JP7212505B2 - Image processing device, image processing method and program - Google Patents

Description

The technology disclosed herein relates to an image processing device, an image processing method, and a program.

Some documents to be read by the scanner device have "tabs". For example, a tab is attached as an index to a manuscript serving as a mark in a bundle of manuscripts bound and managed in a binder. When a tabbed document is read by a scanner device, the image read by the scanner device includes an image of the document (hereinafter sometimes referred to as (document image)) and an image of the tab (hereinafter referred to as " tab images”).

JP 2016-116129 A JP 2009-271644 A

When a tab image is attached to a document image, until now, in general, the operator has checked the tab image, and each time he has checked, the tab image has been left attached, or the tab image has been removed. The processing for the image was specified to the scanner device. In this way, it is troublesome for the operator to specify the processing for the tab image each time the tab image is checked.

The disclosed technique has been made in view of the above, and aims to reduce operator's labor.

According to an aspect of the disclosure, an image processing device includes a detection unit and an image processing unit. The detection section detects features of convex portions around the document image included in the read image read by the reading section. The image processing unit performs image processing corresponding to the detected feature on the read image.

According to the aspect of the disclosure, it is possible to reduce the labor of the operator.

FIG. 1 is a diagram illustrating a configuration example of a scanner device according to a first embodiment. FIG. 2 is a diagram for explaining an operation example of the image processing apparatus according to the first embodiment. FIG. 3 is a diagram for explaining an operation example of the image processing apparatus according to the first embodiment. FIG. 4 is a diagram for explaining an operation example of the image processing apparatus according to the first embodiment. FIG. 5 is a diagram for explaining an operation example of the image processing apparatus according to the first embodiment. FIG. 6 is a diagram for explaining an operation example of the image processing apparatus according to the first embodiment. FIG. 7 is a diagram for explaining an operation example of the image processing apparatus according to the first embodiment. FIG. 8 is a diagram for explaining an operation example of the image processing apparatus according to the first embodiment. FIG. 9 is a diagram illustrating an example of a processing flow of the image processing apparatus according to the first embodiment; 10 is a diagram illustrating an example of a processing flow of the image processing apparatus according to the first embodiment; FIG. 11 is a diagram illustrating an example of a processing flow of the image processing apparatus according to the first embodiment; FIG. FIG. 12 is a diagram for explaining an operation example of the image processing apparatus according to the first embodiment; FIG. 13 is a diagram for explaining an operation example of the image processing apparatus according to the second embodiment. FIG. 14 is a diagram for explaining an operation example of the image processing apparatus according to the second embodiment.

Embodiments of an image processing apparatus, an image processing method, and a program disclosed in the present application will be described below with reference to the drawings. Note that the image processing apparatus, image processing method, and program disclosed in the present application are not limited to these embodiments. Also, in the embodiments, the same symbols are attached to the configurations having the same functions and the steps performing the same processing.

[Example 1]
<Structure of scanner device>
FIG. 1 is a diagram illustrating a configuration example of a scanner device according to a first embodiment. In FIG. 1 , the scanner device 10 has an image processing device 20 , a reading section 12 , an operation section 16 and a display section 17 . The image processing device 20 has a control section 11 , a storage section 13 , a detection section 14 and an image processing section 15 .

The reading unit 12 is implemented as hardware by, for example, a CIS (Contact Image Sensor) type image sensor. The control unit 11, the detection unit 14, and the image processing unit 15 are implemented as hardware, for example, by a processor. Examples of processors include CPUs (Central Processing Units), DSPs (Digital Signal Processors), and FPGAs (Field Programmable Gate Arrays). Also, the control unit 11, the detection unit 14, and the image processing unit 15 may be implemented by an LSI (Large Scale Integrated circuit) including a processor and peripheral circuits. Furthermore, the control unit 11, the detection unit 14, and the image processing unit 15 may be implemented using a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), or the like. The storage unit 13 is realized by, for example, a memory as hardware. Examples of memory include RAM (Random Access Memory) such as SDRAM (Synchronous Dynamic Random Access Memory), ROM (Read Only Memory), and flash memory. The operation unit 16 is implemented as hardware by, for example, a touch sensor or mechanical input buttons. The display unit 17 is implemented as hardware by, for example, a liquid crystal display. The operation unit 16 and the display unit 17 may be implemented as hardware, for example, by a touch panel.

A case in which the image processing device 20 is installed in the scanner device 10 and used will be described below as an example, but the image processing device 20 may be installed in a computer device, an information processing terminal, or the like and used. .

<Processing/Operation of Image Processing Apparatus>
2 to 8 and 12 are diagrams for explaining an operation example of the image processing apparatus according to the first embodiment. 9 to 11 are diagrams showing an example of the processing flow of the image processing apparatus according to the first embodiment.

The storage unit 13 stores an operator setting table OST shown in FIG. The contents of each item in the operator setting table OST are registered by the operator using the operation unit 16 . The control unit 11 registers each content of the operator setting table OST stored in the storage unit 13 according to the operation of the operation unit 16 by the operator.

In the operator setting table OST, it is possible to set whether or not the detection unit 14 detects tab images for the item "Tab detection". "Valid" is set when the tab image is detected, and "Invalid" is set when the tab image is not detected. The default value is, for example, "Valid".

For the item “determination parameter: position”, the position of the tab image with respect to the document image (hereinafter referred to as “determination parameter”) is used as a parameter (hereinafter sometimes referred to as “determination parameter”) when the image processing unit 15 performs determination on the tab image. may be called "tab image position"). "Valid" is set when the tab image position is used as the determination parameter, and "Invalid" is set when the tab image position is not used as the determination parameter. The default value is, for example, "Valid".

For the item "determination parameter: width", it is possible to set whether or not to use the length of the side of the tab image that is in contact with the document image (hereinafter sometimes referred to as "tab image width") as a determination parameter. . "Valid" is set when the tab image width is used as the determination parameter, and "Invalid" is set when the tab image width is not used as the determination parameter. The default value is, for example, "Valid".

For the item "determination parameter: vertical width", the distance between the side of the tab image in contact with the document image and the opposite side of the side in contact with the document image (hereinafter sometimes referred to as "tab image vertical width") is used as a determination parameter. "Valid" is set when the tab image height is used as the determination parameter, and "Invalid" is set when the tab image height is not used as the determination parameter. The default value is, for example, "Valid".

