document with a white border around the image. [Figure 14] Flowchart showing the reading operation of the photographic document with a white border. [Figure 15] Flowchart showing the cutting process of the white border document. [Figure 16] Diagram showing a document with non - straight sides. [Figure 17] Flowchart showing the reading process of the distorted photographic document. [Figure 18] Flowchart showing the cutting process of the distorted photographic document. [Figure 19] Flowchart showing the process of cutting out the image to be output from the read image. [Figure 20] Flowchart showing the method of calculating the rectangle inscribed in the document. [Figure 21] Diagram showing the screen displayed for inputting / selecting the cutting position. [Figure 22]A diagram showing the screen displayed to indicate the cutting position. [Figure 23] A diagram showing how to extract an inscribed rectangle from an image. [Modes for carrying out the invention]

[0013] Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following embodiments are examples for carrying out the present invention, and the present invention is not limited to these embodiments. The present invention should be modified or changed as appropriate depending on the configuration of the apparatus and various conditions in which it is used, without departing from the spirit of the present invention.

[0014] (First embodiment) First, an image reading device according to the first embodiment of the present invention will be described.

[0015] Figure 1 is a schematic partial cross-sectional view showing the configuration of an image reading device according to a first embodiment of the present invention.

[0016] <Device Configuration> Image reading device A is a device that takes one or more transport media (originals) S loaded on a loading platform 1 into the device one by one, reads their images while transporting them along a path RT, and discharges them into an output tray 2 which serves as a loading component. The transport media S to be read are sheets such as photographs, office paper, checks, cheques, business cards, and cards, and may be thick or thin sheets. Examples of cards include insurance cards, driver's licenses, and credit cards. The transport media S also includes booklets such as passports. When booklets are the target, a holder can be used. By placing an open booklet in a transparent holder on the loading platform 1, the booklet is transported together with the holder, and its image can be read.

[0017] <Paper feed> Image reading device A has a first transport unit 10 as a transport mechanism that feeds transport medium S along path RT. The first transport unit 10 comprises a feed roller 11 and a separation roller 12 positioned opposite the feed roller 11, and sequentially transports the transport medium S on the mounting table 1 one by one in the transport direction D1. Driving force is transmitted to the feed roller 11 from a drive unit 3 such as a motor via a transmission unit 5, and it is rotated in the direction indicated by arrow D2 in the figure (the positive direction for transporting the transport medium S along path RT). The transmission unit 5 is, for example, an electromagnetic clutch, which intermittently transmits the driving force from the drive unit 3 to the feed roller 11.

[0018] <Drive Unit> The transmission unit 5, which connects the drive unit 3 and the feed roller 11, is configured, for example, to transmit driving force under normal circumstances, and to cut off the driving force when the conveyed medium S is reversed or stopped. When the transmission of driving force to the feed roller 11 is cut off by the transmission unit 5, the feed roller 11 becomes capable of free rotation. Note that such a transmission unit 5 may not be necessary if the feed roller 11 is driven in only one direction.

[0019] <Separated structure> The separation roller 12, positioned opposite the feed roller 11, is a roller for separating the conveying medium S one by one (one sheet at a time), and is pressed against the feed roller 11 with constant pressure. To ensure this pressure contact, the separation roller 12 is provided to be swingable and is configured to be biased toward the feed roller 11. The separation roller 12 is driven to rotate in the direction indicated by the solid arrow (opposite to the forward direction of the feed roller 11) by a driving force transmitted from the drive unit 3 via a torque limiter 12a.

[0020] Because the transmission of driving force to the separation roller 12 is restricted by the torque limiter 12a, when it is in contact with the feed roller 11, it rotates in the direction that follows the feed roller 11 (indicated by the dashed arrow). As a result, when multiple conveying media S are conveyed to the contact area between the feed roller 11 and the separation roller 12, two or more conveying media S are separated so that they are not conveyed downstream.

[0021] In this embodiment, a separation mechanism is configured with a separation roller 12 and a feed roller 11. However, such a separation mechanism is not necessarily required; any feed mechanism that sequentially feeds the transport medium S one by one along the path RT will suffice. Furthermore, if a separation mechanism is provided, instead of a configuration like the separation roller 12, a separation pad that applies frictional force to the transport medium S may be pressed against the feed roller 11 to provide a similar separation function.

[0022] <Conveying Structure> The second conveying unit 20, located downstream of the first conveying unit 10 in the conveying direction, is equipped with a drive roller 21 and a driven roller 22 that moves with the drive roller 21, and conveys the conveying medium S that has been conveyed from the first conveying unit 10 to its downstream side. The drive roller 21 is driven by a drive unit 4 such as a motor and is rotationally driven in the direction of the arrow in the figure. The driven roller 22 is pressed against the drive roller 21 with a constant pressure and rotates along with the drive roller 21. The driven roller 22 may be configured to be biased against the drive roller 21 by a biasing unit (not shown) such as a spring.

[0023] The third conveying section 30, located downstream of the second conveying section 20 in the conveying direction, is equipped with a drive roller 31 and a driven roller 32 that moves in accordance with the drive roller 31, and conveys the conveying medium S that has been conveyed from the second conveying section 20 to the discharge tray 2. In other words, this third conveying section 30 functions as a discharge mechanism.

[0024] The drive roller 31 receives driving force from a drive unit 4 such as a motor and is rotated in the direction of the arrow in the figure. The driven roller 32 is pressed against the drive roller 31 with constant pressure and rotates along with the drive roller 31. The driven roller 32 may be configured to be biased against the drive roller 31 by a biasing unit (not shown) such as a spring.

[0025] The output tray 2 for loading documents is pivotally supported via a first hinge 101 located below the image reader A, so as to be rotatable relative to the image reader A. The output tray 2 consists of a first output tray 2a on the first hinge 101 side and a first extension tray 2b connected to its tip. The first extension tray 2b is supported so as to be slidable and stowable relative to the first output tray 2a.

