JPH06337937A - Picture processor - Google Patents

Abstract

PURPOSE:To provide a picture processor capable of efficiently extracting a frame line from picture data including the frame line, registering the frame line with small data volume and reproducing the frame line. CONSTITUTION:The frame line is extracted from the shown flow chart. The picture data are read out in the order of raster scanning (S1). The existence of a specific pattern for the frame line is judged. When the specific pattern does not exist, processing is returned to the S1 (S2). Whether a specific pattern for a start point exists or not is judged. When the specific pattern of the start point exists, the extracting/registering processing of the start point of the frame line is executed and then the processing is returned to the S1. When the start point does not exist, the processing goes to S5 (S3, S4). The existence of a specific pattern for a branch point is judged. When the branch point exists, the extracting/registering processing of the branch point of the frame line is executed and the processing is returned to the S1. When there is no branch point, the processing goes to S7 (S5, S6). Finally the extracting/registering processing of the end point of the frame line is executed (S7).

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus for processing image data including a frame line, and more particularly to a frame line extraction process,
The present invention relates to an image processing apparatus that performs a registration process of an extracted frame line, a deterioration correction process of the extracted frame line, and a process of extracting an arbitrary designated region of a document from a document region designated by the frame line.

[0002]

2. Description of the Related Art Functions such as detection of input / output positions of form processing and spreadsheet processing of personal computers and word processors, and extraction of only the original part of the original image specified by the frame line in a copying machine or only the frame line To achieve, (1) frame line extraction technology,
(2) A technique for registering the extracted frame line, (3) A technique for correcting deterioration of the extracted frame line, and (4) Extracting an arbitrary designated region of the document out of the document region designated by the frame line. Technology is required.

(1) The conventional frame line extraction technique is to extract the line segment of the entire frame line.

(2) As a conventional technique for registering the extracted frame line, a technique for registering the image data as it is is widely used, and in that case, the storage capacity becomes large. As a method to solve this, a method of registering the start point and end point of a registered image has been created.

(3) As a conventional deterioration correction technique for the line portion of the extracted frame line, a technique of using a chain code for line segment deterioration has been created.

(4) In the conventional technique for extracting an arbitrary designated area of a document from a document area designated by a frame line,
When extracting an arbitrary designated area of the original from the image data including the original and the frame, only the data of the frame is required separately from the image data including the original and the frame.

(5) In the conventional line segment deviation correction technique, a drawing to be processed is optically converted and input to the image processing apparatus. Noise removal, embedding of broken lines, and the like are performed based on the input line feature amount of the image to obtain a line feature amount image.
A line position table is obtained from the line feature amount image.

[0008]

[Problems to be Solved by the Invention]

(1) With the conventional frame line extraction technology, if the line segment is deteriorated even a little, it may not be possible to extract it, or there is a problem that processing time is required to correct the line segment each time. It was

(2) As the conventional technique of registering the extracted frame line, the technique of registering the start point / end point of the registered image is not suitable for registering the frame line data. Many appear and are not efficient.

(3) As a conventional technique for correcting the deterioration of the extracted frame line, a technique of using a chain code for the deterioration of the line segment first corrects the deterioration of the line segment to extract the line segment, and then the line segment is corrected. It has to be extracted and can take time.

(4) In the conventional technique for extracting an arbitrary designated area of a document from a document area designated by a frame line,
In addition to the manuscript and the image data including the frame line, only the frame line data is required, which is impractical from the viewpoint of convenience in use.

(5) In the conventional line segment shift correction technique, since the frame line is extracted after the correction, the processing time is increased depending on the quality of the line segment.

The present invention overcomes such problems and provides an image processing apparatus which efficiently extracts a frame line from image data including the frame line, registers the frame line with a small amount of data, and reproduces the frame line. The purpose is to do.

[0014]

An image processing apparatus of the present invention efficiently extracts a frame line from image data including the frame line,
An image processing device for reproducing frame line data, comprising frame line extracting means for extracting a specific pattern of the frame line from the image data,
A frame line registration unit that registers a frame line image using the specific pattern of the frame line extracted by the frame line extraction unit as registration data, and a frame line reproduction unit that reproduces the frame line image with a small amount of data. Characterize.

Further, a line part deterioration correction means for correcting the deterioration of the line part of the image including the frame line may be provided by the specific pattern of the frame line extracted by the frame line extraction means.

Further, the apparatus includes an original designated area extracting means for extracting an arbitrary designated area of the original from the original area designated by the frame line by extracting the frame line data from the image data including the original and the frame line. You may.

Further, a line segment deviation correction means for correcting the line segment deviation based on the specific pattern of the frame line extracted by the frame line extraction means may be provided.

[0018]

The frame line extracting means searches the image data including the frame line for a specific pattern of the frame line and extracts the frame line. The frame line registration means registers the specific pattern of the frame line extracted by the extraction means. The frame line reproducing means reads out the specific pattern of the registered frame line and reproduces the frame line. The line portion deterioration correction unit corrects the deterioration of the line portion of the image including the frame line. The document designated area extracting means extracts frame line data from the image data including the document and the frame line, thereby extracting an arbitrary designated region of the document out of the document region designated by the frame line. The line segment shift correction unit corrects the line segment shift based on the specific pattern of the frame line extracted by the frame line extraction unit.