For the item "determination parameter: color", it is possible to set whether or not to use the color of the tab image (hereinafter sometimes referred to as "tab image color") as the determination parameter. "Valid" is set when the tab image color is used as the determination parameter, and "Invalid" is set when the tab image color is not used as the determination parameter. The default value is, for example, "Valid".

For the item "tab feature automatic registration", when a predetermined condition is satisfied, tab features (hereinafter sometimes referred to as "tab features") are automatically stored in a tab feature table TFT, which will be described later. It is possible to set whether or not to register. "Valid" is set when the tab feature is to be automatically registered, and "Invalid" is set when the tab feature is not to be automatically registered. The default value is, for example, "Valid".

For the item "dissimilar tab processing", it is possible to set the processing to be performed when a "dissimilar tab" described later is detected. , “continue reading (leave tab)”, “continue reading (remove tab)”, “continue reading (separate tab)”, or “continue reading (discard image)”. The default value is, for example, "operator notification".

For the item "judgment level", the level for judging the tab image can be set, and either "normal" or "strict" is set. A default value is, for example, "Normal".

The storage unit 13 also stores a tab feature table TFT shown in FIG. In the tab feature table TFT, a tab ID (identification) unique to each tab feature, a correspondence between each tab feature and a process for each tab feature is set as tab data. Tab features are defined, for example, by side (p), horizontal position (X), vertical position (Y), width (w), height (l), and color (h). The contents of each item in the tab feature table TFT are registered by the operator using the operation section 16 or automatically registered by the image processing section 15 . The control unit 11 registers each content of the tab feature table TFT stored in the storage unit 13 according to the operation of the operation unit 16 by the operator.

As shown in FIG. 4, the side (p) indicates the side on which the tab image exists among the four sides of the rectangular document image, and is "upper side", "lower side", "left side", "right side" or "not specified". set to any of the The detection unit 14 refers to the tab feature table TFT, and when the "upper side" is set for the side (p), the upper side of the document image is targeted, and when the "lower side" is set, Targets the bottom edge of the document image. If "Left Edge" is set, the left edge of the document image is targeted, and if "Right Edge" is specified, the right edge of the document image is targeted, and the tab image Attempt detection. Further, when "not specified" is set for the side (p), the detection unit 14 attempts to detect a tab image on all four sides of the document image.

The horizontal position (X) indicates the distance [mm] from the left side of the document image to the left side of the tab image, and is set to a real number of 0 or more, -1 or -2. If the horizontal position (X) is set to -1, it indicates that the tab image is attached to either the left or right edge of the document image and the tab feature does not have a horizontal position (X). If the horizontal position (X) is set to -2, it indicates that the tab image can be attached to any of the four sides of the document image.

The vertical position (Y) indicates the distance [mm] from the upper side of the document image to the upper side of the tab image, and is set to a real number of 0 or more, -1 or -2. If the vertical position (Y) is set to -1, it indicates that the tab image is attached to either the top or bottom edge of the document image and the tab feature does not have a vertical position (Y). If the vertical position (Y) is set to -2, it indicates that the tab image can be attached to any of the four sides of the document image.

Width (w) indicates the tab image width [mm] and is set to 0 or a real number greater than 0. If the width (w) is set to 0, it indicates that there is no limitation on the width of the tab image.

Vertical width (l) indicates the tab image vertical width [mm], and is set to 0 or a real number greater than 0. If the vertical width (l) is set to 0, it indicates that there is no limitation on the vertical width of the tab image.

Color (h) indicates the tab image color, and is set to a real number of 0 or more and less than 360, or -1. The tab image color is specified by the hue of the HSV model with red=0, blue=240, and green=120. If color (h) is set to -1, it indicates that there is no restriction on the tab image color.

Further, in the tab feature table TFT, for the item "processing", processing to be performed when the image processing unit 15 detects a "similar tab" to be described later can be set. Job Separation)", "Continue Reading (Tab Left)", "Continue Reading (Remove Tab)", "Continue Reading (Separate Tab)", or "Continue Reading (Discard Image)" is set. . Among the processes in FIGS. 2 and 4, “reading end” indicates that the reading of the document by the reading unit 12 is finished. "Continue reading (separate jobs)" continues reading of the document by the reading unit 12, and separates the document image around which the tab image exists and the document image around which the tab image does not exist as different files from each other. 13 indicates to save. “Continue reading (leave tab)” indicates that reading of the document by the reading unit 12 is continued and the document image is stored in the storage unit 13 with the tab image left. “Continue reading (remove tab)” indicates that reading of the document by reading unit 12 is continued, the tab image is removed from the document image, and the document image is stored in storage unit 13 . "Continue reading (separate tab)" separates the tab image from the document image while continuing the reading of the document by the reading unit 12, and separates the separated tab image from the document image after the separation of the tab image. It indicates that the file is saved in the storage unit 13 as a different file. “Continue reading (discard image)” indicates that reading of the document by the reading unit 12 is continued and the document image surrounding the tab image is discarded.

Returning to FIG. 3, for example, in the tab data TD1, for tab ID=01, the tab features of the tab with ID=01 are side (p)=not specified, horizontal position (X)=-2, vertical position ( Y) = -2, width (w) = 0, height (l) = 0, color (h) = -1 are set in association, and this is performed when a similar tab having this tab feature is detected. As the process, "continue reading (separate tab)" is associated and set. For example, in the tab data TD2, for tab ID=02, the tab characteristics of the tab with ID=02 are side (p)=upper side, horizontal position (X)=130, vertical position (Y)=-1, Width (w) = 0, height (l) = 8, and color (h) = 240 are set in association with each other, and processing to be performed when a similar tab having this tab feature is detected is "continue reading ( Job Separation)” is associated and set. For tab ID=03, 04, and 05 in tab data TD3, TD4, and TD5, similar tabs having tab characteristics and set tab characteristics are similar to tab ID=01 and 02 in tab data TD1 and TD2. is set in association with the processing to be performed when is detected.