[0026] <Image reading structure, control> In this embodiment, the image reading device A reads images using an image reading unit 70 positioned between the second transport unit 20 and the third transport unit 30. Therefore, the second transport unit 20 and the third transport unit 30 transport the transport medium S at a constant speed. By ensuring that the transport speed is always greater than or equal to the transport speed of the first transport unit 10, it is possible to reliably avoid situations where the following transport medium S catches up to the preceding transport medium S. For example, in this embodiment, the transport speed of the transport medium S by the second transport unit 20 and the third transport unit 30 is controlled to be faster than the transport speed of the transport medium S by the first transport unit 10.

[0027] Furthermore, even if the transport speed of the transport medium S by the second transport unit 20 and the third transport unit 30 is the same as the transport speed of the transport medium S by the first transport unit 10, it is possible to create a minimum gap between the preceding transport medium S and the succeeding transport medium S by controlling the drive unit 3 to intermittently shift the timing of the start of feeding the subsequent transport medium S.

[0028] <Re-feed detection> The double-feed detection sensor 40, positioned between the first transport unit 10 and the second transport unit 20, is an example of a detection sensor (a sensor that detects the behavior and state of sheets) that detects when transport media S, such as paper, become tightly attached to each other due to static electricity or the like and pass through the first transport unit 10 (i.e., when they are transported in a double-feed state). Various types of sensors can be used for the double-feed detection sensor 40, but in this embodiment it is an ultrasonic sensor, comprising an ultrasonic transmitter 41 and a receiver 42, and detects double-feeds based on the principle that the attenuation of ultrasonic waves passing through the transport media S differs depending on whether the transport media S, such as paper, are being transported in a double-feed state or one at a time.

[0029] <Resistance Sensor> The medium detection sensor 50, located downstream in the transport direction from the aforementioned double-feed detection sensor 40, is located upstream of the second transport unit 20 and downstream of the first transport unit 10, and is an example of a detection sensor (a sensor that detects the behavior and state of the sheet) located upstream of the transport path RT. The medium detection sensor 50 detects the position of the transport medium S transported by the first transport unit 10, and more specifically, whether the end of the transport medium S has reached or passed the detection position of the medium detection sensor 50. Various types of medium detection sensors can be used, but in this embodiment, it is an optical sensor comprising a light-emitting unit 51 and a light-receiving unit 52, and detects the transport medium S based on the principle that the light-receiving intensity (amount of light received) changes when the transport medium S reaches or passes through.

[0030] In this embodiment, the medium detection sensor 50 is located downstream of the double-feed detection sensor 40, so that when the leading edge of the transport medium S is detected by the medium detection sensor 50, the transport medium S has reached a position where a double-feed can be detected by the double-feed detection sensor 40. Note that the medium detection sensor 50 is not limited to the optical sensor described above; for example, a sensor capable of detecting the end of the transport medium S (such as an image sensor) may be used, or a lever-type sensor protruding from the path RT may be used. Furthermore, multiple sensors may be provided in a direction perpendicular to the transport direction to detect if the medium is moving obliquely to the transport path.

[0031] A media detection sensor 60 different from the media detection sensor 50 is arranged upstream of the image reading unit 70. This media detection sensor 60 is an example of a downstream detection sensor arranged downstream of the second conveyance unit 20, and detects the position of the conveyance medium S conveyed by the second conveyance unit 20. As the media detection sensor 60, various types can be used. In the case of this embodiment, it is an optical sensor similar to the media detection sensor 50, includes a light emitting unit 61 and a light receiving unit 62, and detects the conveyance medium S based on the principle that the light receiving intensity (light reception amount) changes due to the arrival or passage of the conveyance medium S. In this embodiment, the media detection sensors 50 and 60 are arranged on the upstream side and the downstream side of the conveyance direction of the second conveyance unit 20, respectively, but only one of them may be used.

[0032] <Arrangement of CIS> The image reading unit 70 downstream of the media detection sensor 60 optically scans, for example, an image of the conveyance medium S, converts it into an electrical signal, and reads it as image data, and includes a light source such as an LED, an image sensor, a lens array, etc. inside. The image reading unit 70 is a contact image sensor (CIS) unit. Here, the image reading unit 70 is a CIS unit, but for example, it may be a unit using a two-dimensional CCD as an image sensor, and the type of the image sensor is not limited. In the case of this embodiment, the image reading units 70 (hereinafter synonymous with CIS) are arranged one on each side of the path RT (70a, 70b) and read the front and back surfaces of the conveyance medium S. However, it may be configured to arrange only one on one side of the path RT and read only one side of the conveyance medium S. Also, in this embodiment, the image reading units 70 are arranged to face each other on both sides of the path RT, but for example, they may be arranged at intervals in the direction of the path RT.

[0033] <Explanation of block diagram> Referring to FIG. 2, the control unit 80 of the image reading apparatus A will be described. FIG. 2 is a diagram showing the block configuration of the control unit 80 of the image reading apparatus A.

[0034] The control unit 80 includes a CPU 81, a storage unit 82, a communication unit 84, and an interface unit (a) 85a. The CPU 81 (microcomputer) controls various functions such as reading control of the image reading device A, transport of media, and notification to the operator by executing programs stored in the storage unit 82. The operation unit 83 is configured with, for example, switches 83c, a touch panel 83a, and a display device 83b, and displays information to the operator and accepts operations from the operator.

[0035] Here, the control unit 80 may have multiple CPUs, memory units, communication units, and interface units. For example, one CPU may control the reading of the image reading device A and the transport of the media, while another CPU may provide notifications to the operator. In other words, the functions may be divided and controlled by multiple control systems.

[0036] The communication unit 84 is an interface for communicating information with an external device connected to the CPU 81. If the external device is assumed to be a PC (personal computer), the communication unit 84 could be, for example, a USB interface or a SCSI interface. It could also be a wired network interface such as a LAN, or a wireless communication interface such as a wireless LAN or short-range wireless communication. The communication unit 84 may have multiple communication interfaces.

