JP3412999B2 - Image processing apparatus and method - Google Patents

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus for recognizing a character existing in a region surrounded by ruled lines included in a document image having a predetermined format and recognizing a format of an inputted document image, and its image processing apparatus. It is about the method.

[0002]

2. Description of the Related Art Conventionally, a character recognition device for recognizing a character existing in an area surrounded by a ruled line included in an original image has a structure in which the area of the original image having a predetermined format is predetermined. I could only recognize the characters that exist in.

[0003]

Therefore, the above-described conventional character recognition device has a problem that it cannot be applied to original images having a plurality of types of formats, and its usability is poor. Therefore, it is not limited to a specific format,
Within the area included in the original image having a similar format
To recognize the existing characters, format the original image
There was also a need for an image recognition device capable of recognizing. Also,
When reading the characters contained in the area surrounded by the ruled lines included in the document image of a specific format with a scanner, etc., the reading position must be accurately positioned, which is troublesome for the operation in the character recognition process. There was a problem that it cost.

The present invention has been made in view of the above problems, and relates to a document image having a plurality of formats, the format of the inputted document image can be recognized,
An image processing apparatus and method capable of recognizing a character existing in a region included in a document image having a plurality of formats by identifying the configuration of a region surrounded by a ruled line included in the document image Is intended to provide. Another object of the present invention is to provide an image processing apparatus and method for improving the work efficiency of the operation in the recognition processing of the characters existing in the area surrounded by the ruled lines included in the original image.

[0005]

An image processing apparatus according to the present invention for achieving the above object has the following configuration.
That is, the first type of the original image is determined based on the dividing unit that divides the input original image into a plurality of blocks and the block existing at a specific position among the plurality of blocks divided by the dividing unit. A plurality of types divided by the dividing unit based on a type identifying unit for identifying and a key block information about a key block that is a key for identifying an item in the document image for the first type identified by the type identifying unit. Key block detecting means for detecting the key block from the block, and the second type is determined based on the shape and number of blocks at predetermined positions with respect to the key block detected by the key block detecting means. And an identifier setting means for setting an item identifier of an item corresponding to each block according to the determined second type.

[0006] Further, preferably, it further comprises a character recognition means for recognizing a character existing in the block.

Further, preferably, further, there is provided processing order setting means for setting the character recognition processing order of each block in the character recognition means based on the identifier set by the identifier setting means.

Further, preferably, further, there is a set direction setting means for setting a set direction of a character existing in each block based on the identifier set by the identifier setting means.

Preferably, the type identifying means identifies the first type of the original image based on the shape of a block existing at a specific position among the plurality of blocks divided by the dividing means. .

Further, preferably, the key block information includes information regarding a title included in the key block and position information of the key block.

An image processing method according to the present invention for achieving the above object has the following configuration. That is, the first type of the original image is determined based on the dividing step of dividing the input original image into a plurality of blocks and the block existing at a specific position among the plurality of blocks divided in the dividing step. A plurality of pieces divided in the dividing step based on a type identifying step and a key block information about a key block that is a key for identifying an item in the document image for the first type identified in the type identifying step. Determining the second type based on the key block detecting step of detecting the key block from the block and the shape and number of blocks at predetermined positions with respect to the key block detected in the key block detecting step. , The determined second
An identifier setting step of setting the item identifiers of the items corresponding to the blocks according to the type.

[0012]

[0013]

[0014]

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. FIG. 1 is a block diagram showing the functional arrangement of the image processing apparatus according to this embodiment. In FIG. 1, 101 is a scanner, which irradiates a document image with light and reads the reflected light to convert it into an electric signal. Further, the original image read by the scanner 101 is stored in the VRAM area of the RAM 107 as image data. A scanner interface 102 converts an electric signal obtained by the scanner 101 into a binary digital electric signal and transmits the binary digital electric signal to other device constituent elements. Reference numeral 103 denotes a mouse that functions as a pointing device. By moving the mouse 103, the cursor 100 displayed on the display 108 is moved. The contents can be executed by positioning the cursor 100 on a menu displayed on the screen and performing a drag operation or a click operation using a button (not shown) attached on the menu. A mouse interface 104 receives a signal from the mouse 103 and transmits it to another device component. Reference numeral 114 denotes a KB (keyboard), which inputs data and executes instructions via the keyboard. 11
Reference numeral 3 is a KB interface, which receives a signal from the KB 114 and transmits it to another device component.