A plurality of documents placed on a shooter (not shown) of the scanner device 10 are fed into the scanner device 10 one by one by an ADF (Auto Document Feeder) (not shown) of the scanner device 10, and read by a reading unit. A document 12 reads a document loaded into the scanner device 10 and stores a read image (hereinafter sometimes referred to as a “read image”) RI in a storage unit 13 . When the document is tabbed, the read image RI is formed from the document image DI and the tab image TI, as shown in FIGS. For example, when a document with a rectangular tab on the right side is read by the reading unit 12, a read image RI as shown in FIG. 5 is obtained. Further, for example, when a document with a rectangular tab attached to the left side is read by the reading unit 12, a read image RI as shown in FIG. 6 is obtained. Further, for example, when a document having a rectangular tab attached to the upper side thereof is read by the reading section 12, a read image RI as shown in FIG. 7 is obtained. Further, for example, when a document with a rectangular tab attached to the lower side is read by the reading unit 12, a read image RI as shown in FIG. 8 is obtained.

In FIG. 9, in step S101, the control unit 11 acquires the read image RI from the storage unit 13. FIG.

Next, in step S103, the control unit 11 sets the first flag FLG to 0. A first flag FLG is stored in the storage unit 13 .

Next, in step S105, the control unit 11 refers to the operator setting table OST to determine whether or not the item "Tab detection" in the operator setting table OST is enabled, that is, whether or not to detect tab images. judge.

When the item “tab detection” is disabled in the operator setting table OST (step S105: No), the control unit 11 causes the reading unit 12 to continue reading the document in step S109.

On the other hand, if the item "tab detection" is enabled in the operator setting table OST (step S105: Yes), the control unit 11 outputs the acquired read image RI to the detection unit 14 in step S107. Then, the detection unit 14 attempts to detect the tab image TI in the read image RI. The detection unit 14 determines whether or not a convex portion exists around the document image DI, and if a convex portion exists, the convex portion is detected as the tab image TI. For example, if there is a convex portion having a height equal to or greater than a predetermined threshold value (for example, 3 [mm]) from any of the four sides of the rectangular document image DI, the detection unit 14 detects the convex portion. part is detected as a tab image TI. When the detection unit 14 determines that there is no protrusion around the document image DI, that is, when the tab image TI is not detected (step S107: No), in step S109, the detection unit 14 detects the tab image. The control unit 11 is notified that the TI is not detected, and in response to the notification, the control unit 11 continues the document reading by the reading unit 12 .

On the other hand, when the detection unit 14 determines that there is a convex portion around the document image DI, that is, when the tab image TI is detected (step S107: Yes), similarity determination is performed in step S111. . The details of similarity determination will be described later.

After the similarity determination, the image processing unit 15 determines whether or not the second flag ST is set to 1 in step S113. A second flag ST is stored in the storage unit 13 . When the second flag ST is set to 1 (step S113: Yes), the process proceeds to step S115, while when the second flag ST is set to 0 (step S113: No). , the process proceeds to step S121.

In step S115, a process to be executed by the image processing unit 15 on the read image RI (hereinafter sometimes referred to as "execution process") is determined. The details of determining the execution process will be described later.

After determining the execution process, in step S117, the image processing unit 15 determines that the execution process determined in step S115 (hereinafter sometimes referred to as "determination process") is the process selected by the operator (hereinafter, "operator (sometimes referred to as "processing"). If the determination process is the operator selection process (step S117: Yes), the process proceeds to step S131.

On the other hand, if the determination process is not the operator selection process (step S117: No), the image processing unit 15 executes the determination process in step S119.

Also, in step S121, the image processing unit 15 issues a warning. For example, the image processing unit 15 outputs a message indicating that there is no tab feature similar to the detected tab feature in the tab feature table TFT (that is, the tab image TI detected in step S107 is a dissimilar tab). A warning is given to the operator by displaying it on the display unit 17 .

Next, in step S123, the image processing unit 15 refers to the operator setting table OST, and determines whether or not the item "automatic tab feature registration" in the operator setting table OST is set to valid. When the item "automatic registration of tab characteristics" is set to valid in the operator setting table OST (step S123: Yes), the image processing unit 15 sets the first flag FLG to 1 in step S129.

On the other hand, if the item "automatic tab feature registration" is disabled in the operator setting table OST (step S123: No), in step S125, the image processing unit 15 registers the tab image detected in step S107. The operator is queried as to whether or not the tab feature of TI (hereinafter sometimes referred to as "detection tab feature") is to be registered in the tab feature table TFT. For example, the image processing unit 15 makes an inquiry to the operator by causing the display unit 17 to display a message inquiring whether or not to register the tab feature in the tab feature table TFT.

Next, in step S127, the image processing unit 15 determines the operator's answer to the inquiry in step S125. The operator's answer to the inquiry in step S 125 is input to the control section 11 by the operator's operation on the operation section 16 and output from the control section 11 to the image processing section 15 . If the answer to the inquiry in step S125 is Yes, that is, if the tab feature is to be registered in the tab feature table TFT (step S127: Yes), in step S129 the image processing unit 15 sets the first flag FLG to Set to 1. On the other hand, if the answer to the inquiry in step S125 is No, that is, if the tab feature is not registered in the tab feature table TFT (step S127: No), the process proceeds without performing step S129. The process proceeds to step S131.

In step S131, the image processing unit 15 executes processing M1. The image processing unit 15 executes the following process as the process M1. That is, the image processing unit 15 executes the operator selection process when the determination process is the operator selection process. On the other hand, if the determination process is not the operator selection process, the image processing unit 15 refers to the operator setting table OST to determine whether the content of the item "unsimilar tab processing" in the operator setting table OST is "operator notification". determine whether or not Then, when the content of the item "non-similar tab processing" in the operator setting table OST is "operator notification", the image processing unit 15 inquires of the operator about execution processing. For example, the image processing unit 15 selects “end of reading”, “continue reading (separate job)”, “continue reading (leave tab)”, “continue reading (remove tab)”, “continue reading (separate tab)”, ” and “continue reading (discard image)” are displayed on the display unit 17 as process candidates to inquire of the operator about the processing to be executed. The operator selects desired processing from the menu list by operating the operation unit 16 . The operator's selection result is input from the operation unit 16 to the control unit 11 and output from the control unit 11 to the image processing unit 15 . The image processing unit 15 selects "finish reading", "continue reading (separate job)", "continue reading (leave tab)", "continue reading (remove tab)", "continue reading (remove tab)", and "continue reading ( tab)” and “Continue reading (discard image)” selected by the operator. On the other hand, if the content of the item "dissimilar tab processing" in the operator setting table OST is not "operator notification", the image processing unit 15 performs the processing set in the item "dissimilar tab processing" in the operator setting table OST. That is, any process other than "notify operator" is executed. After executing the process M1 in step S131, the process proceeds to step S133.

