JP4587167B2 - Image processing apparatus and image processing method - Google Patents

Description

  The present invention relates to a technique for converting a paper document read from an input device such as a scanner into editable electronic data, and more particularly to a technique for analyzing a table frame object in a paper document and replacing it with a ruled line.

  In recent years, as information has been digitized, systems for storing or transmitting documents in electronic form instead of paper are rapidly spreading. In particular, as electronic data suitable for storing and transmitting full-color documents, vector data obtained by separating an image area of a paper original into objects such as characters, tables, and figures and converting it into a form suitable for each object is suitable. The amount of data can be reduced and the object can be reused.

Here, for the table object in the document, the text information in the table is extracted by the image area separation process, while the table frame can be extracted as binary image data. The table frame extracted as the binary image data is converted into vector data expressed by ruled lines or the like by the analysis processing of the table frame (see, for example, Patent Document 1). The table frame converted to vector data not only has a small data size as vector data, but also has high reusability as a table frame.
Japanese Patent Laid-Open No. 5-12489

  When binarizing and extracting an object in a document including a table frame and text in the table, the binarization threshold is set in order to binarize the image area or binarize each object. It is set by the image area or the object area.

  For example, when binarization is performed on the table area, if there is a dark cell as shown in FIG. 25A, the dark cell is filled as shown in FIG. 25B. There arises a problem that it is generated as an image. In addition, when binarized, there is a problem that a lot of noise is generated in the cell.

  For such cells, character information cannot be extracted normally. When the original document is a color document, cell filling often occurs due to binarization due to the correlation between the cell colors, and it is difficult to accurately extract the table frame, which is a very serious problem. Yes.

  The present invention has been made to solve the above-mentioned problem, and prevents cells in which character information is originally embedded from being filled by binarization processing, and extracts all character information in a table. With the goal.

The image processing apparatus of the present invention includes an extraction unit that extracts an outer frame region of a table and a rectangular region of a cell in the table based on the result of the outline of the binary image data of the table region, and the outer frame region. Mapping means for mapping a rectangular area of the cell to the area, and creating a colored cell based on corner points of the rectangular area of the cell in an area where the rectangular area of the cell is not mapped in the outer frame area; Based on the mapping result of the means, the recognition means for recognizing the structure of the table area, the re-processing means for performing binarization processing on the colored cells and extracting the objects in the cells, and the recognition means based on the result of extracting the structure and the re-processing means of the tablespace, and table data generating means for generating table data, was closed, the mapping means, of the outer frame region If a point of interest is extracted from a point and a corner point of the rectangular area of the cell that has already been mapped, and there is a corner point of the rectangular region of the cell that is not yet mapped within a certain distance from the point of interest Then, it is determined that the point of interest matches the corner point, and the rectangular region of the cell having the corner point is mapped, and the rectangular region of the cell that has not yet been mapped within a certain distance from the point of interest. If there is no corner point, the colored cell is created based on a horizontal line and a vertical line passing through the corner point of the rectangular area of the cell that has not yet been mapped .

Further, the image processing method of the present invention includes an extraction step in which the extraction unit extracts the outer frame region of the table and the rectangular region of the cell inside the table based on the result of the outline of the binary image data of the table region. Mapping means maps the rectangular area of the cell to the outer frame area, and color-paints the rectangular area of the cell in the outer frame area based on the corner points of the rectangular area of the cell. A mapping step for creating a cell, a recognition unit for recognizing the configuration of the table area based on a mapping result in the mapping step, and a reprocessing unit for binarizing the colored cell A reprocessing step of extracting an object in a cell, and a table data creation unit based on the configuration of the table area recognized in the recognition step and the result extracted by the reprocessing unit A table data creation step of creating a table data, have a, in the mapping step, to extract the target point from the corner point of the rectangular region of the cell already subjected to mapping the intersection of the outer frame region, If there is a corner point of the rectangular area of the cell that has not yet been mapped within a certain distance from the point of interest, it is determined that the point of interest matches the corner point, and the rectangular area of the cell having the corner point is determined. If there are no corner points of the rectangular area of the cell that are not yet mapped within a certain distance from the target point, horizontal and vertical lines passing through the corner points of the rectangular area of the cell that are not yet mapped Based on the above, the colored cell is created .

