JPH0514703A - Picture processor - Google Patents

Abstract

PURPOSE:To automate frame line area extraction as a selected object candidate, and to prevent the soiling of an original by providing a contour tracing means, a character/graphic decision means, a contour comprehensive relation decision means, and an area extracting means by remarking that a frame line and a table line in an original picture can be substituted for a designated area by a marker pen. CONSTITUTION:Area recognition processing is executed mainly by a CPU 7, and an input picture contour line in a RAM 3 is traced by the contour tracing means 9 by using an area recognizing means 13 constituted of the contour tracing means 9, the character/graphic decision means 10, the contour comprehensive relation decision means 11, and the area extracting means 12, etc., and picture contour information is outputted. Here, whether that picture is a graphic picture or a character picture is decided by the means 10 from the size of the contour of each picture based on the picture contour information from the means 9, and on the decision of the graphic picture, the means 11 decides the comprehensive relation of the outer and the inner contours of the graphic picture, and correspond to these contours. After that, the means 12 extracts a frame line area based on the comprehensive relation. Thus, the soiling of the picture by the pen is prevented.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a printer having a digital input / output such as a digital copying machine or a facsimile, which performs digital image processing such as image erasing, italic shadowing, and whitening on an image in a specific area. The present invention relates to an image processing device for outputting to the etc.

[0002]

2. Description of the Related Art Generally, when performing image processing on an image of a specific area in an image processing apparatus of this type, it is necessary to recognize the processing target area and processing content in a document image. As a method of recognizing such an image processing area and processing content in the original image, conventionally, the area is designated by a marker pen. For example, Japanese Patent Application No. 2-
According to No. 229065, the contour data of the mark image is obtained, the pair of the outer contour loop and the inner contour loop is set as the processing target area, and the other portion is regarded as the command and its type is recognized. Further, according to Japanese Patent Application No. 2-299428, a target area and a command are specified in a document image with a marker pen, and image processing is executed for the target area according to the specified command. Japanese Patent Application 2
According to No. 144452, the two stored in the memory
The processing area information is extracted from one of the color mark image information and the processing content information is obtained from the other. Further, according to Japanese Patent Application No. 2-144521, connecting pixels are cut out from the mark image information to determine whether it is a line image having processing area information or a character image having processing content information.

[0003]

However, in any of the methods, the manuscript must be directly written on the manuscript with a marker pen, and the manuscript becomes dirty, and it cannot be applied to the important manuscript. .

On the other hand, as a method not using such a marker pen, for example, when it is desired to leave only the title portion of the table in the manuscript and delete the other image information, the portion may be erased with a correction liquid. Alternatively, if it is desired to subject the title portion to image processing such as italics, outlines, and shadowing, a document having such an image is separately prepared and then cut and pasted at a desired position of the original document. Some of them are designed to be synthesized. However, this is to recreate the manuscript itself, and again to spoil the manuscript.

[0005]

A digital image obtained by optically reading a document image by image input means is temporarily stored in storage means, and the stored input image is subjected to digital image processing by image processing means. An image processing apparatus configured to output to an image output means,
In the described invention, the contour tracking means for tracing the contour line of the input image and outputting the image contour information, and the contour size of each image based on the image contour information are used to determine whether or not the image is a graphic image. A character / figure determining means, a contour inclusion relation determining means for associating the outer contour and the inner contour of the determined graphic image with each other and associating the outer contour with the inner contour, and a frame area based on the obtained inclusion relation. A region recognizing unit having a region extracting unit for extracting the image is provided, and a selecting unit is provided for selecting and instructing the image processing target region and the image processing content from the extracted frame line region.

According to the second aspect of the present invention, the selecting means instructs the size of the image processing target area and the image processing content to be selected from the extracted frame line area, and further, the size of the frame line area is obtained and the selected size is calculated. Area size determination means for determining the image processing target area selected by the selection means from the size is provided.

In the third aspect of the present invention, further, vectorization means for vectorizing the frame line image forming the frame line area extracted by the area extraction means, and vector correction for correcting the vectorized frame line data. Means, vector drawing means for expanding the modified vector data in the output memory for the image output means, image erasing means for erasing the original vectorized frame line image data from the storage means, and image by the image processing means. An image clearing means having an image synthesizing means for synthesizing the processed image data and the frame line vector image created by the vector drawing means is provided between the image processing means and the image output means.

On the other hand, according to the fourth aspect of the present invention, the contour tracing means for tracing the contour line of the input image and outputting the image contour information, and the contour size of each image based on the image contour information are used to determine that image. Character / figure determining means for determining whether or not the image is a graphic image, and contour inclusion relationship determining means for determining an inclusion relationship between the outer contour and the inner contour of the determined graphic image and associating the outer contour with the inner contour. The area recognition means having area extraction means for extracting the frame area based on the inclusion relation and table recognition means for recognizing the table structure based on the positional relationship between the extracted frame areas is provided, and the recognized table structure A selecting means is provided for selecting and instructing the image processing target area and the image processing content from the inside.

According to the fifth aspect of the invention, the contour tracking means for tracing the contour line of the input image and outputting the image contour information, and the contour size of each image based on the image contour information are used to determine that image. Character / graphic determination means for determining whether or not it is a graphic image, contour vectorization means for vectorizing the contour data of the determined graphic image, and the feature of the contour that the continuity of the vectorized contour vector changes. Area recognition means having a feature point extraction means for extracting as a point and a table recognition means for recognizing a table structure based on the contour vector and the extracted feature points is provided, and an image processing target area is selected from the recognized table structure. The selecting means is provided to select and instruct the image processing content.

Further, in the invention according to the sixth aspect, the contour tracking means for tracing the contour line of the input image and outputting the image contour information, and the contour size of each image based on the image contour information are used to determine that image. Character / graphic determination means for determining whether or not a graphic image, image vectorization means for vectorizing the determined graphic image, vector correction means for correcting vectorized vector data, and corrected vector data Area recognition means having a table recognition means for recognizing a table structure based on the table structure is provided, and selection means for selecting and instructing an image processing target area and image processing content from the recognized table structure is provided.
A vector drawing means for synthesizing and drawing the vector data corrected by the vector correction means in the image data after the image processing by the image processing means is provided.

On the other hand, according to the seventh aspect of the present invention, the contour tracing means, the character / graphic determination means, the contour inclusion relation determination means, and the area extraction means as well as the positional relationship between the inner contours of the extracted frame line areas are based on each other. Area recognition means having table recognition means for recognizing the composite table structure is provided, table division means for dividing the recognized composite table into each table is provided, and an image processing target table is selected from among the tables divided from the composite table. The selecting means is provided to select and instruct the image processing content.

According to the present invention, the contour tracing means, the character / graphic determination means, the contour inclusion relation determination means, and the area extraction means as well as the outline direction of the inside contour of each extracted frame line area change greatly. To be recognized as a contour feature point, and a line width recognition means for recognizing a distance from the extracted feature point to another feature point located at the shortest distance as a line width. Area recognition means for recognizing the composite table structure by regarding the portion whose line width is thicker than other line widths as a table frame, and providing table division means for dividing the composite table into each table based on the table frame, A selecting means is provided for selecting and instructing the image processing target table and the image processing content from the tables divided from the composite table.