In step S133, the image processing unit 15 determines whether or not the first flag FLG is set to one. If the first flag FLG is set to 1 (step S133: Yes), the process proceeds to step S135. On the other hand, if the first flag FLG is set to 0 (step S133: No), the process ends without performing the process of step S135.

At step S135, the image processing unit 15 executes the process M2. The image processing unit 15 executes the following process as the process M2. In other words, the image processing unit 15 performs the detection tab feature, as well as "end reading", "continue reading (job separation)", "continue reading (leave tab)", "continue reading (remove tab)", and "continue reading (remove tab)" in FIG. A menu list of each process of "Continue reading (separate tab)" and "Continue reading (discard image)" is displayed on the display unit 17 as process candidates to inquire of the operator about the process associated with the detected tab feature. The operator selects desired processing from the menu list by operating the operation unit 16 . The operator's selection result is input from the operation unit 16 to the control unit 11 and output from the control unit 11 to the image processing unit 15 . The image processing unit 15 selects "finish reading", "continue reading (separate job)", "continue reading (leave tab)", "continue reading (remove tab)", "continue reading (remove tab)", and "continue reading ( Separating tab)” and “Continue reading (discard image)” are associated with any processing selected by the operator and a new tab ID, and then a new tab ID is assigned. The detected tab feature is added and registered in the tab feature table TFT.

Here, when the image processing unit 15 executes "reading end", the image processing unit 15 notifies the control unit 11 that the process to be executed is "reading end". The operations of the ADF and reading unit 12 are stopped. When the image processing unit 15 executes “continue reading (job separation)”, the image processing unit 15 saves the document image without tab images around it while the operations of the ADF and the reading unit 12 continue. The read image RI is stored in a file different from the file in which the read image RI is stored in the storage unit 13 . Further, when the image processing unit 15 executes “continue reading (leave tab)”, while the operations of the ADF and reading unit 12 continue, the image processing unit 15 reads the original document image DI with the tab image TI remaining. (that is, the read image RI as it is) is stored in the storage unit 13 . Further, when the image processing unit 15 executes “continue reading (remove tab)”, the image processing unit 15 removes the tab image TI from the document image DI while the operations of the ADF and reading unit 12 continue. The document image DI after removing the tab image TI is stored in the storage unit 13 . Further, when the image processing unit 15 executes “continue reading (separate tab)”, the image processing unit 15 separates the tab image TI from the document image DI while the operations of the ADF and the reading unit 12 continue. The separated tab image TI and the document image DI after separation of the tab image TI are saved in different files and stored in the storage unit 13 . Further, when the image processing unit 15 executes “continue reading (discard image)”, the image processing unit 15 continues the operations of the ADF and the reading unit 12 and prints the document image DI ( That is, the read image RI) is discarded.

Next, similarity determination in step S111 in FIG. 9 will be described with reference to FIG.

In FIG. 10, in step S201, the detection unit 14 detects the features of convex portions present around the document image DI, that is, the tab features of the tab image TI detected in step S107, and detects the detected tab features in the read image RI. and output to the image processing unit 15 . A detection tab feature is defined by side (p), horizontal position (X), vertical position (Y), horizontal width (w), vertical width (l) and color (h), as in FIG.

Next, in step S203, the image processing unit 15 selects tab data (hereinafter referred to as " It is determined whether or not there is a "same side tab data"). For example, the image processing unit 15 determines whether or not the same side tab data exists in all the tab data including the tab data TD1 to TD5 in the tab feature table TFT (FIG. 3). If there is no same side tab data (step S203: No), the process proceeds to step S255.

On the other hand, if there is the same side tab data (step S203: Yes), in step S205, the image processing unit 15 acquires the same side tab data from among the tab data registered in the tab feature table TFT. In S207, the number of acquired identical side tab data is set to the number N of acquisitions.

Next, in step S209, the image processing unit 15 sets the first counter n to 1 and sets the second counter r to 0.

Next, in step S211, the image processing unit 15 acquires the n-th tab data among the N same side tab data acquired in step S205.

Next, in step S213, the image processing unit 15 determines whether the side (p) in the n-th tab data acquired in step S211 (hereinafter sometimes referred to as "acquired tab data") is the "upper side" or the "lower side". Determine whether or not there is

If the side (p) in the acquired tab data is the "upper side" or the "lower side" (step S213: Yes), in step S215, the image processing unit 15 sets the horizontal position (X) in the detected tab feature to the first position. While setting the distance z1, the lateral position (X) in the acquired tab data is set to the second distance z0.

On the other hand, if the side (p) in the acquired tab data is other than "upper side" and "lower side" (that is, if it is "left side", "right side" or "not specified") (step S213: No), In step S217, the image processing unit 15 sets the vertical position (Y) in the detected tab feature to the first distance z1, and sets the vertical position (Y) in the acquired tab data to the second distance z0.

Next, in step S219, the image processing unit 15 determines whether or not the second distance z0 is -2. If the second distance z0 is not -2 (step S219: No), the process proceeds to step S221. On the other hand, if the second distance z0 is -2 (step S219: Yes), the process proceeds to step S223 without performing the process of step S221.

In step S221, the image processing unit 15 determines whether or not the absolute value of the difference between the second distance z0 and the first distance z1 is less than the threshold Γz. For example, the image processing unit 15 uses 14 [mm] as the threshold value Γz when the item “determination level” in the operator setting table OST is set to “normal”, and , 7 [mm] is used as the threshold Γz. Both thresholds Γz of 14 [mm] and 7 [mm] are stored in the storage unit 13 . If the absolute value of the difference between the second distance z0 and the first distance z1 is less than the threshold Γz (step S221: Yes), the process proceeds to step S223.

On the other hand, if the absolute value of the difference between the second distance z0 and the first distance z1 is equal to or greater than the threshold Γz (step S221: No), the image processing unit 15 determines that the tab feature in the acquired tab data is the detected tab feature. (that is, it is determined that the tab image TI detected in step S107 is a dissimilar tab), and the process proceeds to step S247.