Reference numeral 105 denotes a CPU, which executes control of the entire apparatus and processing such as area division described later and the recognition processing described in the present invention. 106 is a ROM, and the CPU 105
It stores various data such as a control program executed by the computer, various processing programs, and font data. 107 is R
AM, which is used as a work area or the like for developing a document image and area division processing. Further, it has a VRAM area as a predetermined storage area for storing image data (binary image data) read by the scanner 101. 10
A display 8 displays the image data stored in the VRAM area of the RAM 107, the ruled line extraction processing result executed in this embodiment, and the like. 109 is a display interface.

Reference numeral 110 denotes an FDD (floppy disk drive), which is equipped with the FD and can read and write data. Further, it is possible to execute a process by writing a program of a processing flow described later in the attached FD (not shown) and reading the program into the RAM 107 of the present apparatus. 111 is an FDD interface. Further, 112 is a bus for connecting the respective components of the apparatus.

Next, the processing executed in this embodiment will be described with reference to the flowchart of FIG. FIG. 2 is a flowchart showing a processing flow of processing executed in this embodiment. FIG. 2 is a flowchart showing the processing flow executed in this embodiment.

The processing executed in the present embodiment is shown in, for example, FIG. 10 in which an area surrounded by ruled lines forming an original image (hereinafter, this area is referred to as an item) is determined in advance. The case where the invention is applied to such a family register document will be described, but the invention is not limited to this. For example, any original image may be used as long as it has a predetermined configuration.

First, in step S201, the original image is read by the scanner 101 and converted into binary image data. In step S202, for the obtained binary image data,
Attributes included in binary image data (photos, figures, characters, etc.)
Region division processing is performed to divide the region for each. In the present embodiment, in the area division processing, particularly when an item is extracted, information such as coordinate data of the item is stored as block data as shown in FIG.

Now, the block data shown in FIG. 3 will be described. FIG. 3 is a diagram showing the configuration of block data according to the present embodiment. FIG. 3 shows start point coordinates (X1, Y1), end point coordinates (X2, Y2) for indicating the position of an item included in the binary image data expanded in the RAM 107, valid flag, item identification ID, recognition order, and attribute. , Stores information on the set direction. The start point coordinates indicate the position coordinates of the upper right corner of each item as shown in FIG. 10, and the end point coordinates indicate the position coordinates of the lower left corner of each item. The valid flag indicates whether or not the extracted item is valid. The item identification ID stores the item identification ID of each item according to the setting method described later. The recognition order stores the recognition order when recognizing the characters entered in each item.

The attribute stores an attribute which is a division unit in the area division processing. In the case of the present invention, when text data exists in an item (area surrounded by ruled lines), an attribute indicating that fact is stored and “1” is stored in the valid flag.
If the text data does not exist in the item (area surrounded by ruled lines), an attribute indicating that fact is stored and “0” is stored in the valid flag. The set direction stores information indicating the direction (vertical writing or horizontal writing) of the characters written in each item.

Next, in step S203, the item configuration of the document image is classified from the format information indicating the configuration of the item of the document image, and the item identification process for identifying the item configuring the document image is performed. When identifying the configuration of the item of the document image, the type of configuration of the item of the document image is classified according to the position, shape, area, number, etc. of blocks obtained by dividing the document image into regions, and each item is classified. Identify. Further, it is assumed that the format information is stored in the ROM 106 in advance.

Further, in order to classify and identify the items of the family register document used as the manuscript image of the present embodiment, IDs (item identification IDs) for classifying and identifying the respective items are shown in FIGS. Define as in c). And I of each item
The items of the family register document are classified and identified by combining D. Here, I shown in (a) to (c) of FIG.
The D (item identification ID) will be described.

FIG. 4A shows an ID that defines the type of the composition (hereinafter referred to as page type) of the items of the family register document, and is the block area surrounded by the ruled line at the top right of the family register document (see FIG. 10)), "leader" or "non-leader" is defined as the type. 4B is an ID that defines the type of the person who wrote the page of the family register document, and the ID of the type as shown in FIG. 4B.
Is defined. 4C is an ID that defines the item names of the items that make up the family register document, and the IDs of the types shown in FIG. 4C are defined.