  According to the present invention, it is possible to remove noise in a table frame from a color document, accurately extract the table frame, and prevent character information from being extracted due to noise and fill in a cell. In addition, accurate table frame vector information can be extracted.

  The best mode for carrying out the invention will be described below in detail with reference to the drawings.

  FIG. 1 is a diagram illustrating an appearance of a document processing apparatus according to the first embodiment. In FIG. 1, reference numeral 101 denotes a computer device that executes a document digitization processing program including a program for realizing processing described with reference to a flowchart described later. Further, the computer apparatus 101 is accompanied by a display apparatus 102 for displaying a situation and an image to the user, and an input apparatus 103 configured to include a pointing device such as a keyboard and a mouse for receiving a user operation. As the display device 102, a CRT, an LCD, or the like is used. A scanner device 104 optically reads and digitizes a document image and sends the obtained image data to the computer device 101. Note that a color scanner is used as the scanner device 104.

  FIG. 2 is a block diagram illustrating an example of the configuration of the document processing apparatus according to the first embodiment. In FIG. 2, reference numeral 201 denotes a CPU, which realizes various functions including electronic processing described later by executing a control program stored in a ROM or RAM described later. A ROM 202 stores various control programs executed by the CPU 201 and control data. A RAM 203 stores various control programs executed by the CPU 201 and defines a work area necessary for the CPU 201 to execute various processes.

  Reference numeral 204 denotes an external storage device, which stores a control program for realizing the processing in the first embodiment to be described later by the CPU 101, document image data obtained by reading with the scanner device 104, and the like. A computer bus 205 connects the above-described components.

  FIG. 3 is a diagram showing an overview of document digitization processing in the document processing apparatus. Here, the flow of digitization processing is as follows. First, in the input unit 301, a color document to be digitized is read by the scanner device 104 and stored in the external storage device 204 as image data. Next, in the binarization processing 302, the binarization processing is performed on the image data of the document stored in the external storage device 204 for the subsequent image area separation processing and outline generation processing. In the image area separation process 303, elements such as characters, diagrams, tables, frames, lines, and the like are extracted from the binary image obtained in the binarization process 302 and divided into areas.

  Next, in the vectorization process 304, the character part of the image data divided into regions is recognized by the character recognition unit 305, and converted into outline vector data by the outline creation unit 306. Further, the table and frame elements are outlined by the table processing unit 308, and the outline is ruled. Note that the image data converted by the outline creation unit 306 is converted into vector data with high image quality in which the outline of each object is expressed by a smooth curve, independent of resolution, and easy to edit.

  On the other hand, for other figures, photographs, and backgrounds, for example, the background is held and compressed by the compression unit 309 in a form suitable for each, such as JPEG compression.

  Next, the electronic document creation processing 310 creates a digitized document based on the converted image data using character recognition data and table structure data based on the attribute of each divided element. Then, the output unit 311 stores the generated digitized document in the external storage device 204.

  Note that the output form of the output unit 311 is not limited to storage in the external storage device 204, and is displayed on the display device 102 or output to other devices on the network via a network interface (not shown). It can also be sent to a printer (not shown).

  Here, the details of each process in the document digitization process (see FIG. 3) executed in the document processing apparatus shown in FIGS. 1 and 2 will be described in the following order.

[Binarization processing]
In the binarization process 302, luminance information is extracted from the input document image data, and a histogram of the luminance values is created. A plurality of threshold values are set on the histogram, and an optimal threshold value is derived by analyzing the connection of black pixels on the binary image binarized with each threshold value, and a binary image based on the threshold values is obtained.

[Image area separation processing]
The image area separation process 303 recognizes the image data of one page read on the left side shown in FIG. 4 as a block (block) for each object, and sets each block as an attribute such as character / drawing / photo / line / table. This process is to divide into areas having different attributes (TEXT / PICTURE / PHOTE / LINE / TABLE) as shown on the right side of FIG.

  In the image area separation process 303, the pixel line surrounded by the black pixel outline is extracted from the binary image obtained in the binarization process 302 by tracing the outline of the black pixel. Also, for black pixel blocks with a large area, contour tracing is also performed for white pixels inside, and white pixel blocks are extracted, and recursively from the inside of white pixel blocks with a certain area or more. A black pixel block is extracted.