In step S223, the image processing unit 15 sets the vertical width (l) in the detected tab feature to the first vertical width l1, and sets the vertical width (l) in the acquired tab data to the second vertical width l0.

Next, in step S225, the image processing unit 15 determines whether or not the second vertical width l0 is zero. If the second vertical width l0 is not 0 (step S225: No), the process proceeds to step S227. On the other hand, when the second vertical width l0 is 0 (step S225: Yes), the process proceeds to step S229 without performing the process of step S227.

In step S229, the image processing unit 15 determines whether the absolute value of the difference between the second vertical width l0 and the first vertical width l1 is less than the product of the first vertical width l1 and the coefficient αl. . For example, the image processing unit 15 uses 10% as the coefficient αl when the item “determination level” in the operator setting table OST is set to “normal”, and uses 10% when it is set to “strict”. , 5% is used as the coefficient αl. Both coefficients αl of 10% and 5% are stored in the storage unit 13 . If the absolute value of the difference between the second vertical width l0 and the first vertical width l1 is less than the product of the first vertical width l1 and the coefficient αl (step S227: Yes), the process proceeds to step S229. .

On the other hand, if the absolute value of the difference between the second vertical width l0 and the first vertical width l1 is greater than or equal to the product of the first vertical width l1 and the coefficient αl (step S227: No), the image processing unit 15 determines that the tab feature in the acquired tab data is not similar to the detected tab feature (that is, determines that the tab image TI detected in step S107 is a dissimilar tab), and the process proceeds to step S247.

In step S229, the image processing unit 15 sets the width (w) of the detected tab feature to the first width w1, and sets the width (w) of the acquired tab data to the second width w0.

Next, in step S231, the image processing section 15 determines whether or not the second width w0 is zero. If the second width w0 is not 0 (step S231: No), the process proceeds to step S233. On the other hand, when the second width w0 is 0 (step S231: Yes), the process proceeds to step S235 without performing the process of step S233.

In step S233, the image processing unit 15 determines whether the absolute value of the difference between the second width w0 and the first width w1 is less than the product of the first width w1 and the coefficient αw. For example, the image processing unit 15 uses 10% as the coefficient αw when the item “determination level” in the operator setting table OST is set to “normal”, and uses 10% when it is set to “strict”. , 5% is used as the coefficient αw. Both coefficients αw of 10% and 5% are stored in the storage unit 13 . If the absolute value of the difference between the second width w0 and the first width w1 is less than the product of the first width w1 and the coefficient αw (step S233: Yes), the process proceeds to step S235.

On the other hand, if the absolute value of the difference between the second width w0 and the first width w1 is equal to or greater than the product of the first width w1 and the coefficient αw (step S233: No), the image processing unit 15 It is determined that the tab feature in the acquired tab data is not similar to the detected tab feature (that is, it is determined that the tab image TI detected in step S107 is a dissimilar tab), and the process proceeds to step S247.

In step S235, the image processing unit 15 sets the color (h) in the detected tab feature to the first color h1 and sets the color (h) in the acquired tab data to the second color h0.

Next, in step S237, the image processing unit 15 determines whether or not the second color h0 is 1. If the second color h0 is not 1 (step S237: No), the process proceeds to step S239. On the other hand, if the second color h0 is 1 (step S237: Yes), the process proceeds to step S241 without performing the process of step S239.

In step S239, the image processing unit 15 determines whether or not Δh represented by Equation (1) below is less than the threshold Γh. For example, the image processing unit 15 uses 30 as the threshold value Γh when the item “determination level” in the operator setting table OST is set to “normal”, and when it is set to “strict”, 15 is used as the threshold Γh. Both thresholds .GAMMA.h of 30 and 15 are stored in the storage unit 13. FIG. If Δh is less than the threshold Γh (step S239: Yes), the process proceeds to step S241.

On the other hand, when Δh is equal to or greater than the threshold Γh (step S239: No), the image processing unit 15 determines that the tab feature in the acquired tab data is not similar to the detected tab feature (that is, the tab feature detected in step S107). tab image TI is determined to be a dissimilar tab), and the process proceeds to step S247.

In step S241, the image processing unit 15 determines that the tab image TI detected in step S107 is a similar tab, and determines the difference between the detected tab feature and the tab feature in the acquired tab data for the acquired tab data. A similarity S is calculated according to the following equation (2).

Next, in step S243, the image processing unit 15 associates the "tab ID" and "process" in the acquired tab data with the similarity S calculated in step S241 and registers them in the similar tab list STL. The similar tab list STL is stored in the storage unit 13. FIG.

Next, in step S245, the image processing section 15 increments the second counter r.

Next, in step S247, the image processing unit 15 determines whether or not the first counter n has reached the number N of acquisitions. If the first counter n has not reached the acquisition number N (step S247: No), the image processing unit 15 increments the first counter n in step S249. After the process of step S249, the process returns to step S211.

On the other hand, when the first counter n has reached the acquisition number N (step S247: Yes), in step S251, the image processing unit 15 determines whether or not the second counter r is 1 or more. .

If the second counter r is equal to or greater than 1 (step S251: Yes), in step S253, the image processing unit 15 selects an acquired tab whose tab feature is similar to the detected tab feature among the N pieces of acquired tab data. It determines that there is data (hereinafter sometimes referred to as "similar tab data"), and sets the second flag ST to "1".

On the other hand, if there is no same side tab data (step S203: No), or if the second counter r is 0 (step S251: No), in step S255, the image processing unit 15 acquires N pieces of data. It determines that there is no similar tab data in the tab data, and sets the second flag ST to 0.

10, the image processing unit 15, for example, selects tab data TD2, TD4, and TD5 among all tab data including tab data TD1 to TD5 (FIG. 3) in the tab feature table TFT. If it is determined that the tab data are similar, and similarity degrees Sa, Sb, and Sc are calculated for each of the tab data TD2, TD4, and TD5 in step S241, then in step S243, as shown in FIG. The "tab ID" and "process" in TD2, TD4, and TD5 are associated with the degrees of similarity Sa, Sb, and Sc and registered in the similar tab list STL.

Next, determination of execution processing in step S115 in FIG. 9 will be described with reference to FIG.

In FIG. 11, the image processing unit 15 acquires the similar tab list STL from the storage unit 13 in step S301.