[0037] Interface section (a) 85a is an I / O interface connected to the CPU 81, which performs data input and output with the actuator 86 and sensor 87. The actuator 86 includes a drive unit 3, a drive unit 4, a transmission unit 5, etc. The sensor 87 includes a double-feed detection sensor 40, a medium detection sensor 50 and 60, etc. Interface section (b) 85b is a control interface connected to the display device 83b of the operation unit 83, for example. Possible interfaces for display control include SPI, USB interface, eDP, HDMI (registered trademark), etc.

[0038] <Display Panel Configuration> Figure 3 is a front view of the image reading device A in this embodiment with the output tray 2 unfolded. More precisely, it is a view taken from a direction perpendicular to the front panel 90, which is angled to the front side of the image reading device A, and is a view taken from slightly above the front when the device is mounted.

[0039] A display panel 93 is provided on the front panel 90 at the top of the front, and inside it are a power button 122, which is one of the switches as an example of the operation unit 83, and a display unit 94. Here, the display unit 94 consists of a touch panel 83a, a display device 83b, etc.

[0040] The display device 83b is, for example, a liquid crystal display, and can display a screen according to the status of the device and provide the operator with device information. An example of a screen that can be displayed is a screen consisting of a start key for starting the operation of the image reading device A, and a list of jobs that specify reading operations (for example, reading resolution, output method and destination of read image data, etc.) that have been registered in advance on the image reading device A. Icons indicating the status of the device may also be displayed.

[0041] In this embodiment, an example has been described in which the image reading device A has an image processing unit 88, a display panel 93, and an operation unit 83, but it is not limited to this. For example, the image processing unit 88 may be implemented by application software on a PC, which is an external device connected to the image reading device A. In that case, the user interface corresponding to the display panel 93 and operation unit 83 can be implemented by the PC's display screen, keyboard, touch panel, or other operation unit.

[0042] <Control during double feeding> During the image reading operation, the transport medium S is checked for double feeds by the double feed detection sensor 40 during transport, and if no double feed is detected, transport continues. If a double feed is detected, transport may be stopped, or the first transport unit 10 may stop taking in subsequent transport mediums S and discharge the transport medium S that is in the double feed state. Alternatively, a notification that a double feed has occurred may be displayed on an external PC or an internal display device 83b. At the same time, a recovery process may be performed, for example, continuing reading, or discarding the read data of the double-feeded transport medium S and starting the reading process from transport medium S for which no image reading data including the double-feeded transport medium S has been acquired.

[0043] <Start reading and transmit / save the read image according to the output of the resist sensor> The control unit 80, at a timing based on the detection result of the medium detection sensor 60, starts reading images from the transport medium S transported by the second transport unit 20 using the image reading unit 70, processes the read image data, stores it temporarily, and transmits it sequentially to the outside of the device. The temporarily stored image data is transmitted via the communication unit 84 to a connected external PC or network device. Here, the external PC may display the received read image and then save it, or it may directly save the received read image to a predetermined location. Alternatively, it may save it to a predetermined location on a network device, such as an external storage device or FTP server directly connected to the network. The image processing of the image data read by the image reading unit 70 may be performed by the control unit 80, or by an external PC or external device. Naturally, multiple functions may be divided and processed by multiple control units 80, external PCs, or external devices.

[0044] <Paper output structure> The transport medium S from which the image has been read is discharged to the discharge tray 2 by the third transport unit 30, and the image reading process for the transport medium S is completed. The discharge tray 2 is an example of a document placement table.

[0045] A discharge opening 92 is provided in the lower panel 91 at the lower front of the unit, through which the transport medium S transported by the third transport unit 30 is discharged.

[0046] Figure 4 is a front view of the image reading device A in this embodiment with the output tray 2 retracted. The output tray 2 is pivotally supported via a first hinge 101 located below the image reading device A so as to be rotatable relative to the image reading device A, and is configured to cover the front of the main body with the first output tray 2a.

[0047] The tip of the first hinge arm portion 2ac of the first output tray 2a engages with the first hinge 101, and the first output tray 2a is attached to the main body of the image reading device A so as to be rotatable around the first hinge 101. The first output tray 2a is formed to the same size as the front panel 90, and in the stored state of the output tray 2 as shown in Figure 4, it rotates around the first hinge 101 as a pivot point and folds to cover the front panel 90. Even when the output tray 2 is folded towards the front panel 90, the output opening 92 remains open, allowing the transported transport medium S to be discharged.

[0048] <CISユニットのアース> Figure 5 is a cross-sectional view of the image reading unit 70 of the image reading device A according to this embodiment.

[0049] In this embodiment, the image reading units 70 are arranged opposite each other on both sides of the transport path RT, and will be referred to as image reading units 70a and 70b in the following description. Image reading units 70a and 70b are sensor units having the same structure, arranged symmetrically on either side of the transport path RT.

[0050] The image reading unit 70a is equipped with a contact image sensor (hereinafter referred to as CIS) 71a and a color reference plate 72a inside.

[0051] The driving force of a CIS sliding motor (not shown) located in the lower unit 104 is transmitted via a transmission member 74 and a transmission member connecting part 150 provided at the bottom of the image reading unit 70, thereby positioning the CIS 71a and color reference plate 72a to be slidable in the transport direction. By sliding the CIS 71a and color reference plate 72a, it is possible to switch between the color of the color reference in shading correction and the background color in image reading.

[0052] If the color reference plate 72b is white and the background color of the image to be read is white, the CIS 71a is slid by the CIS sliding motor 73 to position the reading position opposite the color reference plate 72b, thereby enabling white background reading. At this time, since the CIS 71a and the color reference plate 72a move together, when the CIS 71a is positioned in the white background position, the color reference plate 72a is positioned opposite the reading position of the CIS 71b, enabling white background reading with both the image reading units 70a and 70b. If the color reference plates 72a and 72b are not white, a separate white background section is provided and the CIS 71a and 71b are moved to the position of the white background section, enabling white background reading.