Further, in the invention described in claim 9, the image processing apparatus further comprises image input means for optically reading a color original image to obtain a black-and-white digital image and a color digital image. Store in the storage means,
It is assumed that the stored input image is subjected to digital image processing by the image processing means and output to the image output means, and a contour tracking means for tracing the contour line of the input image by the black-and-white digital image and outputting the image contour information, A character / graphic determination means for determining whether or not the image is a graphic image based on the size of the outline of each image based on the image outline information, and an inclusion relationship between the outer contour and the inner contour of the determined graphic image is obtained to the outside. The contour inclusion relation determining means for associating the contour with the inner contour, the area extracting means for extracting the frame area based on the obtained inclusion relation, and the color distribution of each frame area extracted by the area extracting means are set to the color. Area information extracted by the area extracting means and color area determining means for determining a color area by checking based on an input image of a digital image. Area recognition means for recognizing the composite table structure based on the area information determined by is provided, table division means for dividing the recognized composite table into respective tables is provided, and an image is selected from among the tables divided from the composite table. A selection means is provided to select and instruct the processing target table and the image processing content.

[0014]

When the original image is subjected to the image processing and output, the image within the area surrounded by the frame lines and the table frame is often targeted. Focusing on this point, even if it is not based on the marker pen method, if a frame line or a table frame structure is extracted from the document image and an arbitrary region in it is selected as a processing target region, the document itself is Does not require any processing. According to the first aspect of the present invention, the area recognizing means including the contour tracing means, the character / graphic determining means, the contour inclusion relation determining means, and the area extracting means allows the frame area to be selected as a candidate for selection from the original image. Are automatically extracted, the subsequent selection may be performed by the selection means, and the area designation by the marker pen is not required.

At this time, if the number of frame line areas is large, the number of selection items by the selection means increases and the operability deteriorates. However, according to the invention of claim 2, the size of the frame line area is made a selection item for area selection, Since the area is determined later by the area size determination means, the selection items by the selection means are reduced, and the operability can be improved to select the target area.

Although the frame image may be handwritten,
According to the invention described in claim 3, since the image clearing means utilizing the vector system is provided, it is possible to obtain an image in which the frame lines are cleanly printed together with necessary image processing as a final output.

On the other hand, according to the invention described in claim 4, since the table recognition means is provided in the area recognition means to recognize the table structure, only the image of the title area in the table is left and the image of the other area is left. It becomes easy to deal with image processing suitable for a table structure such as deleting. In particular, according to the invention described in claim 5, since the table structure is recognized using the contour vectorization method and the feature point extraction method, the invention can be applied to a complicated table. Also, according to the invention of claim 6, after the frame line image itself of the table frame is vectorized, correction such as integration is performed,
Since the table structure is recognized, the present invention can be applied to a complicated table, but in particular, by converting the frame image into vector data, a small amount of data is required and the processing speed is increased. In addition, since the modified vector data is composed and drawn in the image data after the image processing by the vector drawing means, it is possible to make a clear handwriting of the table frame or change the line width of the table frame.

Further, when attention is paid to an original image, some of them have a composite table structure, and in such a composite table, there are cases where it is desired to divide each table into different image processing. In such a case, since the image processing is performed after the area is specified with the marker pen or the tablet and only one table is extracted or the table is colored, the division accuracy is low, There is a problem that a plurality of image processes cannot be selected. In this respect, according to the invention of claim 7, the structure of the composite table is recognized based on the vertical and horizontal lengths of the item areas forming the table and the positional relationship of the center of gravity, and the table is divided. It becomes easy and accurate to perform arbitrary image processing on the table.

Further, according to the invention described in claim 8, the line width of the line segment forming the table is recognized and the line width Since the thick portion is regarded as the table frame = the break of the table and is divided, similarly, it becomes easy and accurate to perform arbitrary image processing on an arbitrary table in the composite table.

Further, in the case where the composite table is color-coded, according to the invention of claim 9, the composite table can be divided based on the color difference, and similarly, any table in the composite table can be divided. It becomes easy and accurate to perform arbitrary image processing on the.

[0021]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT An embodiment of the present invention will be described with reference to FIGS. FIG. 2 is a block diagram showing a schematic configuration of the entire image processing apparatus such as a digital copying machine. First, an image input means 1 such as a scanner for optically reading a document image and converting and outputting the binary image data is output. It is provided. The input image read and converted by the image input means 1 is passed through the bus 2 to the RAM 3 as a storage means.
Stored in. An image processing unit 4 is provided which performs various image processes on the input image stored in the RAM 3 and stores it in the RAM 3 again. Further, the image-processed image stored in the RAM 3 is output to the image output means 5 such as a printer or a CRT and used for hard copy or display. Further, a CPU 7 for executing the programs stored in the ROM 6 and controlling the respective means 1, 4, 5 is provided. The RAM 3 is used as a work area for programs in addition to storing input images and images after image processing. Further, a selecting means 8 constituted by a keyboard, a ten-key pad, a stylus pen, etc. for inputting various messages from the user is also connected through the bus 2.

FIG. 1 shows a block diagram configuration for performing the characteristic area recognition processing of this embodiment. This processing is mainly performed by the CPU 7, and the area recognition means 13 including the contour tracking means 9, the character / graphic determination means 10, the contour inclusion relation determination means 11, and the area extraction means 12 is provided. . The contour tracking means 9 tracks the contour line of the input image in the RAM 3 and outputs the image contour information. The character / graphic determination means 10 determines from the size of the contour of each image based on the image contour information from the contour tracking means 9 whether the image is a graphic image or a character image. The contour inclusion relation determining means 11 determines the inclusion relation between the outer contour and the inner contour of the graphic image and associates the outer contour with the inner contour when it is determined to be a graphic image. The area extracting means 12 extracts a frame area based on the inclusion relationship obtained by the contour inclusion relationship determining means 11.

In such a configuration, FIG.
Consider a case where a document image including the frame line 14 is read and input as shown in FIG. First, the contour tracking means 9 sequentially tracks the contour lines of the black pixels of the image in the RAM 3 and extracts the contour loop (the contour tracking method will be described later). The character / graphic determination means 10 compares the size of the extracted contour line loop with a preset threshold value to determine whether the input image is a character image or a graphic image. Will be described later). FIG. 3B shows a graphic contour which is a result of the frame line 14 being determined as a graphic image, and includes an outer contour 15 and inner contours 16 and 17. In the contour inclusion relation determining means 11, such outer contour 15 and inner contour 1
The inclusive relation with 6, and 17 is examined, and the outer contour 15 and the inner contours 16 and 17 are associated. Although the inclusion relation determination method will be described later, in the example of FIG. 3B, the outer contour 15 includes the inner contours 16 and 17. Based on such a correspondence relationship, the area extracting means 12 extracts the frame line areas 1 and 2 surrounded by the inner contours 16 and 17 as image processing target area candidates as shown in FIG. In this way, the area surrounded by the frame line 14 in the original image is automatically extracted.