Next, in step S303, the image processing unit 15 calculates the sum of similarities registered in the similarity tab list STL (hereinafter sometimes referred to as "total similarity") SS. For example, as shown in FIG. 12, in the similar tab list STL, when similarities Sa, Sb, and Sc are associated with tab IDs=02, 04, and 05 respectively, the total similarity SS is , the sum of similarities Sa, Sb, and Sc (that is, SS=Sa+Sb+Sc).

Next, in step S305, the image processing unit 15 calculates a sum S1 of similarities associated with the process "reading end" in the similarity tab list STL.

Next, in step S307, the image processing unit 15 determines whether the sum S1 is equal to the total similarity SS. When the sum S1 is equal to the total similarity SS (step S307: Yes), in step S309, the image processing unit 15 determines "reading end" as the execution process.

On the other hand, if the sum S1 is not equal to the total similarity SS (step S307: No), in step S311, the image processing unit 15 corresponds to the process "continue reading (job separation)" in the similarity tab list STL. A sum S2 of the attached similarities is calculated.

Next, in step S313, the image processing unit 15 determines whether the sum S2 is equal to the total similarity SS. If the sum S2 is equal to the total similarity SS (step S313: Yes), in step S315, the image processing unit 15 determines "continue reading (job separation)" as the execution process.

On the other hand, if the total S2 is not equal to the total similarity SS (step S313: No), in step S317, the image processing unit 15 selects the process "continue reading (leave tab)" in the similar tab list STL. A total S3 of the associated similarities is calculated.

Next, in step S319, the image processing unit 15 determines whether the sum S3 is equal to the total similarity SS. When the sum S3 is equal to the total similarity SS (step S319: Yes), in step S321, the image processing unit 15 determines "continue reading (leave tab)" as the execution process.

On the other hand, if the total S3 is not equal to the total similarity SS (step S319: No), in step S323, the image processing unit 15 changes the similar tab list STL to the process "continue reading (remove tab)". A total S4 of the associated similarities is calculated.

Next, in step S325, the image processing unit 15 determines whether the sum S4 is equal to the total similarity SS. When the sum S4 is equal to the total similarity SS (step S325: Yes), in step S327, the image processing unit 15 determines "continue reading (remove tab)" as the execution process.

On the other hand, if the sum S4 is not equal to the total similarity SS (step S325: No), in step S329, the image processing unit 15 selects the process "continue reading (separate tab)" in the similar tab list STL. A total S5 of the associated similarities is calculated.

Next, in step S331, the image processing unit 15 determines whether the sum S5 is equal to the total similarity SS. When the sum S5 is equal to the total similarity SS (step S331: Yes), in step S333, the image processing unit 15 determines "continue reading (separate tab)" as the execution process.

On the other hand, if the sum S5 is not equal to the total similarity SS (step S331: No), in step S335, the image processing unit 15 corresponds to the process "continue reading (discard image)" in the similarity tab list STL. A sum S6 of the attached similarities is calculated.

Next, in step S337, the image processing unit 15 determines whether the sum S6 is equal to the total similarity SS. When the sum S6 is equal to the total similarity SS (step S337: Yes), in step S339, the image processing unit 15 determines "continue reading (discard image)" as the execution process.

On the other hand, if the total S6 is not equal to the total similarity SS (step S337: No), in step S341, the image processing unit 15 calculates the maximum value ( hereinafter sometimes referred to as "maximum similarity"), and whether the number of tab IDs associated with the maximum similarity (hereinafter sometimes referred to as "maximum similarity number") is 1 determine whether For example, in the similarity tab list STL shown in FIG. 12, if the similarity Sa is greater than the similarities Sb and Sc, the maximum number of similarities is determined to be 1, and the similarities Sa and Sb are greater than the similarities Sc. Moreover, when the similarities Sa and Sb are of the same magnitude, the maximum number of similarities is determined to be two.

When the maximum similarity number is 1 (step S341: Yes), in step S343, the image processing unit 15 determines the "process" associated with the maximum similarity in the similarity tab list STL as the execution process. do.

On the other hand, if the maximum number of similarities is 2 or more (step S341: No), in step S345, the image processing unit 15 inquires of the operator about execution processing. For example, the image processing unit 15 selects “end of reading”, “continue reading (separate job)”, “continue reading (leave tab)”, “continue reading (remove tab)”, “continue reading (separate tab)”, ” and “continue reading (discard image)” are displayed on the display unit 17 as process candidates to inquire of the operator about the processing to be executed. The operator selects desired processing from the menu list by operating the operation unit 16 . The operator's selection result is input from the operation unit 16 to the control unit 11 and output from the control unit 11 to the image processing unit 15 .

Next, in step S347, the image processing unit 15 selects "finish reading", "continue reading (separate job)", "continue reading (leave tab)", "read Any one of the operator-selected processing out of “Continue (remove tab)”, “Continue reading (separate tab)”, and “Continue reading (discard image)” is determined to be the execution processing.

Next, in step S349, the image processing unit 15 identifies the tab ID associated with the maximum similarity in the similar tab list STL (hereinafter sometimes referred to as "maximum similarity tab ID"). Then, the image processing unit 15 updates the "processing" associated with the maximum similarity tab ID in the tab feature table TFT by operator selection processing.

In the above description, the tab feature is defined by side (p), horizontal position (X), vertical position (Y), horizontal width (w), vertical width (l), and color (h). explained. However, tab features are defined by any one or more of side (p), horizontal position (X), vertical position (Y), width (w), height (l) and color (h). can be

As described above, in the first embodiment, the image processing device 20 has the detection unit 14 and the image processing unit 15 . The detection unit 14 detects the feature (ie, tab feature) of the convex portion (ie, tab image TI) around the document image DI included in the read image RI. The image processing unit 15 performs image processing corresponding to the detected tab feature on the read image RI. The image processing unit 15 executes, for example, processing related to reading of a document as image processing. In addition, the image processing unit 15 performs, for example, “end reading”, “continue reading (separate job)”, “continue reading (leave tab)”, “continue reading (remove tab)”, as processing related to document reading. ”, “Continue reading (separate tab)”, or “Continue reading (discard image)”.

By doing so, the image processing corresponding to the tab feature is automatically executed, so that the operator's labor can be reduced.

In the first embodiment, the detection unit 14 detects the side (p), tab image position (horizontal position (X) and vertical position (Y)), tab image width (w), tab image height (l) and tab At least one of the image colors (h) is detected as a tab feature.