[0053] To make the background color of the read image black, the reading position of CIS71a is positioned at the opposite black background area 76b, enabling reading of images with a black background.

[0054] By diffusing the light emitted from the light-emitting element in CIS71a on the slope of the black background section 76b, and preventing light from entering the light-receiving element in CIS71a, reading from the black background is achieved.

[0055] This example demonstrates a configuration that switches the background color for reading, but switching the background color is not mandatory; it can be fixed to white, black, or any other color.

[0056] The image reading unit 70b has a similar structure to the image reading unit 70a, but the CIS 71b is not driven by the CIS sliding motor 73 and is fixed within the unit.

[0057] When the image reading unit 70a is inserted into the housing portion of the lower unit 104, it is inserted while biasing a metal lower elastic member protruding from the lower unit 104 side, and is fitted and fixed at the completion position of housing.

[0058] The lower surface of the image reading unit 70a is covered with a metal member (not shown), and electrical components such as the CIS 71a are grounded. By inserting while biasing the lower elastic member with the metal member, the image reading unit 70 is grounded to the lower unit 104.

[0059] <Drive by receiving a start instruction from the PC> The basic operation of the image reading apparatus A will be described. When the control unit 80 receives an image reading start instruction from, for example, an external personal computer or control device to which the image reading apparatus A is connected, it starts driving the first conveyance unit 10, the second conveyance unit 20, and the third conveyance unit 30. The conveyance medium S stacked on the mounting table 1 is conveyed one by one from the conveyance medium S located at the bottommost. Here, the connection to the external personal computer or control device is assumed to be a communication unit 84 included in the control unit 80, such as a USB interface, a SCSI interface, a LAN, or a wireless LAN.

[0060] <Drive by receiving a start instruction from the device operation> Also, instead of an instruction to start reading from an external personal computer or control device, an image reading instruction may be received by an input from a start key (not shown) provided on the operation unit 83 of the image reading apparatus A or a touch panel 83a, and the image reading operation may be started.

[0061] <Scanning operation> As described above, the control unit 80 starts scanning an image when it receives a reading start instruction (start instruction) from an external PC or operation unit 83. The start instruction includes information such as the reading resolution setting, color resolution (color or monochrome), and color correction. If a photograph is used as the transport medium S, the image reading instruction instructs the control unit 80 to be in photograph reading mode. If the transport medium S is not a photograph, another reading mode is selected and instructed to the control unit 80.

[0062] Although it was explained that the image reading instruction specifies whether to use photo reading mode or another reading mode, as mentioned above, this can also be specified by the operator, or the control unit 80 can determine this based on the data read from the image. In other words, the image reading instruction does not necessarily specify whether or not to use photo reading mode.

[0063] There may be multiple other reading modes, and the reading mode may be set according to the type of transport medium S. The control unit 80 performs optimal processing according to the transport medium S by changing the reading mode. In other words, the control unit 80 determines the type of document being transported based on the instruction whether it is a photo reading mode or another reading mode, and performs optimal processing according to the type of transport medium S, including image processing such as the document cutting operation described later.

[0064] <Start reading based on the output of the resist sensor> The control unit 80 reads the transport medium S that has been transported by the second transport unit 20 using the image reading unit 70. The start of reading is determined by the timing based on the detection result of the medium detection sensor 60 included in the sensor 87. The control unit 80 reads images from the image reading unit 70 at regular intervals according to the set reading resolution and the movement speed of the transport medium S.

[0065] <Image reading and processing> The image read by the image reading unit 70 undergoes various image processing in the image processing unit 88 and is then transmitted to an external control device via the communication unit 84. The detailed flow when the transport document S is a photograph will be described later.

[0066] As mentioned above, the image reading units 70a and 70b are positioned on either side of the transport path RT and are configured to read both sides of the transport medium S. When the operator places the transport medium S on the platform 1, they place it so that the front surface of the transport medium S is in contact with the platform, that is, so that the back surface is visible to the operator when the transport medium S is placed on the platform 1. The transport medium S is then transported, and the front surface of the transport medium S is read by the image reading unit 70a, and the back surface is read by the image reading unit 70b. If the transport medium S is a photograph, the front surface is the side with the print. The images of the front and back surfaces read by the image reading unit 70 are transmitted as image data to an external control device. Here, the surface read by the image reading unit 70a is considered the front surface, but the orientation of the transport medium S when it is placed on the platform 1 can be reversed, that is, so that the front surface is visible when the transport medium S is placed on the platform 1, and the surface read by the image reading unit 70a is considered the back surface.

[0067] <Automatic size detection function> The image reading device A of this embodiment is equipped with an automatic size detection function that automatically extracts only the original image (a partial image corresponding to the original) from the scanned image. The automatic size detection function can be switched ON / OFF by the operator.

[0068] Specifically, when the automatic size detection function is turned ON, the control unit 80 crops the output image from the scanned image using the following two cropping methods. In the first method, if the document placed on the document glass is a rectangle that is not a rectangle, as shown in Figure 6, the control unit 80 detects four points of the non-rectangular rectangle from the scanned image and uses the bounding rectangle containing all four points as the size of the output image. In the second method, as shown in Figure 7, four points of the non-rectangular rectangle are detected and the bounding rectangle inscribed within the document is used as the size of the output image.

[0069] In this embodiment, even if the original document is not rectangular but has a distorted shape, the inscribed rectangle is still extracted in the second method. Details of this process will be described later.

[0070] In this embodiment, the control unit 80 selects either the first method or the second method depending on the type of transport medium S, and extracts the image using the selected method to obtain the output image. The type of transport medium S may be manually set by the operator, or it may be automatically set by the control unit 80 based on the data of the scanned image. If the operator sets it manually, the operator manually checks a checkbox on the user interface indicating whether it is a photographic original or another type of original, or operates a switch indicating the type of original, and the control unit 80 receives this signal and sets the type of original.