[0019]

Embodiments of the present invention will now be described in detail with reference to the drawings.

FIG. 13 is a block diagram of an image processing apparatus according to an embodiment of the present invention. The image data including the frame line is stored in the image memory 136. When reading image data from the input device 134, a read command from the CPU 131 causes the input device 1 to pass through the system bus 137.
The image data read from 34 is once entered in the image memory 132 and stored in the image memory 136.

Each processing of this embodiment is executed by the CPU 131.
The contents of the image memory 136 are read and processed through the system bus 137. If the image data is the processing result, the CPU 131 to the system bus 13
It is again stored in the image memory 136 through 7. The image memory 136 has a sufficient capacity to store a plurality of image data.

The output device 135 is for displaying. When the display instruction is given from the CPU 131,
It is output to the image memory 133 through the system bus 137 and displayed on the display device 135. The display device 135 and the image memory 133 can be realized without the present invention. The pattern matching device 138 is used especially for pattern matching when extracting a specific pattern of a frame line. High-speed processing can be performed by adding this device. The calculation can be performed by the CPU 131 without this device. FIG. 13 shows an example for realizing the present invention, and other system configurations can be realized. The CPU extracts a frame line extraction process, a frame line registration process, a frame line reproduction process, a line segment deterioration correction process, an original designated area extraction process, and
The line segment shift correction processing is executed.

In the present embodiment, the frame line is extracted by not extracting all the line segments of the frame line but extracting a specific pattern of the frame line. Therefore, the frame line can be extracted without performing the correction process every time the line segment is deteriorated, which is a problem in the related art, and the processing time is shortened. The frame line registration process realizes registering the image data of the frame line with a small capacity by using the specific pattern extracted by the frame line extraction process as the frame line registration data.

The frame pattern in the image data always includes the specific pattern shown in FIG. Image data 1 of the frame line is shown by the diagonal line in the specific pattern of FIG.
It is 0. The image data 11 of the background is shown in white. In addition, it is possible to determine the start point, the midway point (branch point), and the end point of the specific pattern based on its shape. The center point of the extracted specific pattern is set as the coordinate value of the specific pattern.

The specific patterns 1, 2, and 3 represent the start points of the frame lines, and the specific patterns 4, 5, and 6 represent the end points,
In addition, the specific patterns 7, 8 and 9 are intermediate points (branch points)
Is represented. When data is read in the raster scan direction, the extraction order is specified pattern 1 → 7 → 4, specified pattern 2 → 8 → 5, specified pattern 3 respectively.
→ 9 → 6.

The specific pattern of the frame line is to arbitrarily set the size of the block by designating the thickness of the line.

FIG. 1 is a flow chart showing the frame line extraction processing of this embodiment.

First, in step S1, data is read in raster scan order from image data including a frame line.

Next, in step S2, it is determined whether the read data is a specific pattern of the frame line. If the read data is not the specific pattern, the process returns to step S1. If it is the specific pattern, the process proceeds to step S3. In step S3, it is determined whether the read data is the start point. If it is the starting point, the process proceeds to step S4, and if it is not the starting point, the process proceeds to step S5.

In step S4, the starting point of the frame line is registered.

In step S5, it is determined whether or not it is an intermediate point (branch point). If it is an intermediate point (branch point), step S
Go to 6. If it is not an intermediate point (branch point), the process proceeds to step S7.

In step S6, the midpoint (branch point) of the frame line is registered.

In step S7, the end point of the frame line is registered.

The above flow chart shows one frame line element in one line of image data including a frame line. When there are a plurality of frame line elements, it is necessary to search to the end of one line of this image data. Repeat the above work,
The specific pattern in the image data can be extracted by performing the process up to the final line of the image data including the frame line.

At the time of extraction, the frame line can be extracted regardless of deterioration of the frame line image itself other than the specific pattern.

In the above description, the specific pattern indicating the starting point is first extracted, but the specific pattern can be extracted from the midpoint (branch point).

FIG. 3 shows an example of frame image data. This data is composed of frame line image data 31 and background image data 32.

FIG. 4 explicitly shows the specific pattern of the frame line to be extracted in FIG. 3 of the frame line image data example. The pattern 41 is the specific pattern 1 or pattern 4 in FIG.
2 corresponds to the specific pattern 7 in FIG. 2, the pattern 43 corresponds to the specific pattern 7 in FIG. 2, and the pattern 44 corresponds to the specific pattern 4 in FIG.