  The black pixel blocks thus obtained are classified by size and shape, and are classified into regions having different attributes. For example, if the aspect ratio is close to 1 and the size is within a certain range, it is a pixel block corresponding to the character, the portion where adjacent characters can be grouped in a well-aligned manner is the character region, and the flat pixel block is the line region. The area occupied by a black pixel block that is well-aligned and contains square white pixel blocks in a well-aligned manner is a table region, an area where irregular pixel blocks are scattered is a photo region, and pixels of any other shape A block is defined as a drawing area.

  FIG. 5 is a diagram showing block information and input file information for each block separated by the image area separation process 303. As shown in FIG. 5, the block information includes attributes of each block, coordinates (X, Y), width (W), height (H), and OCR information, where attribute 1 is text, attribute 2 is drawing, attribute 3 is a table, attribute 4 is a line, and attribute 5 is a photograph. The input file information has a total number N of blocks (6 in the example shown in FIG. 5 from block 1 to block 6).

  If a clearer binary image is to be obtained for each block, the above-described binarization process may be performed for each block.

[Character recognition section]
The character recognition unit 305 recognizes an image cut out in units of characters using a pattern matching method, and obtains a corresponding character code. This recognition process compares an observed feature vector obtained by converting a feature obtained from a character image into a numerical sequence of several tens of dimensions with a dictionary feature vector obtained in advance for each character type, and determines the character type with the closest distance. This is a process for obtaining a recognition result. There are various known methods for extracting the feature vector. For example, there is a method characterized by dividing a character into meshes and using a mesh number-dimensional vector obtained by counting character lines in each mesh as line elements according to directions.

  When character recognition is performed on the character area extracted in the image area separation process 303, first, horizontal writing and vertical writing are determined for the corresponding area, and the lines are cut out in the corresponding directions, and then the characters are cut out. Get a character image. This horizontal / vertical writing is determined by taking a horizontal / vertical projection of the pixel values in the corresponding area. If the horizontal projection variance is large, the horizontal writing area is determined. If the vertical projection variance is large, the vertical writing is performed. What is necessary is just to determine with an area | region. In the case of horizontal writing, the character strings and characters are decomposed by cutting out lines using horizontal projection, and further cutting out characters from the vertical projection of the cut lines. For vertically written character areas, horizontal and vertical may be reversed. At this time, the character size can be detected.

[Outline generator]
The outline creation unit 306 converts the contour of the extracted pixel block into vector data for the region that has been the image, line, or table region in the image region separation process 303. Specifically, a point sequence of pixels forming an outline is divided by points regarded as corners, and each section is approximated by a partial straight line or curve. An angle is a point where the curvature is maximum, and the point where the curvature is maximum is that a string is placed between k left and right points Pi-k and Pi + k with respect to an arbitrary point Pi as shown in FIG. It is obtained as a point where the distance between the string and Pi becomes maximum when drawn. Furthermore, let R be the chord length / arc length between the points Pi-k and Pi + k, and the point where the value of R is equal to or less than the threshold value can be regarded as a corner. Each section after being divided by the corners can be vectorized by using a least square method for a straight line and a curve using a cubic spline function.

  Further, when the target has an inner contour, it is similarly approximated by a partial straight line or a curve using the point sequence of the white pixel contour extracted by the image area separation process.

[Table processing section]
The table processing unit 308 recognizes the cells in the table and the configuration thereof, and converts the data into editable electronic data for each cell, for example, by expressing the table frame with ruled lines. It should be noted that the table portion is extracted as a table frame separated from the character portion in the table frame by the image area separation processing 303.

  FIG. 7 is a flowchart showing the table processing in the table processing unit 308. First, the table part separated by the image area separation process 303 is binarized to obtain binary data of a table frame (step S701). Here, the binary data of the table frame input from the image area separation process 303 may be output as it is. Alternatively, the binarization process and the table frame extraction process may be performed again on the table area obtained by the image area separation process 303 to accurately extract the table frame.

  Next, the table structure is recognized for the table frame obtained in step S701 (step S702). FIG. 8 is a flowchart showing processing for recognizing a table frame. First, the table frame is outlined by the outline processing described above, and the table frame is expressed by smooth straight lines and curves (step S801). Next, a cell outline representing a cell is extracted from the outline of the table frame (step S802). Here, the outline is originally classified into an outer outline and an inner outline. First, an outline constituting an outer frame of the entire table is extracted from the outer outline. Since there may be a table inside the table, a plurality of outer frames may be extracted.