Details of the item identification processing executed in step S203 will be described below with reference to FIG. FIG. 6 is a flowchart showing a detailed processing flow of the item identification processing of this embodiment. First, in step S601, the page type types of the family register document are classified and identified. As a method of this identification, the page type of the family register document is identified by the shape of the block (item) at the upper right of the family register document.

The page type of the family register document, the page type in which the first person is described (hereinafter referred to as "first person type"), and the page type in which the first person is not described (hereinafter, "non-first person type") There are two types). As an identification method, for example, if the width of the upper right block of the family register document is longer than its height, it is identified as the "first person type", and the others are identified as the "non-first person type". Identify the page type. Alternatively,
If the width of the upper right block is larger than the width of the block having the same Y1 coordinate as the Y1 coordinate of the block, it is identified as the "leader type", while the width of the upper right block is the Y1 coordinate of the block. When the width of the block having the same Y1 coordinate as the coordinate is the same, it can be identified as the "non-first person type".

Returning to the description of the flow chart again. In step S601, if the width of the upper right block of the family register document is longer than its height, the block is identified as "first person type", and the process proceeds to step S604. On the other hand, if the width of the upper right block of the family register document is shorter than its height, the block is identified as "non-leader type" and the process proceeds to step S602.

Once the page type of the family register document has been identified, a block (hereinafter referred to as a KEY block) that is a key for further detailed family register document identification and item identification is configured in the family register document. The relative position of each item is detected. First, in the case where the page type is the "first-person type", in step S604, the block titled "Main registry", the block in the first row of the column in which the edited date is described, and the registration data The block in the first row of the column in which "etc." and the block with the title "Father" are detected as KEY0 to 3 blocks, and the address of each block data is as shown in FIG. Remember in the body.

Now, the KEY block data structure shown in FIG. 5 will be described. FIG. 5 is a diagram showing the configuration of the KEY block data structure of the present embodiment. In FIG. 5, the KEY block structure stores the information of the items that are the key for identifying the items constituting the family register document, and there are six KEY0 to 5 blocks as shown in the figure.
Then, the KEY to be detected according to the type of page type
A block is detected and the block data of the detected KEY block is stored.

Next, in step S605, the detected KE
Using the Y0 to 3 blocks, the items are extracted in more detail for each item having information common to each of the KEY0 to 3 blocks, and the item identification ID is set for the extracted items. Details of this setting will be described later with reference to the flowchart of FIG. 7. On the other hand, the page type is "non-leader type"
In this case, in step S602, the block in the first row of the column in which the registration data of the first person is described, the block titled “Father” of the first person, the registration data of the second person, etc. are described. The block in the first row of the column where the column is present and the block with the title "Father" of the second person are respectively detected as KEY2 to 5 blocks, and the block data of the detected KEY2 to 5 blocks are stored in the KEY block structure. To do.

Next, in step S603, the detected KE
Using the Y2 to 5 blocks, the items are extracted in more detail for each item having information common to each of the KEY2 to 5 blocks, and the item identification ID is set for the extracted items. Details of this setting will be described later with reference to the flowchart of FIG. First, the process of setting the item identification ID when the page type is the “first person type” will be described with reference to the flowchart of FIG. 7.

FIG. 7 is a flow chart showing the processing flow of the processing for setting the item identification ID when the page type of this embodiment is the "first person type". First, in step S701, an item identification ID is set for each of the three blocks having the same width below the KEY0 block (the block with the title “main registry” in FIG. 10). In step S702, the four blocks to the left including the KEY1 block from the KEY1 block (the block in the first row of the column in which the editing items are described in FIG. 10) and the blocks below the same block have the same item group (editing). Since the blocks can be regarded as items), item identification IDs are set in these blocks.

In step S703, 10 blocks including the KEY2 block from the KEY2 block (the block in the first row in the column where the registration data etc. are described in FIG. 10) have the same item group (enrollment data etc.). Column), item identification IDs are set in these blocks. In step S704, the block below the item group including the KEY2 block has the same Y1 coordinate as the KEY3 block on the left including the KEY3 block from the KEY3 block (the block titled “father” in FIG. 10). There are blocks, and the number of blocks is counted. Then, in step S705, the item identification IDs of the blocks below the item group including the KEY2 block are set based on the counted number of blocks. Details of this setting will be described later with reference to the flowchart of FIG.