After this, the selection means 8 allows the user to select which of the extracted frame line areas 1 and 2 is to be the target area for image processing and what kind of image processing content is to be applied. By the selection instruction, the image processing means 4 performs the designated image processing on the designated area 1 or 2. The image after such image processing is printed out on, for example, paper by the image output means 5. FIG. 3D shows an example of an output image when the image erasing in the area 2 is designated, and FIG. 3E shows an example of an output image when the italic type and the shadowing process are designated for the image in the area 1. .

Next, an embodiment of the invention described in claim 2 will be described with reference to FIGS. In the above embodiment,
Paying attention to the fact that when the number of extracted frame line areas increases, the selection items by the selection means 8 increase and the operability deteriorates. In the present embodiment, each frame of the inner contour included in the outer contour with respect to the extraction result. The size (area) of the line region is calculated, and the image processing target or non-processing target is specified according to the size. For this reason, the selection means 8 of the present embodiment selects and instructs the image processing target area by size, and
A region size judging means 18 is added.

In such a structure, FIG.
Consider a case where a document image including a frame line 19 as shown in FIG. First, as in the case of the above-described embodiment, the outline tracking means 9, the character / graphic determination means 10, the outline inclusion relation determination means 11 and the area extraction means 12 are subjected to the processing, so that a frame line is formed as shown in FIG. Extraction results of regions 1, 2, and 3 are obtained. Next, the user uses the selection means 8
In the extracted frame area, which area is to be subjected to image processing is instructed to be selected from among “in the minimum area”, “other than the minimum area”, “in the maximum area”, and “other than the maximum area”, and , Instructing selection of the image processing content. In response to such designation, the area size determination unit 18 calculates the size of each of the frame line areas 1, 2, and 3 included in the outer contour and determines the designated processing target area (area size determination). The method will be described later). In the illustrated example, there is a size relationship of region 1 <region 3 <region 2. After determining the processing target area, the image processing means 4 performs the designated image processing on the area and outputs the image processing means 5 to the image output means 5. Figure 5 (c)
Shows an example of an output image when image erasing other than the minimum area is designated, and FIG. 5D shows an example of an output image when italicizing and shading processing of an image in the minimum area is designated.

Further, an embodiment of the invention described in claim 3 will be described with reference to FIGS. 6 and 7. In the present embodiment, a clear copy output function is provided in the case of a handwritten frame line. For example,
Image processing means 4 and image output means 5 in comparison with the configuration of FIG.
Between the vectorization means 20, the vector correction means 21, the vector drawing means 22, the image erasing means 23, and the image synthesizing means 2.
An image clear copy means 25 constituted by 4 and 4 is provided. The vectorization means 20 vectorizes the frame line image forming the frame line area extracted by the area extraction means 12. The vector correction means 21 corrects the frame line data converted into a vector in order to absorb the shake of handwriting. The vector drawing means 22 expands the modified vector data in the RAM 3 for the image output means 5. The image erasing means 23 erases the vectorized original frame image data from the RAM 3.
The image synthesizing means 24 synthesizes the image data after the image processing by the image processing means 4 and the frame line vector image created by the vector drawing means 22.

In such a structure, FIG.
Consider a case where a document image including a handwritten frame line 26 as shown in FIG. First, as in the above-described embodiment, the outline tracking means 9, the character / graphic determination means 10, the outline inclusion relation determination means 11 and the area extraction means 12 are processed to obtain a frame as shown in FIG. Line areas 1, 2,
Extraction results of 3 are obtained. Next, when the selection means 8 gives an instruction to select, for example, image deletion of the areas 2 and 3, the image processing means 4 performs the designated processing, and the processing result as shown in FIG. 7C is obtained. The processing so far is the same as the case of FIG. 3, for example. Thereafter, the processing result is sent to the vectorization means 20, the frame line image is vectorized from the outline information of the frame line, and the vector data and the frame line image passing through the center of the frame line image as shown in FIG. 7D. Line width (the vectorization method will be described later). In parallel with this processing, the original frame image is erased from the RAM 3. Then, the shake of the handwritten frame line 26 is corrected by the vector correction means 21, and
A modified contour vector as shown in (e) is obtained (the vector modification method will be described later).

The corrected contour vector data is sent to the vector drawing means 22 together with the line width data acquired when the frame line image is vectorized, and a cleanly written contour vector is drawn as shown in FIG. 7 (f). Such a vector drawing image is combined with the image data after the image processing by the image processing means 4 by the image combining means 24, and a combined output as shown in FIG. 7 (g) is obtained.

In the present embodiment, the image data after the frame image is erased (image processed) and the cleanly drawn contour vector image after vector drawing are written in different memory units, and both are written by the image synthesizing means 24. The vector drawing means also serves as the image combining means, and the vector drawing means 22 directly draws the image data after the frame line image is erased so that the output image can be combined. You may According to this, the image synthesizing means 24 can be omitted and the memory capacity can be saved.

Next, an embodiment of the invention described in claim 4 will be described with reference to FIGS. 8 and 9. In the present embodiment, the table frame area can be extracted instead of the simple frame area extraction, and the table recognition means 31 is added to the area recognition means 13. The table recognizing means 31 recognizes the table structure based on the mutual positional relationship between the frame line areas extracted by the area extracting means 12, and thereby divides the table area into a title area portion and other area portions. The divided areas can be automatically extracted as image processing target candidates.

In such a structure, FIG.
Consider a case where a document image including the table frame 32 as shown in FIG. First, as in the above-mentioned embodiment, the contour tracing means 9 and the character / figure determining means 10 perform the processing, whereby a figure composed of an outer contour 33 and a large number of inner contours 34 as shown in FIG. 9B. The contour is obtained as the determination result. Then, the contour inclusion relation determining means 11 and the area extracting means 12 perform the processing, whereby the inside contours 34 are surrounded by the frame line areas a to a in the table frame 32 as shown in FIG. 9C.
Extract as p. The areas a to p thus extracted are input to the table recognition means 31, and representative points of the respective areas a to p, for example, the center of gravity of the areas are extracted like black dots shown in FIG. The table structure is recognized from the positional relationship between the X direction and the Y direction. When the table structure is recognized, as shown in FIG. 9 (e), the top area (a to d) of the table is divided into the horizontal title area T1 and the leftmost area (a, e, i, m) is determined as the vertical title area T2 portion.

After that, the user selects and designates which area is to be subjected to the image processing and the processing content by the selecting means 8. In response to this designation, the image processing means 4 performs the designated image processing for the target area, and the image output means 5
Output to. FIG. 9F shows an example of an output image in the case where the image erasing of the area other than the title areas T1 and T2 is designated, and FIG. 9G shows the images of the title areas T1 and T2 with the italic and white processing. An example of an output image in the case is shown.