  Next, the outline which comprises the cell which exists inside an outer frame is extracted. In this process, it is determined from the outline whether or not the outline is the size that constitutes the cell, and further, it is determined whether or not the outline constitutes a rectangular figure or a triangular figure by graphic recognition processing. To do. An outline determined as a rectangular figure, a triangular figure, or a set of rectangular figures is defined as a cell outline. (A), (b), and (c) shown in FIG. 9 are examples of outlines determined to be a rectangular figure, a triangular figure, and a set of rectangular figures.

  Next, the cell outline determined to constitute the outer frame or cell in step S702 is converted into a cell graphic (step S803). Specifically, first, in step S802, the outline constituting the outer frame and the outline constituting the inner cell are extracted. However, the figure represents that all the angles of the outline constituting the outer frame are represented by 90 °. If it is judged, it is converted into a figure that expresses between 90 ° angles as a straight line. Next, the cell determined to constitute the cell inside the outer frame is converted into a cell figure. Here, the cell graphic is a rectangular graphic.

  For example, FIG. 10 shows an example in which the cell outline shown in FIG. 9 is converted into a cell figure. The cell outlines (a), (b), and (c) shown in FIG. 9 are converted into (a), (b), and (c) shown in FIG. 10, respectively. Here, the cell outline of (a) shown in FIG. 9 becomes (a) shown in FIG. 10 as it is by the fitting process of the rectangular figure. Similarly, the triangle outline cell outline as shown in FIG. 9B is subjected to a rectangular figure fitting process. In the fitting process of the rectangular figure to the triangular figure, the cell rectangle is fitted so as to surround the cell outline constituting the triangle.

  Note that the fitted rectangular figure is finally integrated with each other from the positional relationship and extracted as one cell figure. For example, the cell graphic of (b) shown in FIG. 10 is integrated into the cell graphic shown in FIG. 11 and expressed as one cell graphic. Of course, there are cell figures that are not integrated, and for those figures, cell figures that are applied to the triangle outline are used as cell figures.

  Further, a cell outline extracted as a set of rectangular figures as shown in FIG. 9C is separated into rectangular figures as shown in FIG. 10C. In this separation processing into rectangular figures, corners that will form a right angle in the outline are found, and the composition of the corner points is decomposed into rectangular figures. Further, the horizontal and vertical directions of the table are obtained using all the extracted cells, and all the cell graphics are converted into cell graphics comprising the obtained horizontal and vertical components. In this way, the outer frame figure and the cell figure are extracted, but each cell figure is given attribute information by its cell outline. FIG. 12 is a diagram illustrating an example of a cell graphic, a cell outline constituting the cell graphic, and each attribute information.

  Next, a mapping area for mapping the cell graphic converted in step S803 is created (step S804). Here, the mapping area is an area for mapping the cell graphic, and the area inside the outer frame is directly used as the mapping area. Also, the intersections of the outer frames are extracted. The intersection is a point where the ruled line of the table intersects with the ruled line. In the outer frame, the corner point of the outer frame becomes the intersection. FIG. 13 shows an example of the mapping area and the intersection.

  Next, the cell graphic is mapped to the cell graphic mapping area (step S805), and the configuration of the cell graphic is recognized. Specifically, the table figure is recognized by mapping the cell figure in the mapping area created in step S804, and extracting the intersection where the ruled line of the table intersects the ruled line from the mapped cell figure. To do. That is, the table structure is recognized by examining the adjacent relationship between the intersections.

  Here, details of the cell graphic mapping process for mapping the cell graphic in step S805 will be described.

  FIG. 14 is a flowchart showing the cell graphic mapping process. First, an attention point is extracted from the intersection point of the outer frame described above (step S1401). Here, the attention point is an intersection having intersections adjacent to each other on the right side and the lower side. A rectangular area including these three points is a mapping area, and nothing is mapped to the rectangular area. Not an intersection. FIG. 15 shows an example showing the relationship between the mapping area, the intersection, the mapping cell, and the point of interest.