Next, the page type is "non-first person type".
In the case of, the process of setting the item identification ID will be described with reference to the flowchart of FIG. FIG. 8 is a flowchart showing a processing flow of processing for setting an item identification ID when the page type of the present embodiment is “non-first person type”. First, in step S801, nine blocks to the left including the KEY2 block from the KEY2 block (the block in the first row of the column in which the enrollment data etc. are written) have the same item group (enrollment data etc. column). Since these blocks can be regarded, item identification IDs are set in these blocks.

In step S802, nine blocks to the left of the KEY4 block (the block in the first row of the column in which the second person's enrollment data etc. are written) including the KEY4 block have the same item group (the second one). (Registration data column)
Since these blocks can be regarded as, the item identification IDs are set in these blocks. In step S803, KEY2
The block below the item group including the block is KEY3.
There is a block having the same Y1 coordinate as the KEY3 block on the left, including the KEY3 block from the block (the block having the title "Father"), and the number of blocks is counted. Then, in step S804, the item identification ID of a block below the item group including the KEY2 block is set based on the counted number of blocks.

In step S805, the block below the item group including the KEY4 block is the same as the KEY5 block on the left including the KEY5 block from the KEY5 block (the block having the title "father" of the second person) Y1. There is a block with coordinates, and the number of blocks is counted. Then, in step S806, the item identification ID of a block below the item group including the KEY4 block is set based on the counted number of blocks.

Next, the details of the process of setting the item identification ID of the block below the entry data field will be described with reference to FIG.
This will be described with reference to the flowchart of. FIG. 9 shows an item identification I of a block below the entry data column in this embodiment.
7 is a flowchart showing a processing flow of processing for setting D. The flowchart of FIG. 9 is the processing executed in step S704 of the flowchart of FIG. 7, step S804 and step S805 of the flowchart of FIG. 8, but here, step S70 of the flowchart of FIG.
4, that is, a case where the page type is a family register document of “first person type” will be described as an example. In addition, steps S804 and S805 of the flowchart of FIG.
In other words, if the page type is a family register document of "non-first person type", it is realized by the same process.
It is omitted here.

First, in step S901, the counted number of blocks is determined. If the number of blocks is 4, it is determined that the type is the type in which only the actual parents are described (hereinafter referred to as "real child type"). It proceeds to step S902. If the number of blocks is 5, only one of the adopted father or adopted mother is listed (hereinafter, "adopted type A").
Is called) and the process proceeds to step S905. Furthermore,
If the number of blocks is 6, it is determined that both the adopted father and adopted mother are described (hereinafter referred to as “adopted type B”), and the process proceeds to step S909.

If the counted number of blocks is 4, that is, if it is the "real child type", then in step S902,
It is determined whether or not the shape of the second block to the left of the KEY3 block is horizontally long. If it is horizontally long (YES in step S902), it is determined to be “married (husband or wife) type” and the process proceeds to step S903. On the other hand, if it is not horizontally long (NO in step S902), it is determined as “unmarried type” and the process proceeds to step S904.

In step S903, the item identification ID is set as the "real child type" and the "married (husband or wife) type" from the relative positional relationship with the KEY3 block. Also,
In step S904, the item identification IDs are set as the “real child type” and the “unmarried type” based on the relative positional relationship with the KEY3 block. If the number of counted blocks is 5, that is, if the "adopted type A" is selected, step S
At 905, it is determined whether the shape of the third block to the left of the KEY3 block is horizontally long. If it is horizontally long (YES in step S905), it is determined to be “married (husband or wife) type” and the process proceeds to step S906. On the other hand, if it is not horizontally long (NO in step S905), it is determined to be “unmarried type” and the process proceeds to step S907.

In step S906, the item identification ID is set as the "real child type" and the "married (husband or wife) type" from the relative positional relationship with the KEY3 block. Also,
In step S907, the item identification IDs are set as the “real child type” and the “unmarried type” from the relative positional relationship with the KEY3 block. If the number of counted blocks is 6, that is, if the “adopted type B” is selected, step S
At 909, it is determined whether the shape of the fourth block to the left of the KEY3 block is horizontally long. If it is horizontally long (YES in step S909), it is determined to be “married (husband or wife) type” and the process proceeds to step S910. On the other hand, if it is not horizontally long (NO in step S909), it is determined as “unmarried type” and the process proceeds to step S911.