[0071] <Document cutting operation> Next, in this embodiment, we will describe the operation of changing the method of cropping the scanned image depending on the type of transport medium (original) S.

[0072] Figure 8 is a flowchart showing the operation of scanning a document in this embodiment.

[0073] First, in step S301, the scanning of the document begins.

[0074] In step S302, it is determined whether the image reading size setting set by the operator is for automatic size detection or not. If it is for automatic size detection, the process proceeds to step S303; otherwise, the process proceeds to step S306.

[0075] In step S303, four points (the four corners) of the scanned document are detected.

[0076] Here, we will explain how to detect the edges of the document. For example, when scanning a document, if the background is white and the document itself has text or images printed on a white background, it may be difficult to distinguish between the background and the edges of the document in the scanned image. Therefore, in this embodiment, the edges of the document are detected using the following method.

[0077] Figure 9(a) shows the arrangement of light-emitting elements and light-receiving elements inside the image reading units 70a and 70b. In the image reading unit 70a, which reads the surface of the original document S, the light-emitting element 751 is positioned to emit light obliquely toward the front in the transport direction of the original document S, as indicated by the dashed arrow F. The light-receiving element 752 receives the light emitted from the light-emitting element 751 and reflected from the surface or background of the original document S. At this time, because the light from the light-emitting element 751 is emitted obliquely, a shadow 771 is formed at the leading edge Sa of the original document S in the transport direction, as shown in Figure 9(b). The light-receiving element 752 can detect this shadow 771 even if it cannot detect the leading edge Sa of the original document S. In other words, a shadow 771 exists at the leading edge of the original document in the transport direction of the scanned image data, and the position of the leading edge Sa of the original document S in the transport direction can be detected by the position of this shadow.

[0078] On the other hand, in the image reading unit 70b that reads the back side of the document S, the light-emitting element 761 is positioned to emit light obliquely toward the rear in the transport direction of the document S, as shown by the dashed arrow G. The light-receiving element 762 receives the light emitted from the light-emitting element 761 and reflected from the back side or background of the document S. At this time, because the light from the light-emitting element 761 is emitted obliquely, a shadow 781 is formed at the rear end Sb of the document S in the transport direction. The light-receiving element 762 can detect this shadow 781 even if it cannot detect the rear end Sb of the document S. In other words, a shadow 781 exists at the rear end of the document in the transport direction of the scanned image data, and the position of the rear end Sb of the document S in the transport direction can be detected by the position of this shadow.

[0079] The edges of the original document S in the width direction (the direction perpendicular to the transport direction) can also have their shadows detected using the same principle. In the width direction, although the light from the light-emitting element is not emitted at an angle, the shadow can be detected because the original document S may lift due to fluttering or other factors during transport.

[0080] In this way, by detecting the position of the shadow formed on the edges of the original document S, the leading edge, trailing edge, and width edges of the original document S can be detected, and four points (the four corners) of the scanned original document can be detected.

[0081] In step S304, the detected coordinates (X1,Y1) of the upper left corner are corrected to (0,0). Accordingly, the other three points are also corrected for skew by subtracting (X1,Y1) from their detected coordinates. Conventional methods can be used to correct the skew. Alternatively, techniques such as affine transformation may be used to correct the skew.

[0082] In step S305, a cropping process is performed to extract the output image from the scanned image. The cropping process is performed using the method shown in Figure 10.

[0083] In Figure 10, the cutting process is first started in step S401.

[0084] In step S402, it is determined whether the type of document selected by the operator is a photograph or not. Note that the type of document is set manually by the operator. If the type of document is a photograph, the process proceeds to step S403; if the type of document is a document, the process proceeds to step S404.

[0085] In step S403, since the document type is a photograph, cropping the image with a rectangle that circumscribes the image would crop out the white margins outside the photograph along with the photograph. To avoid this, a rectangle that inscribes the image is calculated. This prevents the white border from being printed in borderless printing and other cases, thus preventing unsightly images.

[0086] In step S404, since the document type is not a photograph, it is not a problem if the white margins are also cropped, so the rectangle circumscribing the image is calculated. Alternatively, the size of the document detected by automatic size detection (for example, A4 size) may be used as the size of the circumscribing rectangle (A4 size).

[0087] Here, Figure 11 is a flowchart showing the method for calculating the rectangle inscribed in the original document, which is performed in step S403 of Figure 10.

[0088] First, in step S501, the calculation of the inscribed rectangle begins.

[0089] In step S502, the lengths of the four sides of the rectangle of the original document are calculated from the coordinates of the four points corrected in step S303 of Figure 8. At this time, the top side is calculated as the difference between the X coordinates of the upper left corner and the X coordinates of the upper right corner, and the length related to the Y component is not included. The length of the bottom side is calculated using the same method. The length of the left side is calculated from the difference between the Y coordinates of the upper left corner and the Y coordinates of the lower left corner, and the length of the right side is calculated using the same method.

[0090] In step S503, the difference between the lengths of the top and bottom sides (=L1) and the difference between the lengths of the left and right sides (=L2) calculated in step S502 are calculated.

[0091] In step S504, it is determined whether both the difference L1 and the difference L2 calculated in step S503 are zero. If at least one of the differences L1 and L2 is not zero, the process proceeds to step S505. If both the difference L1 and the difference L2 are zero, the process proceeds to step S509.

[0092] In step S505, it is determined whether the difference L1 is 2 mm or less. If the difference L1 is 2 mm or less, the process proceeds to step S506. If the difference L1 is greater than 2 mm, the lengths of the top and bottom sides are compared, the length of the shorter side is adjusted to match the length of the longer side, and the process proceeds to step S507.

[0093] In step S506, the lengths of the top and bottom sides are compared, and the length of the longer side is adjusted to match the length of the shorter side (by subtracting the difference L1 from the length of the longer side).

[0094] In step S507, the difference L1 The process determines whether the difference L2 is 2mm or less. If the difference L1 is 2mm or less, the process proceeds to step S508. If the difference L1 is greater than 2mm, the lengths of the left and right sides are compared, the length of the shorter side is adjusted to match the length of the longer side, and the process proceeds to step S509.