  Next, for the extracted attention point, it is determined whether or not there is a cell graphic having the attention point at the upper left intersection (step S1402). Specifically, the distance between the upper left corner point of all cell shapes that have not yet been mapped and the attention point is examined, and the distance between the upper left corner point of the cell shape and the attention point is within a certain value, and the most attention A cell graphic close to a point is determined as a cell graphic in which the point of interest matches the upper left corner. Here, if there is a cell graphic in which the attention point and the upper left corner point match, the cell graphic is mapped on the mapping area (step S1403).

  If there is no cell graphic in which the distance between the upper left corner of all cell graphics and the target point is within a certain value, a colored cell is created and mapped (step S1404). A colored cell is a rectangular figure. First, it is determined whether there is a corner point of a cell figure that has not yet been mapped within a rectangular area (hereinafter referred to as a rectangular area A) that is slightly wider than the intersection of the right point and its adjacent right side and the lower side. If present, the area is delimited by horizontal and vertical straight lines passing through the corner points. This division operation is performed for all corner points existing in the rectangular area A, and the rectangular figure at the upper left of the area divided by the horizontal and vertical lines is used as a colored cell and mapped.

FIG. 16 is a diagram illustrating an example of creating a colored cell in the rectangular area A. In the example shown in FIG. 16, since the corner points of two cell figures exist in the rectangular region A, the rectangular region A is divided by horizontal and vertical straight lines passing through these corner points, and the most of the divided regions. Map the rectangular figure in the upper left as a colored cell.

  Next, an intersection on the cell graphic is created from the cell graphic mapped in steps S1403 and S1404 (step S1405). The intersection point of this mapping figure is the intersection point as it is, but if the corner point of the mapping figure is within a certain threshold distance from the existing intersection point, the intersection point created by that corner point already exists Since it can be judged, no new intersection is created from the corner. Here, since the intersection at the upper left of the mapping figure is determined to coincide with the point of interest, a new intersection from the upper left corner is not created. Also, the intersection created from the upper right corner point of the mapping figure is created on the horizontal line from the attention point, and the lower left corner point is created on the vertical line from the attention point.

Next, it is determined whether or not there is a point of interest among the intersections currently extracted (step S1406). The point of interest, as described above, at the intersection with the intersection which is connected adjacent to the right and bottom sides, a rectangular region including its these three points are mapping area, and still nothing to the rectangular region It is an unmapped intersection. If there is an area where no cell graphic or colored cell is mapped in the area surrounded by the intersection, the point of interest exists. If there is no point of interest, the table structure recognition process is terminated. If the point of interest still exists, the process returns to step S1401, and the point of interest is extracted again and a series of processing is repeated.

  By the above iterative process, the adjacent relationship between the intersections is created, and it becomes possible to express a ruled line. FIG. 17 shows an example in which the adjacent relationship of intersections created, mapped cell graphics and colored cells, and attribute information in the case of cell graphics are described. The table ruled lines obtained from the attribute information shown in FIG. 17 are as shown in FIG.

  Here, when the cell graphic mapping process shown in FIG. 14 is completed, the process proceeds to step S806 shown in FIG. 8, and the thickness and positional relationship of the ruled lines are adjusted to extract the exact position of the intersection. The thickness of the ruled line is obtained from the distance between adjacent cell graphics among the cell graphics mapped in step S805. Further, the position of the ruled line is adjusted so as to be in the middle of adjacent cell graphics.

  It should be noted that the position of the intersection is determined as the intersection where the ruled lines obtained in step S806 intersect.

[Color cell reprocessing]
In step S703 shown in FIG. 7, re-processing is performed on the colored cells extracted in the table configuration recognition process (step S702).

  FIG. 19 is a flowchart showing the color painting cell reprocessing. First, cell discrimination is performed (step S1901). In the cell determination, it is determined whether or not there is a cell delimiter on the manuscript with respect to the color cell delimiter created in step S702, and in some cases, the color painted cells are integrated. Specifically, with respect to the original image, the edge components of neighboring pixels corresponding to the separation lines of adjacent colored cells are examined, and it is determined whether or not there is a ruled line on the separation line in the original image. If it is determined that there is no ruled line on the original image, the two cells are integrated into one cell. The above integration process is performed for all adjacent colored cells to extract cells.