In step S910, the item identification ID is set as the "real child type" and the "married (husband or wife) type" from the relative positional relationship with the KEY3 block. Also,
In step S911, the item identification IDs are set as the “real child type” and the “unmarried type” from the relative positional relationship with the KEY3 block. Next, a specific process of the process executed in step S203 of the flowchart of FIG. 2 will be described with reference to FIGS.

For example, as a result of performing the area division processing described in step S202 of FIG. 2 on the original image of the family register document as shown in FIG. 10, a plurality of item blocks B1101 as shown in FIG. It is assumed that B1136 is obtained. Then, when the item identification processing described in step S203 of FIG. 2 is performed on the area division result of FIG. 11, in this case, the width of the upper right block B1101 is longer than the height and has the same other Y1 coordinates. Since it is different from the block width, it is determined to be the "leader type".

Then, the page type is “first person type”
Since it was determined that the block B1101 in the upper right corner is the block with the title “Main registry” (KE
Y0) ”and record the address as KEY block data. Next, a block B11 adjacent to the left of the KEY0 block and having the same Y1 coordinate of the KEY0 block
05 is regarded as "a block (KEY1) in the first row of the column in which the editing items are described", and its address is stored as KEY block data.

Next, the block B1109 having the same Y1 coordinate as the Y1 coordinate of the KEY0 block, having a height higher than that of the KEY1 block, and having its X2 coordinate on the far right is "first in the column where the enrollment data etc. is described." Row block (KEY2) ”and its address is recorded as KEY block data. Furthermore, the block B11
The block B1123 adjacent under 09 is regarded as a "block (KEY3) titled" Father "", and its address is stored as KEY block data.

Next, blocks are extracted in more detail for each item having information common to each of the KEY blocks detected as described above. Then, the item identification ID is set in each of the extracted blocks. First, since the page type is the “leader type”, there are three blocks B1102 to B1104 having the same width under the KEY0 block. Therefore, the item identification ID is set in each block including the KEY0 block. For example, block B
4A to 4C are used for the item identification ID 1101, 1000 (page type is the first person) +000 (the person who describes the page of the first person) +10 (the title of the main domicile) = 10
10 is set as the item identification ID. Similarly, the item identification IDs of the other blocks B1102 to B1104 are set to 1011 to 1013, respectively.

Next, from the KEY1 block to the left including the KEY1 block, four blocks B1105 to B110 are provided.
8 and the blocks B1119 to B1122 below it are blocks having information in common with the KEY1 block, and therefore item identification IDs corresponding to the respective blocks are set. In this case, each item identification ID is 1020
-1027 is set.

Next, from the KEY2 block to the KEY2 block, the ten blocks B1109 to B11 on the left side are included.
Since 18 is a block having information common to the KEY2 block, the item identification I corresponding to each block
Set D. In this case, each item identification ID is 1
109 to 1118 are set. Next, the blocks under the KEY2 block are the KEY3 block to the KEY2 block.
Item identification IDs are further set according to the number on the left including blocks.

In the case of the family register document shown in FIG. 10, since the number is 6, it is determined that both the adoptive father and the adoptive mother are the described type (“adoptive father type B”). Further, since the shape of the fourth block B1133 to the left of the KEY3 block is horizontally long, it is determined to be a "married (husband or wife) type". As a result, KEY3
From the right with respect to the block having the same Y1 coordinate as the block Y1 coordinate, the block B1123 is determined to be the KEY3 block itself, which is a “block titled“ father ””, and the item identification ID is set to 1030.

Further, the block B1126 is judged as "a block having a title of" mother "", and the item identification I
As for D, 1032 is set. The block B1129 is determined to be a “block titled“ Adoptive Father ””, and the item identification ID is set to 1040. Block B
1132 is determined to be "a block having a title of" foster mother "", and item identification ID 1042 is set. The block B1133 is determined to be a “block described as“ husband ”or“ wife ””, and the item identification ID is 1050.
Is set. The block B1135 is determined to be “a block with the title“ Birth ””, and the item identification ID
Is set to 1070.