An embodiment of the invention described in claim 5 will be described with reference to FIGS. The embodiment described above
The positional relationship between the frame line areas is obtained by using representative points, which is intended for table recognition with a simple structure as shown in FIG. 9 (a). Even a table with a more complicated structure can be recognized.
Therefore, together with the contour tracking means 9 and the character / graphic determination means 10, the contour vectorization means 35 for vectorizing the determined contour data of the graphic image, and the point where the continuity of the vectorized contour vector changes Area recognition means 38 including a feature point extraction means 36 for extracting as a feature point and a table recognition means 37 for recognizing a table structure based on the contour vector and the extracted feature points is provided.

In such a structure, FIG.
Consider a case where a document image including a front frame 39 as shown in (a) is read and input. Such an image is obtained by the contour tracking means 9
And the character / figure determining means 10 through the processing, the outer contour 40 and the inner contour 4 as shown in FIG.
A figure contour consisting of 1 is obtained as a determination result. Such a determination result is input to the contour vectorization means 35,
Inner contour 4 by absorbing digital noise of contour data
One contour chain code data is vectorized. Next, the feature point extraction means 36 calculates the angle change between the continuous contour vectors and extracts the point with a large angle change as the feature point (the feature point extraction method will be described later). Figure 12 (a)
White circles in (b) indicate feature points. In the table recognition means 37, from the contour vector data of the inner contour 41 obtained by the contour vectorization means 35 and the feature points extracted by the feature point extraction means 36, the table structure, that is, the title area T1 in the horizontal direction of the table. The portion and the vertical title area T2 portion are recognized.

As a method of recognizing the title area T1 portion in the horizontal direction, for example, as shown in FIG. 12 (a), first, the upper left uppermost feature point p ₁ in the inner leftmost inner contour loop is detected.
Starting from, the contour vector v ₁ traveling in the positive Y direction is traced to reach the first feature point p ₂ . Next, the contour vector v ₂ that advances in the positive direction of X from this feature point p ₂ is traced to find the next feature point p ₃ . This time, of the feature points p ₄ and p ₅ located at a distance corresponding to the line width of the table frame from this feature point p _3, it is in the extension direction of the current traveling direction and beyond that, the current traveling direction. The feature point p _{4 in} which the contour vector v ₃ exists in the extension direction of is searched for. Such processing is sequentially repeated, and when there is no feature point that advances in the same direction, it means that the end of the table frame 39 has been reached. In the example of FIG. 12A, the feature point p ₆ is the rightmost one of the table frame. This time, from the feature point p ₆ to the negative direction of Y in the same tracking method, and when the feature point p ₇ at the upper right of the table frame 39 is reached, the same tracking method from the feature point p ₇ to the negative direction of X is performed. Then, the tracking is completed when returning to the starting point p ₁ . The area traced in this way and surrounded by the thick line arrow is the title area T1 in the horizontal direction (see FIG. 11C).

On the other hand, the method of recognizing the vertical title area T2 portion is basically the same. For example, FIG. 12 (b)
As shown in, the first feature point p ₈ is searched for by following the contour vector v ₄ that advances in the positive direction of X from the start point p ₁ . This time, the contour vector v ₅ that advances in the positive direction of Y from this feature point p ₈ is traced, and the next feature point p ₉ is searched. This time, among the feature points p ₁₀ and p ₁₁ located at a distance corresponding to the line width of the table frame from this feature point p ₉ , it is in the extension direction of the current traveling direction,
In addition, a feature point p ₁₀ at which the contour vector v ₆ exists in the extension of the current traveling direction is searched for, and the process proceeds in that direction.
Such processing is sequentially repeated, and when there is no feature point that advances in the same direction, it means that the lower end portion of the table frame 39 has been reached. In the example of FIG. 12B, the feature point p ₁₁ is the bottom edge of the table frame. This time, from the feature point p _{11 in} the negative direction of X, the same tracking method is performed, and when the feature point p ₁₃ at the lower left of the table frame 39 is reached, the similar tracking method is performed in the negative direction of Y from the feature point p ₁₃ Then, the tracking is completed when returning to the starting point p ₁ . The area traced in this way and surrounded by a thick arrow is the title area T2 in the vertical direction (see FIG. 11C).

By the processing by the table recognizing means 37,
The table frame 39 shown in FIG. 11A is recognized as a table structure having horizontal and vertical title areas T1 and T2 as shown in FIG. 11C. Thereafter, the user uses the selection means 8 to select and instruct which image processing is to be performed on the image of which region in the extracted region, as in the case of the above-described embodiment. In response to this selection instruction, the image processing means 4 performs the designated image processing and outputs it to the image output means 5. Figure 11
(d) shows an example of an output image when image erasing of an area other than the title areas T1 and T2 is designated.

Further, an embodiment of the invention described in claim 6 will be described with reference to FIGS. 13 and 14. This embodiment also makes it possible to recognize even a table frame having a complicated table structure as in the above-mentioned embodiment. However, if the table frame is handwritten, for example, it is necessary to correct (clear) it. Is also possible.
In the case of a handwritten frame line, it can be realized by vectorizing the frame line image of the front frame and correcting the vector so as to absorb the shake of the handwriting. Of course, it is possible to draw with the original line width at the time of this drawing, but it is also possible to draw after changing the line width and line type. Further, in the vectorization method, the table structure can be recognized by the method of the embodiment, but in the present embodiment, the table recognition is performed by using the vector data obtained by vectorizing the frame image. To reduce the amount of data and increase the processing speed. Therefore, the contour tracking means 9 and the character /
An area recognition unit 45 including a graphic determination unit 10, an image vectorization unit 42, a vector correction unit 43, and a table recognition unit 44 is provided, and a vector drawing unit 46 is provided between the image processing unit 4 and the image output unit 5. Is provided.

The image vectorization means 42 vectorizes the graphic image itself (the vectorization method will be described later). The vector correction means 43 corrects the contour vector vectorized by the image vectorization means 42, and is used for recognition of the table structure by the table recognition means 44. Further, the vector drawing means 46 adds the vector correction means 43 to the image data after the image processing by the image processing means 4.
The contour vector data corrected by is synthesized and drawn.

In such a structure, FIG.
Consider a case where a document image including a front frame 47 (which may be handwritten) is read and input as shown in FIG. Also in this case, the contour tracking means 9,
The contour data of the table frame image is obtained through the processing by the character / graphic determination unit 10 (see FIG. 11B). Next, the frame line image itself is vectorized by the image vectorization unit 42, and after the frame line image is erased, the vector correction unit 43 absorbs the shake caused by handwriting in the case of the handwritten table frame 47. Are combined with each other, or the vectors divided by the lines of the table frame 47 at the time of vectorization are integrated, or the vector close to horizontal or vertical is corrected to horizontal or vertical, respectively. Will be described later). In this way, as a result of the vector correction, the corrected vector data represented by the thick line and the thin line as shown in FIG. 14B is obtained. White circles in the figure indicate the end points (start point or end point) of the vector.