[0095] In step S508, the lengths of the left and right sides are compared, and the length of the longer side is adjusted to match the length of the shorter side (by subtracting the difference L2 from the length of the longer side).

[0096] In step S509, the rectangle is calculated based on the side lengths set up to this point, and the calculation of the inscribed rectangle is completed.

[0097] On the other hand, returning to Figure 10, in step S405, the read image is cropped based on the size of the rectangle calculated in step S403 or in step S404.

[0098] Step S406 completes the document cutting process.

[0099] In the above explanation, the operator manually set the document type, but the document type can also be determined automatically. Figure 12 is a flowchart showing a method for automatically determining the document type.

[0100] In step S701, the automatic detection process for the type of document is started.

[0101] In step S702, the read multi-level image is converted into a binary halftone image using error diffusion.

[0102] In step S703, it is determined whether or not there are halftone dots in the image based on whether the area of ​​interest in the binary halftone image is surrounded by the same color, either white or black, and whether or not there are pixels of a different color from the surrounding area within the area of ​​interest, and the number of halftone dots is calculated.

[0103] In step S704, it is determined whether the number of halftone dots obtained in step S703 is equal to or greater than a predetermined threshold. If the number of halftone dots is equal to or greater than the threshold, the process proceeds to step S705; otherwise, the process proceeds to step S706.

[0104] In step S705, the scanned document is determined to be a photographic document.

[0105] In step S706, the scanned document is determined to be a document.

[0106] Then, in step S707, the automatic detection process for the type of document is terminated.

[0107] Here, some photographic originals have a white border around the image, as shown in Figure 13. For photographs with white borders, cropping with a circumscribed rectangle and adding a margin has the advantage of preventing loss of information and resulting in an output image with minimal margins, rather than cropping with an inscribed rectangle.

[0108] Figure 14 is a flowchart showing the process of cropping an image from a photograph with a white border.

[0109] In step S901, begin scanning the document.

[0110] In step S902, it is determined whether the image reading size setting set by the operator is for automatic size detection or not. If it is for automatic size detection, the process proceeds to step S903; otherwise, the process proceeds to step S906.

[0111] In step S903, four points (the four corners) of the scanned document are detected. The method for detecting these four points is the same as the method described in step S303 in Figure 8.

[0112] In step S904, the detected coordinates (X1,Y1) of the upper left corner are corrected to (0,0). Accordingly, the (X1,Y1) values ​​of the other three points are subtracted from their detected coordinates, and then the skew of the document is corrected.

[0113] Step S905 involves cutting out the white-bordered original document. The white-bordered original document is cut out using the method shown in Figure 15.

[0114] In Figure 15, step S1001 starts the process of cutting out the white-bordered original document.

[0115] In step S1002, the color components within the inner 2mm of the detected document size are acquired.

[0116] In step S1003, the luminance value C1 of the most abundant color among the acquired color components is compared with the luminance value C2 of white, which has been predetermined as a threshold.

[0117] In step S1004, the white threshold C is set to the value that is closer to white between the luminance value C1 of the most frequent color and the luminance value C2 of white.

[0118] In step S1005, if 95% or more of the color components obtained in step S1002 are above the white threshold C, the process proceeds to step S1006; otherwise, the process proceeds to step S1007.

[0119] In step S1006, the rectangle circumscribing the original document is calculated.

[0120] In step S1007, the inscribed rectangle of the original document is calculated. The method for calculating the inscribed rectangle is the same as the method shown in Figure 11.

[0121] This method allows for the creation of images with margins, such as a photograph showing a wide area of ​​clouds that are nearly white, rather than simply cropping the image using an inscribed rectangle. This improves the accuracy of the reproduction of the original photograph.

[0122] Alternatively, instead of steps S1003 to S1005, the luminance value C1 of the most frequent color may be compared with a predetermined white threshold C, and it may be determined whether the area above threshold C accounts for 95% or more of the total area.

[0123] In step S1008, the scanned image is cropped based on the calculated rectangle size.

[0124] Step S1009 completes the process of cutting out the white-bordered document.

[0125] Then, returning to the flow shown in Figure 14, in step S906, image processing is performed on the extracted image.

[0126] Step S907 ends the scan.

[0127] Next, we will explain how to perform in-segment cropping on documents where margins remain after in-segment cropping using four-point detection.

[0128] In particular, with photographic originals, the edges may not be straight lines, as shown in Figure 16 (hereinafter referred to as distorted photographic originals). When cutting out a distorted photographic original with an inscribed rectangle, the method for calculating the inscribed rectangle shown in Figure 11 may leave margins. For such originals, the shadow remaining at the edges of the scanned image is used to calculate the inscribed rectangle.

[0129] Figure 17 is a flowchart showing the process for calculating the inscribed rectangle of a distorted photographic original.

[0130] First, in step S1201, start scanning the document.

[0131] In step S1202, it is determined whether the image reading size setting set by the operator is for automatic size detection or not. If it is for automatic size detection, the process proceeds to step S1203; otherwise, the process proceeds to step S1206.

[0132] In step S1203, four points (the four corner points) of the scanned document are detected, similar to step S903 in Figure 14.

[0133] In step S1204, the detected upper-left corner coordinate (X1, Y1) is corrected to (0, 0). Accordingly, the other three points are corrected for skew by subtracting (X1, Y1) from their detected coordinates.

[0134] Step S1205 involves cutting out the distorted photographic original. The cutting process is performed using the method shown in Figure 18.

[0135] In Figure 18, step S1301 initiates the process of cutting out the distorted photographic original.

[0136] In step S1302, the surface image of the document to be scanned is acquired.

[0137] In step S1303, the shadow area remaining at the upper edge of the scanned surface image (the leading edge in the document's transport direction) is acquired.