Next, the blocks immediately below the "father", "mother", "foster father", "foster mother", "husband" or "wife" and "birth" blocks are their "name" or "birth" respectively. date"
Is determined to be the block in which B11
In item 24, 1031 is set as the item identification ID.
The block B1127 contains 1033 as the item identification ID.
Is set. The block B1128 has an item identification ID.
Is set as 1041. In the block B1131, 1043 is set as the item identification ID. In the block B1134, 1051 is set as the item identification ID. In the block B1136, 1071 is set as the item identification ID.

Next, the block B1125 immediately below the blocks B1124 and B1127 is determined to be a block in which "relationship" is described, and 1034 is set in the block B1125 as an item identification ID. Also, block B
A block B1130 immediately below 1128 and B1131 is determined to be a block in which “relationship” is described, and 1034 is set as an item identification ID in the block B1130.

In this way, the item identification ID as shown in FIG. 12 is set for each item. Explained above
As described in step S201 to step S203
Depending on the processing performed, family register statements with a specific format
Not only a book, but a family register document with multiple formats
(Original image) can be recognized. Next, in step S204, a processing order setting process for setting the processing order of the character recognition processing performed only for the items in which the text data exists, in order from the smallest item identification ID set in each item in step S203. To do. The processing order set for each item is stored in the recognition order of the corresponding block data. On the other hand, "-1" is stored in the block data corresponding to the item where the text data does not exist, and a flag indicating that the character recognition processing is not performed is set. For example, when the processing order setting process is performed on each item for which the value of the item identification ID is set as shown in FIG. 12, the processing order 1 is set for the item in which the text data as shown in FIG. 13 exists. -19 are set.

In step S205, a set direction setting process for setting the set direction of the text data existing in the item for which the processing order has been set in step S204 is performed. Note that, for the method of setting the set direction, for example, a database of the set direction corresponding to the value of the item identification ID as shown in FIG. 14 is stored in the ROM 106 in advance, and the stored database and the item to be processed are set. By comparing the item identification IDs with, the set direction of the text data existing in each item is set.

In step S206, character recognition processing for recognizing the character corresponding to the text data existing in each item is performed according to the processing order set in step S204. The character recognition process is performed using a known character recognition method, and any method that can recognize the character may be used. As described above, according to the present invention, by identifying the configuration of items included in a family register document,
Characters that exist in each item can be recognized.

The above-described area division processing, item identification processing, processing order setting processing, set direction setting processing, and character recognition processing are provided for each item in the processing order set for each item. By making it possible to recognize the characters corresponding to the text data, the character recognition processing order of multiple types of formats becomes accurate, and it is possible to deal with the deviation of items when reading an image with a scanner etc. Can be improved and the time required for the entire process can be shortened.

It is also possible to add a ruled line extracting process for extracting a ruled line included in the original image before performing the area dividing process in step S202.
With such a configuration for performing ruled line extraction processing, it is possible to identify the type of document image before performing the area division processing. For example, step S20 of the flowchart of FIG.
It is easily realized by the flowchart as shown in FIG.

FIG. 15 is a flow chart showing a processing flow of processing executed by another configuration of the present embodiment. First, in step S1501, the original image is read by the scanner 101 and converted into binary image data. In step S1502, the obtained binary image data is subjected to ruled line extraction processing for extracting the ruled lines included in the binary image data. Then, information such as the coordinate data of the extracted ruled lines is stored as block data as shown in FIG.

In step S1503, the obtained binary image data is subjected to area division processing for dividing an area for each attribute (photograph, figure, character, etc.) included in the binary image data. In the present embodiment, in the area division processing, particularly when an item is extracted, information such as coordinate data of the item is stored as block data as shown in FIG. Then, information such as coordinate data of the divided items is stored as block data as shown in FIG. Next, step S15
In 04, the item configuration of the document image is classified based on the format information indicating the configuration of the item of the document image, and the item identification process for identifying the item configuring the document image is performed. The item identification process is the same as step S203 in FIG.
The details are omitted.