Next, the table recognizing means 44 first searches the corrected outline vector data for four vectors corresponding to the outer frame. This is achieved by searching the minimum or maximum vectors V1 and V2 in the Y direction from horizontal or near horizontal vectors and the minimum and maximum vectors V3 and V4 in the X direction from vertical or near vertical vectors. To be done.
Next, the vectors V5 and V6 having the same length as the retrieved outer frame vectors V1 to V4 and located at the second position from the smallest in the X and Y directions are searched. As a result of such processing, the area surrounded by the vectors V1, V3, V5, and V4 is the horizontal title area T1 portion, and the vectors V1 and V4.
A region surrounded by 3, V2 and V6 is recognized as a vertical title region T2 portion. FIG. 14C shows the recognition result of such a table structure.

After that, the user instructs the selection means 8 to select what kind of image processing is to be performed on the image of which area in the extracted area, as in the case of the above-described embodiment.
At this time, if it is desired to change the line width and line type of the frame line when outputting the image, the content is specified. In response to the selection instruction, the image processing means 4 executes the designated image processing. Then, the vector drawing means 46 receives the processing. In the vector drawing means 46, the corrected contour vector data is erased by the image vectorization means 42 with the line width acquired at the time of vectorization of the frame image or the line width and line type selected and designated by the selection means 8. The composite image is formed in the image data after this, and is output to the image output means 5. In FIG. 14 (d), image erasing of areas other than the title areas T1 and T2 is specified, and for the frame lines, the outer frame is a thick line, the title part boundary line is a double line, and the remaining frame lines are outside. A frame line reaching the outer frame from the frame is a middle line, and other frame lines are thin lines.

Further, an embodiment of the invention described in claim 7 will be described with reference to FIGS. 15 and 16. In the present embodiment, in the case of a composite table structure, the structure can be analyzed and recognized to be divided into each table, and different image processing can be performed for each table.
For this reason, the area recognition means 54 provided with the table recognition means 53 for recognizing the composite table structure based on the positional relationship between the inner contours of the respective frame line areas extracted by the area extraction means 12 is provided, and the composite table is further created. A table dividing means 55 for dividing each table at the break is provided. The selection unit 8 is for selecting and instructing an image processing target table and its image processing contents from the tables divided from the composite table.

In such a structure, FIG.
Consider a case where a document image including the composite table 56 as shown in FIG. First, by performing the processing by the contour tracing means 9 and the character / figure determining means 10 as in the above-described embodiment, the outer contour 57 and a large number of inner contours 58 as shown in FIG. The figure contour is obtained as the determination result. Then, the contour inclusion relation determining means 11
Then, the inside of each inner contour 58 is extracted as the frame area E1 to E28 in the composite table 56 as shown in FIG. The frame line areas E1 to E28 thus extracted are input to the table recognizing means 53, and representative points of the respective areas E1 to E28, for example, the center of gravity of the areas are extracted as shown by black dots in FIG. , Their X,
The structure of the composite table 56 is recognized from the positional relationship in the Y direction. From the recognition result, the structural break of the composite table 56 is recognized,
Recognize it as a divided part. In the example of FIG. 6D, one table 56a is configured by the frame line areas E1 to E16,
It can be seen that the frame areas E17 to E28 form another table 56b, and the divided portions are found. Therefore, in the table dividing means 55, the areas E13 to E16 and the areas E17 to E1 are
The composite table 56 is divided into two tables 56a and 56b with the boundary portion with 9 as the division portion. FIG. 6E shows the result of this division. Of course, in the illustrated example, the division result is intentionally shifted in order to make the division part easier to understand, but in reality, only the table structure information is divided.

The selection means 8 uses the extracted tables 56a and 56b.
The user is allowed to select which one of the areas is to be subjected to image processing and what kind of image processing should be performed. The image processing means 4 selects the table 56a selected based on such a user instruction.
Or, perform the selected image processing on the area of 56b,
The image is output to the image output means 5. In the same figure (f), hatching is applied to the area of the table 56a, and
An example of an output image in which the title portion of the area is subjected to recognition processing, and the title portion is italicized and shaded is shown.

Next, an embodiment of the present invention will be described with reference to FIGS. 17 to 19. In the above embodiment,
The composite table structure is analyzed and divided by using the representative points of the positional relationship between the frame line areas, but there is no change in each table structure and the line width of the boundary table frame is thickened to distinguish them. It is not effective in such cases. Therefore, in this embodiment,
This is a structure in which the line widths of the line segments that make up the composite table are recognized so that the composite table structure, that is, the breaks, can be recognized and divided.

Therefore, the area recognition means 54 of this embodiment is provided with a feature point extraction means 59 and a line width recognition means 60 in place of the table recognition means 53. Feature point extraction means 59
Is to extract, as a feature point of the contour, a point in which the contour direction of the inner contour of each frame area extracted by the area extracting unit 12 changes greatly. The line width recognizing means 60 recognizes the distance from the extracted feature point to the shortest feature point as the line width.

With such a structure, FIG.
As shown in FIG. 2, two tables 61a and 6 having no structural difference are shown.
Consider a case where a document image including the composite table 61 composed of 1b is read and input. Such an image includes a contour tracking means 9, a character / graphic determination means 10, and a contour inclusion relation determination means 1.
By going through the process of 1, the contour similar to the case of FIG. The contour line thus obtained is linearly approximated by the feature point extraction means 59 so as to fall within a predetermined error range to generate a contour vector, and the angle difference between the continuous contour vectors is larger than the threshold value. , And extract them as the feature points of the contour. The black circle points in FIG. 18B indicate the contour feature points.

The line width recognizing means 60 recognizes, as the line width, the distance between the extracted outline feature points and another feature point closest to a certain point. The arrow shown in FIG. 19 represents the distance recognized as the line width. Here, if the line connecting the feature points is horizontal, vertical, or close to it, the line is taken as the line width, and in the case of other diagonal lines, the diagonal line is set in the horizontal or vertical direction as indicated by the broken arrow. The projected object is the line width.

Further, the table dividing means 62 of this embodiment examines a portion where the obtained line width is larger than the others, and finds that portion in the composite table 61.
It is determined that the table is a divided portion and divided into each of the tables 61a and 61b.
18B shows the respective tables 61a and 61b in which the broken line is divided. The subsequent processing is the same as that of the above-mentioned embodiment.

Further, an embodiment of the invention described in claim 9 will be described with reference to FIGS. 20 and 21. In the present embodiment, in the case of a composite table in which each table is color-coded, its structure can be recognized and divided into each table. For this reason, in the present embodiment, first, the image input means 63 is supposed to optically read a color original image to obtain a black and white digital image (black and white binary image) and a color digital image. The contour tracking means 9, the character / graphic determination means 10, the contour inclusion relation determination means 11 and the area extraction means 12 are supposed to perform processing based on a black and white digital image in the image information from the image input means 63. Further, a color area determination means 64 for determining a color area from the color digital image obtained from the image input means 63 and the area information obtained from the area extraction means 12 is provided, and the area recognition means 65 is configured.