  Next, regarding the cells extracted in step S1901, one cell is regarded as one image, and binarization processing is performed for each cell (step S1902). By performing binarization processing for each cell, it is possible to extract binary objects such as text and patterns in the cell from the painted cells that have been filled. Then, image area separation processing is performed for each cell (step S1903).

  Note that the image area separation process particularly extracts text data. When the extracted text data is extracted, the text code is extracted by applying OCR, further converted into a font by being outlined, and added to the data of the character part.

[Table data generation processing]
In step S704 shown in FIG. 7, table data is created using the vector information created in steps S702 and S703. For example, the table shown in FIG. 18 is as shown in FIG. In FIG. 24, text information is extracted from parts 2401 to 2403. In addition, if a cell has no text information, it can be left as it is as a colored cell.

  With the above processing, it is possible to avoid creating a cell that fills the table frame, accurately extract text information from the table, and create table data.

  In the above-described processing, cell discrimination is performed for the colored cells, and binarization and image area separation processing are performed for each obtained cell. However, the regions of all of the plurality of colored cells extracted are more simply extracted. It can be regarded as a single document, and binarization and image area separation processing can be performed on the original, and information such as characters and lines can be obtained from the area of the colored cell.

[Conversion to application data]
As described above, image data for one page is subjected to the image area separation process 303, and the result of the vectorization process 304 is converted into an intermediate data format file as shown in FIG. Such a data format is called a document analysis output format (DAOF).

  FIG. 20 shows the data structure of DAOF. In FIG. 20, reference numeral 2001 denotes a header, which holds information relating to document image data to be processed. Reference numeral 2002 denotes a layout description data section. Characters (TEXT), titles (TITLE), captions (CAPTION), line drawings (LINEART), natural images (PICTURE), frames (FRAME), tables (TABLE), etc. in the document image data. The attribute information of each block recognized for each attribute and the rectangular address information thereof are held. Reference numeral 2003 denotes a character recognition description data portion, which holds character recognition results obtained by character recognition of TEXT blocks such as TEXT, TITLE, and CAPTION. Reference numeral 2004 denotes a table description data portion, which stores details of the structure of the TABLE block. Reference numeral 2005 denotes an image description data section, which cuts out image data of blocks such as PICTURE and LINEART from document image data and holds them.

  Such a DAOF is not only used as intermediate data, but may be stored as a file itself. However, in this file state, individual objects cannot be reused in a so-called general document creation application. .

  Therefore, an electronic document creation process 309 for converting DAOF into application data will be described.

  FIG. 21 is a flowchart showing an outline of the entire electronic document creation process. First, in step S2101, DAOF data is input. In step S2102, a document structure tree that is the source of application data is generated. In step S2103, actual data in the DAOF is flowed based on the document structure tree to generate actual application data.

  FIG. 22 is a flowchart showing details of the document structure tree generation process. FIG. 23 is a diagram for explaining the document structure tree. As a basic rule of overall control, the process flow shifts from a micro block (single block) to a macro block (an aggregate of blocks). In the following description, “block” refers to a micro block and an entire macro block.

  First, in step S2201, regrouping is performed on a block basis based on the relevance in the vertical direction. Immediately after the start, judgment is made in units of micro blocks. Here, the relevance can be defined by the fact that the distance is close and the block width (height in the horizontal direction) is substantially the same. Information such as distance, width, and height is extracted with reference to DAOF.

  FIG. 23 is a diagram showing a page structure and a tree of its document structure. 23A shows an actual page configuration, and FIG. 23B shows its document structure tree.

  As a result of step S2201, T3, T4, and T5 shown in FIG. 23 are generated as one group V1, and T6 and T7 are generated as one group V2, and as shown in FIG. Group V2 is generated as a group of the same hierarchy. In step S2202, the presence / absence of a vertical separator is checked. For example, the separator is physically an object having a line attribute in the DAOF. In addition, as a logical meaning, it is an element that explicitly divides a block in an application. If a separator is detected here, it is subdivided at the same level.

  Next, in step S2203, it is determined using the group length whether or not there are no more divisions. If the vertical group length is the page height, the document structure tree generation is terminated. In the example shown in FIG. 23, since there is no separator and the group height is not the page height, the process proceeds to step S2204, and regrouping is performed on a block basis based on the horizontal relationship. Here too, the first time immediately after the start is determined in units of microblocks. The definition of the relevance and the determination information is the same as in the vertical direction.