By doing this, the appropriate tab feature can be detected.

Further, in the first embodiment, the image processing device 20 has the storage unit 13 . The storage unit 13 stores a tab feature table TFT in which "tab features" and "processing" are associated with each other. The image processing unit 15 determines execution processing according to the correspondence in the tab feature table TFT.

By doing so, it is possible to easily determine the processing to be executed.

In addition, in the first embodiment, the image processing apparatus 20 calculates the similarity S between the detected tab feature and the tab feature in the acquired tab data, and determines the execution process based on the calculated similarity S.

By doing so, an appropriate execution process can be determined.

Further, in the first embodiment, the image processing unit 15 executes the image processing selected in the processing candidate menu list when the maximum number of similarities is two or more.

By doing so, when there are a plurality of image processes suitable for execution, it is possible to execute image processing reflecting the operator's intention.

In the first embodiment, the image processing unit 15 uses the horizontal position (X), vertical position (Y), horizontal width (w), vertical width (l), or color (h) in the tab feature table TFT as the detection tab feature. If not similar (step S221: No, step S227: No, step S233: No, or step S239: No), the image processing selected in the processing candidate menu list and the detection tab feature are associated with each other and tabbed. Add to the feature table TFT (step S135).

By doing so, dissimilar tab features can be automatically registered in the tab feature table TFT in association with image processing.

In the first embodiment, the image processing unit 15 uses the horizontal position (X), vertical position (Y), horizontal width (w), vertical width (l), or color (h) in the tab feature table TFT as the detection tab feature. If not similar (step S221: No, step S227: No, step S233: No, or step S239: No), a warning is issued (step S121).

In this way, the operator can be notified that dissimilar tab features have been detected.

The first embodiment has been described above.

[Example 2]
In the first embodiment, the case where one tab feature table TFT is stored in the storage unit 13 has been described. On the other hand, in the second embodiment, the storage unit 13 stores a plurality of tab feature tables.

<Processing/Operation of Image Processing Apparatus>
13 and 14 are diagrams for explaining an operation example of the image processing apparatus according to the second embodiment.

For example, the storage unit 13 stores three tab feature tables TFT01, TFT02, and TFT03 respectively corresponding to three operators. In the tab feature table TFT01, the tab feature table TFT02, and the tab feature table TFT03, the same tab ID (that is, the same tab feature) is associated with different processes.

For example, in the tab feature table TFT01, for tab ID=01, the tab features of the tab with ID=01 are side (p)=not specified, horizontal position (X)=-2, and vertical position (Y)=-. 2, width (w) = 0, height (l) = 0, and color (h) = -1 are set in association with each other, and processing to be performed when a similar tab having this tab feature is detected is as follows: "Continue reading (separate tab)" is associated and set. On the other hand, in the tab feature table TFT02, for tab ID=01, the tab features of the tab with ID=01 are side (p)=not specified, horizontal position (X)=-2, and vertical position (Y). =-2, width (w) = 0, height (l) = 0, and color (h) = -1 are set in association with each other, and processing to be performed when a similar tab having this tab feature is detected. , and “reading continuation (job separation)” are set in association with each other. Further, in the tab feature table TFT03, for tab ID=01, the tab features of the tab with ID=01 are side (p)=not specified, horizontal position (X)=-2, and vertical position (Y)=-. 2, width (w) = 0, height (l) = 0, and color (h) = -1 are set in association with each other, and processing to be performed when a similar tab having this tab feature is detected is as follows: Continue reading (remove tab)” is associated and set.

When the tab feature tables TFT01, TFT02 and TFT03 are stored in the storage unit 13, the storage unit 13 further stores an operator ID table OIT shown in FIG. In the operator ID table OIT, correspondence between an operator ID unique to each operator and a table name of the tab feature table is set. The operator ID is input to the control unit 11 by the operator's operation on the operation unit 16 and output from the control unit 11 to the image processing unit 15 . The image processing unit 15 acquires the table name corresponding to the input operator ID from the operator ID table OIT, and selects the tab feature table having the acquired table name among the plurality of tab feature tables stored in the storage unit 13. is used to perform the same processing as in Example 1. For example, the image processing unit 15 uses the tab feature table TFT01 associated with AAA when the input operator ID is AAA, and uses BBB when the input operator ID is BBB. If the input operator ID is CCC, the tab feature table TFT03 associated with CCC is used in the same manner as in the first embodiment. Decide what to do.

Further, for example, the storage unit 13 stores four tab feature tables TFTa, TFTb, TFTc, and TFTd corresponding to four document sizes. In the tab feature table TFTa, the tab feature table TFTb, the tab feature table TFTc, and the tab feature table TFTd, the same tab ID (that is, the same tab feature) is associated with different processes. is set. When the storage unit 13 stores the tab feature tables TFTa, TFTb, TFTc, and TFTd, the storage unit 13 further stores a document size table DST shown in FIG. In the document size table DST, correspondence between each document size and the table name of the tab feature table is set. For example, the document size is input to the control unit 11 by the operator's operation on the operation unit 16 and output from the control unit 11 to the image processing unit 15 . Further, for example, the image processing unit 15 determines the document size from the document image DI included in the read image RI. The image processing unit 15 acquires the table name corresponding to the input or determined document size from the document size table DST, and selects the tab having the acquired table name among the plurality of tab feature tables stored in the storage unit 13. Processing similar to that of the first embodiment is performed using the feature table. For example, if the document size is A4 size, the image processing unit 15 uses the tab feature table TFTa associated with A4 size, and if the document size is A5 size, the tab feature table TFTa corresponds to A5 size. If the document size is B4 size, the tab feature table TFTc associated with B4 size is used. , using the tab feature table TFTd associated with the long size, the process to be executed is determined in the same manner as in the first embodiment.

As described above, in the second embodiment, the storage unit 13 stores a plurality of tab feature tables in which different processes are associated with the same tab feature. The image processing unit 15 uses a tab characteristic table that satisfies a predetermined condition among the plurality of tab characteristic tables stored in the storage unit 13 to determine the execution process in the same manner as in the first embodiment. For example, an operator ID, document size, or the like can be used as the predetermined condition.

By doing so, it is possible to determine the processing to be executed using a tab characteristic table that is suitable for each condition.

The second embodiment has been described above.