In step S1505, step S150
In step 4, in order from the smallest item identification ID set for each item, a processing order setting process for setting the processing order of the character recognition process to be performed only on the item having the text data is performed. In step S1506, a grouping direction setting process for setting the grouping direction of the text data existing in the item for which the processing order has been set in step S1505 is performed. Step S150
In step S7, a character recognition process for recognizing the character corresponding to the text data existing in each item is performed according to the processing order set in step S1505.

For example, it is assumed that when the ruled line extraction processing is executed on the family register document of FIG. 10, a processing result as shown in FIG. 16 is obtained. In this case, if the ruled line 1601, the ruled line 1602, or the ruled line 1603 exists, the page type is identified as a family register document of “first person type”. On the other hand, there is no ruled line 1601 or ruled line 1602, but ruled line 1603
X1 coordinate of the top ruled line 1604 or the bottom ruled line 16
If the same as 05, the page type is identified as a family register document of “non-first person type”.

In the set direction setting process, it is also possible to determine the set direction based on the width and height of the item containing each text data. In this case, it is not necessary to prepare a database in the set direction corresponding to the item identification ID of the item including each text data, and RO
It is possible to save the storage capacity of the storage medium such as M106.

Even when the present invention is applied to a system composed of a plurality of devices (eg, host computer, interface device, reader, printer, etc.), a device composed of one device (eg, copying machine, facsimile device) etc)
May be applied to. Further, an object of the present invention is to supply a storage medium recording a program code of software that realizes the functions of the above-described embodiments to a system or apparatus, and the computer (or CPU or MPU) of the system or apparatus stores the storage medium. It is needless to say that it is achieved by reading and executing the program code stored in.

In this case, the program code itself read from the storage medium realizes the function of the above-described embodiment, and the storage medium storing the program code constitutes the present invention. As a storage medium for supplying the program code, for example, a floppy disk, a hard disk, an optical disk, a magneto-optical disk,
A CD-ROM, a CD-R, a magnetic tape, a non-volatile memory card, a ROM or the like can be used.

Further, not only the functions of the above-described embodiment are realized by executing the program code read by the computer, but also the OS (operating system) running on the computer based on the instructions of the program code. It is needless to say that this also includes the case where the above) performs a part or all of the actual processing and the processing realizes the functions of the above-described embodiments.

Further, after the program code read from the storage medium is written in the memory provided in the function expansion board inserted in the computer or the function expansion unit connected to the computer, based on the instruction of the program code, It goes without saying that a case where the CPU or the like included in the function expansion board or the function expansion unit performs some or all of the actual processing and the processing realizes the functions of the above-described embodiments is also included.

When the present invention is applied to the above-mentioned storage medium, the storage medium stores the program code corresponding to the above-mentioned flow chart. Briefly, in the memory map example of FIG. Each module shown will be stored in the storage medium. That is, in FIG. 17, at least the program code of each of the “storage module”, the “division module”, the “identification module”, the “assignment module”, and the “recognition module” may be stored in the storage medium.

The "storage module" stores format information relating to document images having a plurality of predetermined formats in a storage medium. "Split module" is
A document image having a predetermined format is divided into a plurality of areas. The "identification module" identifies the type of document image having the predetermined format based on the characteristics of the divided areas. The "assignment module" assigns the format information of the document image having a predetermined format corresponding to the identified type to the divided areas of the document image. The "recognition module" recognizes the character existing in the area to which the format information is assigned.

[0069]

As is apparent from the above description, regarding an original image having a plurality of types of formats, the format of the input original image can be recognized, and the area surrounded by the ruled lines included in the original image is configured. By identifying
It is possible to provide an image processing apparatus and method capable of recognizing characters existing in the area included in a document image having a plurality of formats. Further, it is possible to provide an image processing apparatus and its method that improve the work efficiency of the operation in the recognition processing of the characters existing in the area surrounded by the ruled lines included in the document image.

[0070]

[Brief description of drawings]

FIG. 1 is a block diagram showing a functional configuration of a character recognition device of the present embodiment.

FIG. 2 is a flowchart showing a processing flow of processing executed in this embodiment.

FIG. 3 is a diagram showing a configuration of block data according to the present embodiment.

FIG. 4 shows a structure of an item identification ID according to the present embodiment.

FIG. 5 is a diagram showing a configuration of a KEY block data structure according to the present embodiment.