  In the case of the example shown in FIG. 23, H1 is generated at T1 and T2, and H1 is generated as a group in the same hierarchy above V1 and V2 at V1 and V2. In step S2205, the presence / absence of a horizontal separator is checked. In the example shown in FIG. 23, since there is S1, this is registered in the tree, and a hierarchy of H1, S1, and H2 is generated.

  Next, in step S2206, it is determined using the group length whether or not there are no more divisions. If the horizontal group length is the page width, the document structure tree generation is terminated. If not, the process returns to step S2201, and the relevance check in the vertical direction is repeated again at the next higher level. In the example shown in FIG. 23, since the division width is the page width, the process ends here, and finally V0 of the highest hierarchy representing the entire page is added to the document structure tree.

  After the document structure tree is completed, application data is generated based on the information (step S2103). Specifically, the example shown in FIG. 23 is as follows.

  That is, since there are two blocks T1 and T2 in the horizontal direction, H1 has two columns, and after T1 internal information (refer to DAOF, text of character recognition result, image, etc.) is output, the column is changed and the internal of T2 Information is output, and then S1 is output. Next, since H2 has two blocks V1 and V2 in the horizontal direction, it outputs as two columns, V1 outputs its internal information in the order of T3, T4, T5, then changes the column, and inside of T6, T7 of V2 Output information.

  The conversion processing into application data can be performed by the above processing.

  Even if the present invention is applied to a system composed of a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), it is applied to an apparatus (for example, a copier, a facsimile machine, etc.) composed of a single device. It may be applied. Specifically, the scanned image data may be input (image data may be input from a public line or a network) in order to change the image quality with a multifunction device, copier, or facsimile machine. It can be applied when extracting a contour vector from data, scaling the extracted contour vector, generating image data from the scaled contour vector, and printing the generated image data.

  Another object of the present invention is to supply a recording medium in which a program code of software realizing the functions of the above-described embodiments is recorded to a system or apparatus, and the computer (CPU or MPU) of the system or apparatus stores the recording medium in the recording medium. Needless to say, this can also be achieved by reading and executing the programmed program code.

  In this case, the program code itself read from the recording medium realizes the functions of the above-described embodiment, and the recording medium storing the program code constitutes the present invention.

  As a recording medium for supplying the program code, for example, a floppy (registered trademark) disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a magnetic tape, a nonvolatile memory card, a ROM, or the like is used. be able to.

  Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an OS (operating system) operating on the computer based on the instruction of the program code. It goes without saying that a case where the function of the above-described embodiment is realized by performing part or all of the actual processing and the processing is included.

  Further, after the program code read from the recording medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, the function expansion is performed based on the instruction of the program code. It goes without saying that the CPU or the like provided in the board or the function expansion unit performs part or all of the actual processing and the functions of the above-described embodiments are realized by the processing.

1 is a diagram illustrating an appearance of a document processing apparatus according to a first embodiment. 1 is a block diagram illustrating an example of a configuration of a document processing apparatus in Embodiment 1. FIG. It is a figure which shows the outline | summary of the digitization process of the document in a document processing apparatus. FIG. 6 is a diagram for explaining image area separation processing according to the first exemplary embodiment. It is a figure which shows the block information and input file information with respect to each block isolate | separated by the image area separation process 303. FIG. It is a figure for demonstrating conversion to outline vector data. It is a flowchart which shows the table process in the table process part 308. FIG. It is a flowchart which shows the process which recognizes a table frame. It is a figure which shows an example of the outline determined to be a collection of a rectangular figure, a triangular figure, and a rectangular figure. It is a figure which shows the example which converted the cell outline shown in FIG. 9 into the cell figure. It is a figure which shows the example of integration of the adjacent cell figure. It is a figure which shows an example about the cell outline which comprises a cell figure, and each attribute information. It is a figure which shows an example of a mapping area | region and an intersection. It is a flowchart which shows a cell figure mapping process. It is a figure which shows the relationship between a mapping area | region, an intersection, a mapping cell, and an attention point. It is a figure which shows the example which produces a colored cell in the rectangular area. It is a figure which shows the example which described the adjacent relationship of the produced intersection, the mapped cell figure, the coloring cell, and the attribute information in the case of a cell figure. It is a figure which shows the process result obtained from the adjacent relationship of the intersection shown in FIG. It is a flowchart which shows color painting cell reprocessing. It is a figure which shows the data structure of a document analysis output format (DAOF). It is a flowchart which shows the outline of the whole electronic document preparation process. It is a flowchart which shows the detail of a document structure tree production | generation process. It is a figure which shows the structure of a page, and the tree of the document structure. It is a figure which shows the table frame produced in a present Example. It is a figure for demonstrating the problem in the conventional table process.