[0138] In step S1304, the Y-coordinate of the lower edge of the acquired shadow area is set to Y1. Note that in the example shown in Figure 16, only the left and right edges are distorted, but the top and bottom of the document may also be distorted. In that case, multiple shadow areas may appear in the left and right directions, but the Y-coordinate of the lowest point among them is set to top end Let the Y coordinate be Y1.

[0139] In step S1305, the image of the back side of the document is obtained.

[0140] In step S1306, the shadow area remaining at the bottom edge (the rear end in the document transport direction) of the scanned backside image is acquired.

[0141] In step S1307, the Y coordinate of the point whose Y coordinate is located at the top of the acquired shadow region is lower end Let the Y coordinate be Y2.

[0142] In step S1308, the shadow areas remaining at the left and right edges of the read front and back images are obtained.

[0143] In step S1309, the X coordinate of the point located furthest to the right among the acquired leftmost shadow regions is Leftmost The X coordinate X1 is the X coordinate of the leftmost point in the shadow region at the right edge. right edge Let the x-coordinate be X2.

[0144] The principle for acquiring the shadow region in steps S1303, S1306, and S1308 described above is the same as the principle already explained using Figure 9.

[0145] In step S1310, a rectangle is cut out from the original document, with the four points (X1,Y1), (X1,Y2), (X2,Y2), and (X2,Y1) as its vertices.

[0146] Step S1311 completes the process of cutting out the distorted photographic original.

[0147] Returning to Figure 17, in step S1206, image processing is performed on the extracted image.

[0148] Step S1207 ends the scan.

[0149] As described above, according to the above embodiment, in an image reader with an automatic size detection function, when the transport medium (original document) is a photograph, the image is cropped using the inscribed rectangle of the scanned image and output, thereby preventing the white border from being printed and resulting in an unsightly image, even when performing borderless printing of photographs. Furthermore, for original documents other than photographs, the image is cropped using the circumscribed rectangle of the scanned image, thereby preventing the loss of information in the peripheral areas of the image.

[0150] It's possible that the original photograph is not rectangular, and that the edges of the photograph are not straight lines. Therefore, instead of calculating an inscribed rectangle and cropping the image, when photo mode is selected, you can ensure that all four sides are cropped by a specified size, so that the background margin is not included in the rectangular image.

[0151] (Second embodiment) The following describes a second embodiment of the present invention. This embodiment describes cases where necessary information is captured at the edge of a borderless photograph.

[0152] If important information is captured at the edge of a borderless photograph, such as the date of photography, cropping the image with a rectangle inscribed within the image will result in the loss of this important information. However, cropping the image with a rectangle circumscribed around it will crop out the outer margins of the photograph along with the image itself. Therefore, by cropping the image at the center of both the inscribed and circumscribed rectangles, it is possible to crop the image without capturing unnecessary outer margins and without losing any important information from the image.

[0153] Figure 19 is a flowchart showing the process of cropping an image at the center position of an inscribed rectangle and a circumscribed rectangle.

[0154] In step S1401, begin scanning the document.

[0155] In step S1402, it is determined whether the image reading size setting set by the operator is for automatic size detection or not. If it is for automatic size detection, the process proceeds to step S1403; otherwise, the process proceeds to step S1406.

[0156] In step S1403, four points (the four corners) of the scanned document are detected. The method for detecting these four points is the same as the method described in step S303 in Figure 8.

[0157] In step S1404, the detected upper-left corner coordinate (X1, Y1) is corrected to (0, 0). Accordingly, the other three points are corrected for skew by subtracting (X1, Y1) from their detected coordinates.

[0158] In step S1405, cropping is performed at the center position of the inscribed rectangle and the circumscribed rectangle. The process of cropping at the center position of the inscribed rectangle and the circumscribed rectangle will be explained with reference to Figure 20. Note that the process in Figure 20 may be started if it is determined that the original is a borderless photograph and the necessary information is captured at the edge of the borderless photograph. Alternatively, the process may be started when the operator instructs the borderless photograph mode (necessary information at the edge) or the control unit 80 may decide and start the process based on the data read from the image.

[0159] First, in step S1501, the calculation of the rectangle begins.

[0160] In step S1502, the lengths of the four sides of the rectangle of the original document are calculated from the coordinates of the four points corrected in step S1403 of Figure 19. At this time, the top side is calculated as the difference between the X coordinates of the upper left corner and the X coordinates of the upper right corner, and the length related to the Y component is not included. The length of the bottom side is calculated using the same method. The length of the left side is calculated from the difference between the Y coordinates of the upper left corner and the Y coordinates of the lower left corner, and the length of the right side is calculated using the same method.

[0161] In step S1503, the difference between the lengths of the top and bottom sides (=L1) and the difference between the lengths of the left and right sides (=L2), which were calculated in step S502, are calculated.

[0162] In step S1504, it is determined whether both the difference L1 and the difference L2 calculated in step S1503 are zero. If at least one of the differences L1 and L2 is not zero, the process proceeds to step S1505. If both the difference L1 and the difference L2 are zero, the process proceeds to step S1507.

[0163] In step S1505, the midpoint between the lengths of the top and bottom sides is set as the lengths of the top and bottom sides, and the process proceeds to step S1506. The midpoint between the lengths of the top and bottom sides is calculated by subtracting half of the difference L1 from the length of the longer side and adding half of the difference L1 to the length of the shorter side.

[0164] In step S1506, the midpoint between the lengths of the right and left sides is set as the lengths of the right and left sides, and the process proceeds to step S1507. The midpoint between the lengths of the right and left sides is calculated by subtracting half of the difference L2 from the length of the longer side and adding half of the difference L2 to the length of the shorter side.

[0165] In step S1507, the rectangle is calculated based on the side lengths set up to this point, and the calculation of the inscribed rectangle is completed.

[0166] Then, returning to the flow shown in Figure 19, in step S1406, image processing is performed on the extracted image.

[0167] Step S1407 ends the scan.