FIG. 6 is a flowchart showing a detailed processing flow of item identification processing according to the present embodiment.

FIG. 7 is a flowchart showing a processing flow of processing for setting an item identification ID when the page type of the present embodiment is “first person type”.

FIG. 8 is a flowchart showing a processing flow of processing for setting an item identification ID when the page type of the present embodiment is “non-first person type”.

FIG. 9 is a flowchart showing a processing flow of processing for setting an item identification ID in a block below a field of enrollment data etc. according to the present embodiment.

FIG. 10 is a diagram showing an example of a document image according to the present embodiment.

FIG. 11 is a diagram showing a processing result of area division processing executed on a document image according to the present embodiment.

FIG. 12 is a diagram showing a setting result of an item identification ID set for a document image according to the present embodiment.

FIG. 13 is a diagram showing a setting result of a processing order set for a document image according to the present embodiment.

FIG. 14 is a diagram showing a relationship between an item identification ID and a set direction according to the present embodiment.

FIG. 15 is a flowchart showing a processing flow of processing executed by another configuration of the present embodiment.

FIG. 16 is a diagram showing a processing result of ruled line extraction processing executed on a document image according to the present embodiment.

FIG. 17 is a diagram showing a structure of a memory map of an FD in which a program of a processing flow executed in the present invention is stored.

[Explanation of symbols]

101 scanner 102 Scanner interface 103 mouse 104 mouse interface 105 CPU 106 ROM 107 RAM 108 display 109 display interface 110 FDD 111 FDD interface 112 bus 113 KB interface 114 KB

Front page continued (58) Fields surveyed (Int.Cl. ⁷ , DB name) G06K 9 / 00- 9/76 G06T 11/60

Claims (12)

(57) [Claims] 1. A first division of the original image based on a division unit that divides the input original image into a plurality of blocks, and a block existing at a specific position among the plurality of blocks divided by the division unit.
The type discriminating means for discriminating the type, and the dividing means for dividing based on the key block information about the key block which is the key for identifying the item in the original image with respect to the first type identified by the type identifying means. A second type based on a key block detecting means for detecting the key block from a plurality of generated blocks, and the shape and number of blocks at predetermined positions with respect to the key block detected by the key block detecting means. And an identifier setting means for setting an item identifier of an item corresponding to each block according to the determined second type. 2. The image processing apparatus according to claim 1, further comprising character recognition means for recognizing a character existing in the block. 3. The method according to claim 2, further comprising processing order setting means for setting a character recognition processing order of each block in the character recognition means based on the identifier set by the identifier setting means. The image processing device described. 4. The method according to claim 1, further comprising set direction setting means for setting a set direction of a character existing in each block based on the identifier set by the identifier setting means. The image processing apparatus according to any one of items. 5. The type identifying means identifies the first type of the original image based on the shape of a block existing at a specific position among a plurality of blocks divided by the dividing means. The image processing apparatus according to claim 1. 6. The image processing apparatus according to claim 1, wherein the key block information includes information regarding a title included in the key block and position information of the key block. 7. A first division of the original image based on a division step of dividing the input original image into a plurality of blocks, and a block existing at a specific position among the plurality of blocks divided in the division step.
A type identification step for identifying the type of the document, and a division in the division step based on key block information regarding a key block that is a key for identifying an item in the original image with respect to the first type identified in the type identification step. A second type based on a key block detecting step of detecting the key block from a plurality of generated blocks, and a shape and number of blocks at predetermined positions with respect to the key block detected in the key block detecting step. And an identifier setting step of setting an item identifier of an item corresponding to each block according to the determined second type. 8. The image processing method according to claim 7, further comprising a character recognition step of recognizing a character existing in the block. 9. The method according to claim 8, further comprising a processing order setting step of setting a character recognition processing order of each block in the character recognition step based on the identifier set in the identifier setting step. The described image processing method. 10. The method according to claim 7, further comprising a set direction setting step for setting a set direction of a character existing in each block based on the identifier set in the identifier setting step. The image processing method according to any one of items. 11. The type identifying step identifies a first type of the original image based on a shape of a block existing at a specific position among a plurality of blocks divided in the dividing step. The image processing method according to claim 7. 12. The image processing method according to claim 7, wherein the key block information includes information regarding a title included in the key block and position information of the key block.