Claims (4)

Extraction means for extracting the outer frame region of the table and the rectangular region of the cell inside the table based on the result of the outline of the binary image data of the table region;
Mapping that maps the rectangular area of the cell to the outer frame area and creates a colored cell based on the corner points of the rectangular area of the cell in the area where the rectangular area of the cell is not mapped in the outer frame area Means,
Recognition means for recognizing the configuration of the table area based on the mapping result of the mapping means;
Re-processing means for performing binarization processing on the colored cells and extracting objects in the cells;
Table data creation means for creating table data based on the configuration of the table area recognized by the recognition means and the result extracted by the reprocessing means,
The mapping means extracts an attention point from the intersection of the outer frame region and the corner point of the rectangular region of the cell that has already been mapped,
If there is a corner point of the rectangular area of the cell that has not yet been mapped within a certain distance from the point of interest, it is determined that the point of interest matches the corner point, and the rectangular area of the cell having the corner point is determined. Mapping,
If there is no corner point of the rectangular area of the cell that is not yet mapped within a certain distance from the point of interest, based on the horizontal and vertical lines passing through the corner point of the rectangular area of the cell that is not yet mapped, images processor characterized in that to create a color painting cell. An extracting step for extracting an outer frame region of the table and a rectangular region of the cells inside the table based on the result of the extraction unit that binarizes the binary image data of the table region;
The mapping means maps the rectangular area of the cell to the outer frame area, and in the area where the rectangular area of the cell is not mapped in the outer frame area, a colored cell based on the corner points of the rectangular area of the cell Mapping process to create
A recognition unit for recognizing a configuration of the table area based on a mapping result in the mapping step;
A reprocessing unit that performs binarization processing on the colored cells and extracts objects in the cells;
A table data creating step for creating table data based on the configuration of the table area recognized in the recognition step and the result extracted by the reprocessing unit;
In the mapping step, a point of interest is extracted from the intersection of the outer frame area and the corner point of the rectangular area of the cell that has already been mapped,
If there is a corner point of the rectangular area of the cell that has not yet been mapped within a certain distance from the point of interest, it is determined that the point of interest matches the corner point, and the rectangular area of the cell having the corner point is determined. Mapping,
If there is no corner point of the rectangular area of the cell that is not yet mapped within a certain distance from the point of interest, based on the horizontal and vertical lines passing through the corner point of the rectangular area of the cell that is not yet mapped, An image processing method characterized by creating colored cells. Computer
Extraction means for extracting the outer frame area of the table and the rectangular area of the cell inside the table based on the result of the outline of the binary image data of the table area;
Mapping that maps the rectangular area of the cell to the outer frame area and creates a colored cell based on the corner points of the rectangular area of the cell in the area where the rectangular area of the cell is not mapped in the outer frame area means,
Recognition means for recognizing the configuration of the table area based on the mapping result of the mapping means;
Reprocessing means for performing binarization on the colored cells and extracting objects in the cells;
Based on the configuration of the table area recognized by the recognition means and the result extracted by the reprocessing means, function as table data creation means for creating table data,
The mapping means extracts an attention point from the intersection of the outer frame region and the corner point of the rectangular region of the cell that has already been mapped,
If there is a corner point of the rectangular area of the cell that has not yet been mapped within a certain distance from the point of interest, it is determined that the point of interest matches the corner point, and the rectangular area of the cell having the corner point is determined. Mapping,
If there is no corner point of the rectangular area of the cell that is not yet mapped within a certain distance from the point of interest, based on the horizontal and vertical lines passing through the corner point of the rectangular area of the cell that is not yet mapped, A computer program for creating colored cells. A computer-readable recording medium on which the program according to claim 3 is recorded.

Images