In such a structure, FIG.
Consider a case where a color original image including a composite table 66 made up of color-coded tables 66a and 66b (schematically shows different colors for different colors) is read and input. The read black and white digital image information and the read color digital image information are stored in the RAM 3, respectively. Of these, the contour tracking means 9, using the black and white digital image information,
By sequentially performing the processing by the character / graphic determination unit 10, the contour inclusion relation determination unit 11, and the region extraction unit 12, the frame line region information is extracted as in the case described above.

On the other hand, the color area determination means 64 uses the RAM 3 based on the frame area information extracted by the area extraction means 12.
The color distribution in the table area is checked by using the color digital image read from the table, and the portion where the color changes is determined to be the divided portion of the composite table 66. Therefore, the table dividing unit 67 of this embodiment divides the composite table 66 based on the divided region information output from the color region determining unit 64. As a result, the tables 66a and 66b are divided as shown by the broken lines in FIG. The subsequent processing is the same as that of the above-mentioned embodiment.

By the way, each processing method in the above-described embodiment will be described with reference to FIGS. First, the contour tracking method will be described. In this process, RAM3
Raster scan the input image inside to find the black pixel that starts tracking. Next, the contour pixels are traced counterclockwise from the tracking start pixel in the case of the outer contour line and clockwise in the case of the inner contour line, and when returning to the tracking start pixel again, the contour line of one black pixel set Tracking has ended. Such processing is repeated until there are no contour pixels for which tracking has not been completed. Whether the contour line is the outer contour line or the inner contour line can be discriminated by determining that the left side of the tracking start pixel (the pixel immediately before the raster scanning) is a white pixel, and the black contour is an inner contour line. .

The contour tracking method will be described in detail with reference to FIG. Here, as the direction of the contour line, FIG.
As shown in (4), the direction was set to 0 to 7 in 8 directions.
First, as shown in FIG. 9A, raster scanning is performed to search for a tracking start pixel. As the tracking start pixel, at least one pixel out of the eight pixels around the pixel (in each of the above directions 0 to 7) is a white pixel, and a pixel which has not been subjected to contour tracking corresponds. The tracking start pixel is found at the position (i1, j1), and the previous pixel at the time of raster scanning is a white pixel, so it is determined to be the outer contour line, and tracking is performed counterclockwise from this position (i1, j1). To start. Then to the left (direction 4)
Then, the neighboring pixels are examined counterclockwise from, and the direction of the first black pixel found is set as the direction of the contour line. Next, move the tracking center pixel to this found black pixel, and check the neighboring pixels counterclockwise from the direction of (previous contour direction -2),
This is repeated until the tracking start pixel is reached. As a result,
This means that the contour line can be traced as indicated by the arrow loop on the outer side of FIG.

Next, raster scanning is again performed from the position (i1, j1) to search for the next tracking start pixel. The next tracking start pixel
Since it is found at the position (i2, j2) and the pixel immediately before the raster scanning is a black pixel, it is determined to be the inner contour line, and tracking is started clockwise from this position (i2, j2). Next, check the neighboring pixels clockwise from the lower direction (direction 6),
The direction of the black pixel immediately before the first white pixel found is the direction of the contour line. Then, the tracking center pixel is moved to this black pixel, the neighboring pixels are examined in the clockwise direction from the direction (previous contour direction + 2), and this is repeated until the tracking start pixel is reached. As a result, the contour line can be traced as shown by the inner arrow loop in FIG.

R is the tracing result as contour data.
Store in AM3. As shown in FIG. 16, the contour data is stored in the RAM 3 with the start position and length of the contour loop, and an identification flag for identifying the outer contour or the inner contour. FIG. 23
22 shows the contour tracing result in the case of FIG.

Next, the character / graphic determination will be described. Among the contour data obtained as the contour tracing result, X
Based on the size in the direction and the Y direction, it is determined whether the image inside the contour line is noise, characters, or a figure. Here, if the upper limit of the size of the noise image and the upper limit of the size of the character image are determined in advance and are set to L1 and L2, respectively, as shown in the flowchart of FIG.
When both are smaller than L1, noise image, length X, Y
Is larger than L1 and smaller than L2, it is determined to be a character image, and the others are determined to be graphic images. As the image determination data, the determination result is coded and registered in the order of FIG. 23 as shown in FIG.

It is to be noted that L1 ′ = L1 × R, L2 ′ = L2 × R (R is a scaling factor because accurate image determination cannot be performed during scaling reading unless the set values L1 and L2 are changed according to the scaling factor. ), And L1 ′ and L2 ′ are used instead of L1 and L2 at the time of determination.

A method of determining the contour inclusion relationship will be described. For example, in the case of FIG. 3, it is determined whether the inner contour is included in the outer contour, as shown in FIG. 26, the upper left point P1S of the smallest rectangular area including the outer contour.
And the lower right point P1E, the upper left point P of the smallest rectangular area of the inner contour
2S and the lower right point P2E, similarly, when the relationship between the upper left point P3S and the lower right point P3E of the smallest rectangular area of the inner contour is P1S ≦ P2S and P1E ≧ P2E, the inner contour 1 is included in the outer contour, and P1S When ≦ P3S and P1E ≧ P3E, it is determined that the inner contour 2 is included in the outer contour. As a result, in the example of FIG. 26, it is determined that the outer contour includes the area 1 indicated by the inner contour 1 and the area 2 indicated by the inner contour 2.

Next, the contour vectorization method will be described. The vectorization of the contour is performed by the contour chain code data (0 to 0 shown in FIG. 22B) obtained by the contour tracing process.
This is a process of replacing a continuous portion of inner values of the data represented by the direction code 7) with a longer vector while integrating so as not to exceed the allowable error range. As illustrated in FIG. 27, when a certain contour point is set as a start point and the end point of the vector is moved while tracing the contour chain code 48, the distance error between the contour point and the vector between them is within the allowable error d ₁ . Then, we can approximate the vector. By this processing, the digital noise of the contour can be absorbed and the data amount of the contour shape can be reduced.

Next, the feature point extraction method will be described.
The characteristic point is a point at which the angle difference between the continuous contour vectors 49 changes greatly. For example, as shown in FIG. 28, when the angle difference θ ₁ between a certain contour vector 49a and the contour vector 49b continuously connected thereto exceeds a preset threshold value, the connection point 49ab is the feature point. Is extracted as.

The image vectorization method will be described. As a method of vectorizing a binary line figure image, for example, the Institute of Electronics and Communication Engineers, Journal of April 1985, Vol. J68-D
No. 4 (p.845-852) and JP-A-62-2.
As shown in Japanese Patent Publication No. 86177, etc., a method may be used in which the center line of the line graphic image is traced, the center line is obtained, and the center line is approximated as a polygonal line vector. According to this method, line width data can be acquired at the same time when the image is vectorized.

Further, the vector correction method will be described. As shown in FIG. 29, a vector 50 that connects the start point of a certain vector 48a and the end point of a vector 48n that is n ahead of the vector and the end point of each of the vectors 48b, 48c, ... If the distance is equal to or less than the preset allowable error d ₂ , the vector 50 is set as the modified vector after approximation.