[0168] Alternatively, at step S1503, a screen like those shown in Figure 21(a) or Figure 21(b) may be displayed, allowing the user to input or select the cropping position. Or, a screen showing the image and cropping position may be displayed as shown in Figure 22, allowing the user to visually confirm the position and also allowing the user to change the cropping position.

[0169] In step S1505, half of the difference L1 is subtracted from the length of the longer side, and half of the difference L1 is added to the length of the shorter side. However, as shown in Figure 23, the difference (L3) between the coordinates of the upper left corner (X1, Y1) and the lower left corner (X3, Y3) may differ from the difference (L4) between the coordinates of the upper right corner (X2, Y2) and the lower right corner (X4, Y4). In that case, the difference L1 may be subtracted from the length of the longer side and added to the length of the shorter side based on the difference ratio (L3:L4). The same applies to step S1506.

[0170] The present invention is not limited to the embodiments described above, and various modifications are possible based on the spirit of the invention, and these modifications are not excluded from the scope of the invention. Furthermore, the various processes, configurations, and their contents described above are not limited to these, and may be composed of various configurations and contents depending on the application and purpose.

[0171] For example, in the above embodiment, for illustrative purposes, an image reading device A having all the necessary components was described as an example, but the invention is not limited to this. As stated above, the image processing unit 88, which is implemented by application software on a PC as an external device connected to the image reading device A, may perform the image processing such as the cropping operation described above. In that case, the present invention is realized by an image reading system including the image reading device A and the PC connected to it. [Explanation of Symbols]

[0172] A: Image reading device, S: Transport medium, 1: Mounting platform, 2: Discharge tray, 3,4: Drive unit, 5: Transmission unit, 11: Feed roller, 12: Separation roller, 21,31: Drive roller, 22,22: Driven roller, 40: Double feed detection sensor, 50,60: Medium detection sensor, 70: Image reading unit, 80: Control unit, 81: CPU, 82: Memory unit, 83: Operation unit, 84: Communication unit, 85a,85b: Interface unit, 86: Actuator, 87: Sensor, 88: Image processing unit, 90: Front panel, 93: Display panel, 94: Display unit, 95: Surface image processing unit

Claims

1. A reading method that reads the document as an image, A means for determining the type of the aforementioned document, A cutting means for cutting out a partial image from an image using one of several cutting methods for cutting out a document area as a partial image from an image read by the reading means, Equipped with, The discrimination means determines whether the type of the document is a photograph or not, and the cutting means is a means for changing the cutting method based on the discrimination result of the discrimination means. An image reading system characterized in that, when the type of document is determined to be a photograph by the determination means, the partial image cut out by the cutting means is a rectangle inscribed within the document area from the image read by the reading means.

2. Having a transport means for transporting the aforementioned manuscript, The image reading system according to claim 1, characterized in that the reading means reads the original document conveyed by the transport means.

3. The image reading system according to claim 1 or 2, characterized in that the cropping means crops the partial image based on the shadow of the original document.

4. The system includes a detection means for detecting the shadowed region of the original document from the aforementioned image, The image reading system according to claim 3, characterized in that the cutting means calculates the coordinates of the four corner points of a rectangle based on the coordinates of the shadow closest to the original document among the shadow regions detected by the detection means, and calculates the rectangle with the four corner points as vertices as a rectangular region inscribed in the original document.

5. The system includes a detection means for detecting points at the four corners of the original document based on the shadow region of the original document included in the image, The image reading system according to claim 3, characterized in that the cutting means calculates a rectangular area inscribed in the original document based on the coordinates of the four corner points of the original document detected by the detection means.

6. The image reading system according to claim 5, characterized in that the cutting means calculates the lengths of the four sides of the rectangle of the original document based on the coordinates of the four corner points of the original document detected by the detection means, sets the lengths of the top and bottom sides based on whether the difference between the lengths of the top and bottom sides is 2 mm or less, and sets the lengths of the right and left sides based on whether the difference between the lengths of the right and left sides is 2 mm or less, thereby calculating a rectangular area inscribed in the original document area.

7. The image reading system according to any one of claims 1 to 6, characterized in that, when the determination means determines that the type of document is other than a photograph, the cutting means cuts out a rectangular area circumscribing the document area as the partial image.

8. The image reading system according to claim 7, characterized in that the discrimination means determines the type of document based on the operator's instructions.

9. The image reading system according to claim 8, characterized in that the determination means determines the type of document based on a reading mode specified by the operator.

10. The image reading system according to claim 7, characterized in that the discrimination means determines the type of the original document based on the image read.

11. The image reading system according to any one of claims 1 to 3, characterized in that, if the determination means determines that the original document is a borderless photograph, and the necessary information is captured at the edge of the borderless photograph, the cropping means crops the partial image at the center position of the rectangle inscribed in the original document area and the rectangle circumscribed around it.

12. A reading method that reads the document as an image, A means for determining the type of the aforementioned document, A cropping means for cropping a partial image from an image, using one of a plurality of cropping methods for cropping a document area as a partial image from an image read by the reading means, Equipped with, The discrimination means determines whether the type of the document is a photograph or not, and the cutting means is a means for changing the cutting method based on the type of document determined by the discrimination means. An image reading device characterized in that, when the type of document is determined to be a photograph by the determination means, the partial image cut out by the cutting means is a rectangle inscribed within the document area from the image read by the reading means.

13. The scanning process involves reading the original document as an image, A discrimination step for determining the type of the aforementioned document, A cutting step in which a partial image is extracted from the image using one of several cutting methods for extracting the document area as a partial image from the image read in the reading step, Equipped with, The discrimination step determines whether the type of the document is a photograph or not, and the cutting step is a step of changing the cutting method based on the type of document determined by the discrimination step. The image reading method for a document reading system, characterized in that, when the type of document is determined to be a photograph by the determination step, the partial image cut out in the cutting step is a rectangle inscribed within the document area from the image read in the reading step.

14. A program for causing a computer to perform each step of the image reading method described in claim 13.

Images