[Example 3]
All or part of each processing in the above description in the image processing device 20 may be realized by causing a processor of the image processing device 20 to execute a program corresponding to each processing. For example, a program corresponding to each process described above may be stored in a memory, and the program may be read from the memory and executed by a processor. The program is stored in a program server connected to the image processing apparatus 20 via an arbitrary network, downloaded from the program server to the image processing apparatus 20 and executed, or stored in a record readable by the image processing apparatus 20 . It may be stored in a medium and read and executed from the recording medium. Examples of recording media readable by the image processing device 20 include memory cards, USB memories, SD cards, flexible disks, magneto-optical disks, CD-ROMs, DVDs, and Blu-ray (registered trademark) disks. A portable storage medium is included. A program is a data processing method written in an arbitrary language and an arbitrary description method, and may be in any format such as source code or binary code. In addition, the program is not necessarily configured in a single unit, but may be distributed as multiple modules or multiple libraries, or cooperate with a separate program represented by the OS to achieve its function. Including things.

The specific form of distribution and integration of the image processing device 20 is not limited to the one shown in the figure, and all or part of the image processing device 20 can be arranged in arbitrary units according to various additions or functional loads. It can be configured by distributing and integrating functionally or physically.

10 scanner device 11 control unit 12 reading unit 13 storage unit 14 detection unit 15 image processing unit 16 operation unit 17 display unit 20 image processing device

Claims (13)

a detection unit that detects features of convex portions around a document image included in a read image read by the reading unit;
an image processing unit that performs image processing corresponding to the detected feature on the read image;
a storage unit that stores correspondence between the features and the image processing;
and
The image processing unit
determining the image processing to be performed according to the correspondence;
calculating a degree of similarity between the detected feature and the feature stored in the storage unit, and determining the image processing to be performed based on the calculated degree of similarity;
Image processing device. The image processing unit executes image processing selected from a list of candidates for image processing when there are a plurality of features having the same maximum degree of similarity among the features stored in the storage unit. do,
The image processing apparatus according to claim 1 . a detection unit that detects features of convex portions around a document image included in a read image read by the reading unit;
an image processing unit that performs image processing corresponding to the detected feature on the read image;
a storage unit that stores correspondence between the features and the image processing;
and
The image processing unit
determining the image processing to be performed according to the correspondence;
When the feature stored in the storage unit is not similar to the detected feature, the storage unit associates the detected feature with an image process selected from a list of image process candidates. to add to
Image processing device. a detection unit that detects features of convex portions around a document image included in a read image read by the reading unit;
an image processing unit that performs image processing corresponding to the detected feature on the read image;
a storage unit that stores correspondence between the features and the image processing;
and
The image processing unit
determining the image processing to be performed according to the correspondence;
issuing an alert if the feature stored in the storage unit is not similar to the detected feature;
Image processing device. a detection unit that detects features of convex portions around a document image included in a read image read by the reading unit;
an image processing unit that performs image processing corresponding to the detected feature on the read image;
a storage unit that stores correspondence between the features and the image processing;
and
The image processing unit determines the image processing to be performed according to the correspondence,
The storage unit stores a plurality of associations in which the same feature is associated with different image processing,
The image processing unit determines the image processing to be executed according to one of the plurality of associations that meets a predetermined condition,
Image processing device. Detecting features of convex portions around a document image included in a read image read by a reading unit,
performing image processing corresponding to the detected feature on the read image;
storing the correspondence between the features and the image processing in a storage unit;
determining the image processing to be performed according to the correspondence;
calculating a degree of similarity between the detected feature and the feature stored in the storage unit, and determining the image processing to be performed based on the calculated degree of similarity;
Image processing method. Detecting features of convex portions around a document image included in a read image read by a reading unit,
performing image processing corresponding to the detected feature on the read image;
storing the correspondence between the features and the image processing in a storage unit;
determining the image processing to be performed according to the correspondence;
When the feature stored in the storage unit is not similar to the detected feature, the storage unit associates the detected feature with an image process selected from a list of image process candidates. to add to
Image processing method. Detecting features of convex portions around a document image included in a read image read by a reading unit,
performing image processing corresponding to the detected feature on the read image;
storing the correspondence between the features and the image processing in a storage unit;
determining the image processing to be performed according to the correspondence;
issuing an alert if the feature stored in the storage unit is not similar to the detected feature;
Image processing method. Detecting features of convex portions around a document image included in a read image read by a reading unit,
performing image processing corresponding to the detected feature on the read image;
storing the correspondence between the features and the image processing in a storage unit;
determining the image processing to be performed according to the correspondence;
storing in the storage unit a plurality of the associations in which the same feature is associated with the different image processing;
determining the image processing to be executed according to any one of the plurality of associations that meets a predetermined condition;
Image processing method. Detecting features of convex portions around a document image included in a read image read by a reading unit,
performing image processing corresponding to the detected feature on the read image;
storing the correspondence between the features and the image processing in a storage unit;
determining the image processing to be performed according to the correspondence;
calculating a degree of similarity between the detected feature and the feature stored in the storage unit, and determining the image processing to be performed based on the calculated degree of similarity;
A program that causes a processor to execute a process. Detecting features of convex portions around a document image included in a read image read by a reading unit,
performing image processing corresponding to the detected feature on the read image;
storing the correspondence between the features and the image processing in a storage unit;
determining the image processing to be performed according to the correspondence;
When the feature stored in the storage unit is not similar to the detected feature, the storage unit associates the detected feature with an image process selected from a list of image process candidates. to add to
A program that causes a processor to execute a process. Detecting features of convex portions around a document image included in a read image read by a reading unit,
performing image processing corresponding to the detected feature on the read image;
storing the correspondence between the features and the image processing in a storage unit;
determining the image processing to be performed according to the correspondence;
issuing an alert if the feature stored in the storage unit is not similar to the detected feature;
A program that causes a processor to execute a process. Detecting features of convex portions around a document image included in a read image read by a reading unit,
performing image processing corresponding to the detected feature on the read image;
storing the correspondence between the features and the image processing in a storage unit;
determining the image processing to be performed according to the correspondence;
storing in the storage unit a plurality of the associations in which the same feature is associated with the different image processing;
determining the image processing to be executed according to any one of the plurality of associations that meets a predetermined condition;
A program that causes a processor to execute a process.

Images