Also, when a line segment originally written horizontally or vertically is slightly inclined due to the way the document is placed at the time of reading, this is also corrected. For example, as shown in FIG. 30, if the vector 51 before correction is slightly deviated from the horizontal direction and the deviation angle θ ₂ is within the allowable range, the vector 5 is
1 is corrected in the horizontal direction to obtain a corrected vector 52.

[0067]

As described above, the present invention focuses on the fact that a frame line or a table frame that can be included in an original image can be replaced with a region specification by a marker pen. In the invention according to claim 1, contour tracing is performed. The area recognizing means including the means, the character / graphic determining means, the contour inclusion relationship determining means, and the area extracting means automatically extracts the frame line area as a candidate for selection from the original image. It suffices to select and specify the target area by the means, and the original is not contaminated without the need to specify the area with the marker pen.

At this time, according to the invention of claim 2,
Since the size of the frame area is used as the selection item for area selection and the area selected by the area size determination unit is specified later, even if there are many frame areas, the selection item selected by the selection unit is Therefore, the target area can be selected with reduced operability.

According to the third aspect of the present invention, since the image clearing means utilizing the vector system is provided, even if the frame line image is handwritten, the image processing required as the final output is performed. It is also possible to obtain an image in which the frame line is clearly written together with the image to which the mark is applied.

Further, according to the invention described in claim 4, since the table recognizing means is provided in the area recognizing means to recognize the table structure, only the image of the title area in the table is left and other than that. It becomes easy to cope with image processing suitable for a table structure such as deleting an image of a region. In particular,
According to the invention described in claim 5, since the table structure is recognized by using the contour vectorization method and the feature point extraction method, it is possible to apply to a complicated table such that the title part has a multi-stage structure. The range of application will be expanded. Further, also in the case of the invention according to claim 6, since the frame image of the table frame itself is vectorized, corrections such as integration are made to recognize the table structure. Also, at the same time, it is possible to reduce the amount of data and increase the processing speed by converting the frame line image itself into vector data. In addition, since the modified vector data is composed and drawn in the image data after image processing by the vector drawing means, it is possible to change the line width of the table frame and the line width of the table frame by handwriting. Is.

According to the seventh aspect of the invention, the area recognition means has a table recognition means for recognizing the structure of the composite table based on the vertical and horizontal lengths of the item areas constituting the table and the positional relationship of the center of gravity. Since the table dividing means divides each table based on the recognized table structure, any image in the composite table can be easily and accurately subjected to any image processing.

Further, in the case where there is little change in each table structure in the composite table structure and distinction is made by the line width, according to the invention of claim 8, the feature for extracting the feature points of the contour in the area recognition means. It has a point extracting means and a line width recognizing means for recognizing the line width of the line segment that composes the table based on the feature points, and regards the thick portion of the line width as a table frame = a break of the table and by the table dividing means. Since the table is divided, it is possible to easily and accurately perform arbitrary image processing on an arbitrary table in the simple structure composite table.

Further, in the case where each table of the composite table is color-coded, according to the invention of claim 9, a color distribution is performed using the extraction result of the area extraction means and the color digital image in the area determination means. Since the color area determination means for determining the area is provided and the portion where the color changes is divided by the table sentence and means as the break of the table, any image processing can be performed on any table in the composite table by color classification. Can be applied easily and accurately.

[Brief description of drawings]

FIG. 1 is a block diagram showing an embodiment of the invention described in claim 1.

FIG. 2 is a block diagram showing an overall configuration.

FIG. 3 is an explanatory diagram showing an example of area recognition / image processing in order.

FIG. 4 is a block diagram showing an embodiment of the invention described in claim 2.

FIG. 5 is an explanatory diagram showing an example of region recognition / image processing in order.

FIG. 6 is a block diagram showing an embodiment of the invention according to claim 3;

FIG. 7 is an explanatory diagram showing an example of region recognition / image processing in order.

FIG. 8 is a block diagram showing an embodiment of the invention described in claim 4.

FIG. 9 is an explanatory diagram showing an example of region recognition / image processing in order.

FIG. 10 is a block diagram showing an embodiment of the invention described in claim 5.

FIG. 11 is an explanatory diagram showing an example of region recognition / image processing in order.

FIG. 12 is an explanatory diagram showing a table structure recognition process.

FIG. 13 is a block diagram showing an embodiment of the invention described in claim 6;

FIG. 14 is an explanatory diagram sequentially showing an example of area recognition / image processing.

FIG. 15 is a block diagram showing an embodiment of the invention described in claim 7;

FIG. 16 is an explanatory diagram showing an example of region recognition / image processing in order.

FIG. 17 is a block diagram showing an embodiment of the invention described in claim 8;

FIG. 18 is an explanatory diagram sequentially showing an example of region recognition / image processing.

FIG. 19 is an explanatory diagram showing acquisition of line width information.

FIG. 20 is a block diagram showing an embodiment of the invention according to claim 9;

FIG. 21 is an explanatory diagram showing an example of region recognition / image processing in order.

FIG. 22 is a schematic diagram showing contour line tracking processing.

FIG. 23 is a RAM showing a storage state of contour line tracking processing results.
It is a map.

FIG. 24 is a flowchart showing a character / graphic determination process.

FIG. 25 is a RAM showing a storage state of character / graphic determination results.
It is a map.

FIG. 26 is a schematic diagram showing contour inclusion relation determination processing.

FIG. 27 is a schematic diagram showing contour vectorization processing.

FIG. 28 is an explanatory diagram showing a feature point extraction process.

FIG. 29 is a schematic diagram showing a vector correction process.

FIG. 30 is a schematic diagram showing a vector correction process.

[Explanation of symbols]

1 Image input means 3 storage means 4 Image processing means 5 Image output means 9 Contour tracking means 10 Character / figure determination means 11 Contour inclusion relation determining means 12 Area extraction means 13 Area recognition means 18 Area size determination means 20 Vectorization means 21 Vector correction means 22 Vector drawing means 23 Image erasing means 24 Image synthesizer 25 Image fair copy method 31 Table recognition means 35 Contour Vectorization Means 36 Feature Point Extraction Means 37 Table recognition means 38 Area recognition means 42 image vectorization means 43 Vector correction means 44 Table recognition means 45 Area recognition means 53 Table recognition means 54 Area recognition means 55 Table dividing means 56 composite table 59 Feature Point Extraction Means 60 Line width recognition means 61 Composite table 62 Table dividing means 63 Image input means 64 color region determination means 65 Area recognition means 66 composite table 67 Table dividing means

Claims (9)

[Claims] 1. A digital image obtained by optically reading a document image by image input means is temporarily stored in a storage means, and the stored input image is subjected to digital image processing by an image processing means to be output to an image output means. In the image processing apparatus adapted to output, the contour tracing means for tracing the contour line of the input image and outputting the image contour information, and the contour image of each image based on the image contour information, the image is a graphic image. Character / figure determining means for determining whether or not
A contour inclusion relation determining means for determining an inclusion relation between the outer contour and the inner contour of the determined graphic image and associating the outer contour and the inner contour with each other; and a region extracting means for extracting a frame line region based on the obtained inclusion relation. Area recognition means having
An image processing apparatus, comprising: a selection unit for selecting and instructing an image processing target area and image processing content from the extracted frame area. 2. A digital image obtained by optically reading a document image by the image inputting means is temporarily stored in the storing means, and the stored input image is subjected to digital image processing by the image processing means to be output to the image outputting means. In the image processing apparatus adapted to output, the contour tracing means for tracing the contour line of the input image and outputting the image contour information, and the contour image of each image based on the image contour information, the image is a graphic image. Character / figure determining means for determining whether or not
A contour inclusion relation determining means for determining an inclusion relation between the outer contour and the inner contour of the determined graphic image and associating the outer contour and the inner contour with each other; and a region extracting means for extracting a frame line region based on the obtained inclusion relation. Area recognition means having
A selection unit for selecting and instructing the size of the image processing target region and the image processing content from the extracted frame line region is provided, the size of the frame line region is obtained, and the image processing target region selected by the selection unit from the size. An image processing apparatus, comprising: an area size determining unit for determining. 3. Vectorizing means for vectorizing a frame image forming a frame area extracted by the area extracting means, vector modifying means for modifying the vectorized frame data, and modified vector data. Image drawing means for expanding the above into an output memory for the image output means, an image erasing means for erasing the original vectorized frame line image data from the storing means, image data after image processing by the image processing means and the vector. 3. The image clearing means having an image synthesizing means for synthesizing the frame line vector image created by the image drawing means is provided between the image processing means and the image output means. Image processing device. 4. A digital image obtained by optically reading a manuscript image by the image inputting means is temporarily stored in the storing means, and the stored input image is subjected to digital image processing by the image processing means to be output to the image outputting means. In the image processing apparatus adapted to output, the contour tracing means for tracing the contour line of the input image and outputting the image contour information, and the contour image of each image based on the image contour information, the image is a graphic image. Character / figure determining means for determining whether or not
A contour inclusion relation determining means for determining an inclusion relation between the outer contour and the inner contour of the determined graphic image and associating the outer contour and the inner contour with each other; and a region extracting means for extracting a frame line region based on the obtained inclusion relation. Area recognition means having table recognition means for recognizing a table structure based on the positional relationship between the extracted frame line areas is provided, and an image processing target area and image processing contents are selected and instructed from the recognized table structure. An image processing apparatus comprising a selection unit. 5. A digital image obtained by optically reading an original image by the image inputting means is temporarily stored in the storing means, and the stored input image is subjected to digital image processing by the image processing means to be output to the image outputting means. In the image processing apparatus adapted to output, the contour tracing means for tracing the contour line of the input image and outputting the image contour information, and the contour image of each image based on the image contour information, the image is a graphic image. Character / figure determining means for determining whether or not
Contour vectorization means for vectorizing the contour data of the determined graphic image, feature point extraction means for extracting points where the continuity of the vectorized contour vector changes as feature points of the contour, and the contour vector and extraction Area recognition means having a table recognition means for recognizing a table structure based on the recognized feature points, and selection means for selecting and instructing an image processing target area and image processing contents from the recognized table structure are provided. An image processing device characterized by: 6. A digital image obtained by optically reading an original image by the image inputting means is temporarily stored in the storing means, and the stored input image is subjected to digital image processing by the image processing means to be output to the image outputting means. In the image processing apparatus adapted to output, the contour tracing means for tracing the contour line of the input image and outputting the image contour information, and the contour image of each image based on the image contour information, the image is a graphic image. Character / figure determining means for determining whether or not
Area recognition means having image vectorization means for vectorizing the determined graphic image, vector modification means for modifying the vectorized vector data, and table recognition means for recognizing the table structure based on the modified vector data. And a selection means for selecting and instructing an image processing target area and image processing contents from the recognized table structure, and vector data corrected by the vector correction means in the image data after image processing by the image processing means. An image processing apparatus characterized by comprising vector drawing means for synthesizing and drawing. 7. A digital image obtained by optically reading a document image by the image inputting means is temporarily stored in the storing means, and the stored input image is subjected to digital image processing by the image processing means to be output to the image outputting means. In the image processing apparatus adapted to output, the contour tracing means for tracing the contour line of the input image and outputting the image contour information, and the contour image of each image based on the image contour information, the image is a graphic image. Character / figure determining means for determining whether or not
A contour inclusion relation determining means for determining an inclusion relation between the outer contour and the inner contour of the determined graphic image and associating the outer contour and the inner contour with each other; and a region extracting means for extracting a frame line region based on the obtained inclusion relation. Table dividing means for dividing the recognized composite table into respective tables by providing area recognition means having table recognition means for recognizing the composite table structure based on the positional relationship between the inner contours of the respective extracted frame areas. The image processing apparatus is provided with a selecting means for selecting and instructing an image processing target table and image processing contents from a table divided from the composite table. 8. A digital image obtained by optically reading an original image by the image inputting means is temporarily stored in the storing means, and the stored input image is subjected to digital image processing by the image processing means to be output to the image outputting means. In the image processing apparatus adapted to output, the contour tracing means for tracing the contour line of the input image and outputting the image contour information, and the contour image of each image based on the image contour information, the image is a graphic image. Character / figure determining means for determining whether or not
A contour inclusion relation determining means for determining an inclusion relation between the outer contour and the inner contour of the determined graphic image and associating the outer contour and the inner contour with each other; and a region extracting means for extracting a frame line region based on the obtained inclusion relation. , A feature point extracting means for extracting a point whose contour direction of the inside contour of each extracted frame area largely changes, as a feature point of the contour, and a distance from the extracted feature point to another feature point at the shortest distance With a line width recognition means for recognizing as a line width, a region recognition means for recognizing a composite table structure by recognizing a portion where the recognized line width is thicker than other line widths as a table frame, Table division means for dividing the composite table into each table based on the frame is provided, and selection means for selecting and instructing the image processing target table and the image processing content from the table divided from the composite table is provided. Image processing device. 9. An image input means for optically reading a color original image to obtain a black-and-white digital image and a color digital image. These read images are temporarily stored in the storage means, and the stored input image is imaged. In an image processing apparatus adapted to perform digital image processing by the processing means and output to the image output means, contour tracing means for tracing the contour line of the input image by the black-and-white digital image and outputting image contour information, and this image A character / graphic determining means for determining whether or not the image is a graphic image based on the size of the outline of each image based on the outline information, and an outer contour by determining an inclusion relation between the outer contour and the inner contour of the determined graphic image. The contour inclusion relationship determining means for associating the inner contour with the inner contour, the area extracting means for extracting the frame line area based on the obtained inclusion relationship, and the area extracting means. Area information extracted by the area extracting means and color area determining means for determining the color area by checking the color distribution of each extracted frame area based on the input image of the color digital image Area recognition means for recognizing the composite table structure based on the area information judged by the judgment means is provided, table division means for dividing the recognized composite table into respective tables is provided, and among the tables divided from the composite table An image processing apparatus comprising: a selection unit for instructing to select an image processing target table and image processing contents.