From FIG. 4, the image data including the frame line is read in the raster scan order to search for the specific pattern.
First, the specific pattern 41 representing the starting point of the frame line is extracted. Register the coordinates of the extracted starting point. Image data including frame lines are read out in order, and the middle point (branch point)
Alternatively, the end point pattern is extracted. In the example of the figure, the midpoint (branch point) 42 is extracted. Register the extracted waypoint (branch point). Similarly, another waypoint (branch point) 43
And the end point 44 are extracted and registered. When the end point 44 is extracted, the extraction of one line segment of the frame line is completed. In this way, the specific pattern of the frame line in FIG. 3 is extracted as shown in FIG.

FIG. 5 is a pattern representing the straight line of the frame line. It appears when the image data including the frame line is read in order to extract the specific pattern of the frame line. In the case of the present embodiment, the frame line can be extracted irrespective of the elements of FIG. 5, but when reading the image data and searching for the specific pattern, it is confirmed that it is the line segment of the frame line. Therefore, it may be read. However, since this data is unrelated to the extraction of the elements of the frame line, it can be seen that this data may be deteriorated and this extraction method is effective.

By the above method, the starting point, the middle point (branch point) and the ending point of the frame line can be obtained from the image data including the frame line. It is also easy to create a frame line image by connecting each point of the obtained frame line.

FIG. 6 is a flow chart showing the frame line registration processing for registering the frame line image of this embodiment.

In step S61, a specific pattern of the frame line is extracted from the image data including the frame line by the frame line extraction processing described above.

The center point of the specific pattern extracted in step S62 is registered as coordinates.

The extracted patterns correspond to the specific patterns 1 to 9 in FIG. By registering the specific pattern extracted as described above together with the data of the extracted coordinates, it is possible to register with a far smaller capacity than simply registering as the image data of the frame line.

To reproduce the registered frame line data, FIG.
Connect the specific patterns of each as follows. A specific pattern is drawn at the center point coordinates of each specific pattern, and the specific pattern 1 → 7 → 4, the specific pattern 3 → 9 → 6, and the specific pattern 2 are horizontally drawn from the central point of each specific pattern.
Connect a straight line between the pattern center points of → 8 → 5. Similarly, the center points of the specific patterns 1 → 3 → 2, the specific patterns 4 → 6 → 5, and the specific patterns 7 → 9 → 8 are connected by straight lines in the vertical direction from each specific pattern. By this process, contrary to the frame line extraction process, FIG. 3 to FIG. 3 can be created.

Images can be efficiently registered by the above processing.

The present embodiment is characterized in that the frame line is extracted by searching and extracting a specific pattern of the frame line from the image data containing the frame line. By this method, even if the line segment itself other than the specific pattern of the frame line data has image deterioration, the line segment can be extracted by detecting the specific pattern. Since only a specific pattern is extracted, it is not necessary to separately perform a process of determining whether a line segment or noise due to image deterioration or the like, so high-speed processing is possible. By using the specific pattern of the frame line extracted by the frame line extraction process as the data for frame line registration, it is possible to reproduce the frame line image with a smaller data amount than when registering the entire image data of the frame line. is there. In addition, since the coordinates of the specific pattern are extracted, it is easy to use it for data processing such as forms rather than the frame image as it is.

The line part deterioration correction process corrects the line segment data of the frame line from the specific pattern extracted by the frame line extraction process. Therefore, the line segment extraction can be performed without correcting the deterioration by the chain code, and the deterioration of the frame line data can be corrected, so that high-speed processing can be performed.

FIG. 7 is a flow chart showing a line part deterioration correction process for correcting a frame line having deterioration.

In step S71, the specific pattern of the frame line is extracted from the image data by the frame line extraction.

In step S72, the shape of the extracted specific pattern is determined, and the center points are connected by a straight line in the vertical and horizontal directions.

The process of connecting the specific pattern is the same as the process of reproducing the registered frame line data. By connecting with a straight line, the line segment of the frame line that has deteriorated can be corrected.

FIG. 8 explicitly shows a frame line having a deterioration and a specific pattern. The patterns 81, 82, 83, 86, 87, 88 are extracted by the frame line extraction processing. In order to correct the deteriorated image of FIG. 8, straight lines are connected between the center points of the specific patterns. The process of connecting is the same as the process of reproducing the registered frame line data. By performing this process, the deteriorated portions 84 and 85 in FIG. 8 can be corrected. The correction process can be performed by connecting the centers of the specific patterns with a straight line, or since the patterns of FIG. 5 are present between the specific patterns, the patterns are replaced with the patterns when the specific pattern of the frame line is searched. .

The frame line data can be corrected by the above processing.

Since the connection of the frame line data can be determined by the specific pattern of the frame line extracted by the frame line extraction processing,
Even if the frame itself other than the specific pattern has image deterioration, the frame line data can be corrected from the coordinates of the specific pattern. Further, since the correction is performed using the extracted specific pattern, it can be realized at a higher speed than the correction using the chain code or the like.

In the original designated area extraction processing, only the frame line is first extracted from the image data including the original document and the frame line, and the original data and the image data including the original document and the frame line are arithmetically processed. It is possible to extract an arbitrary designated area of the document.

FIG. 9 is a flow chart of the original designated area extraction processing for extracting an arbitrary designated area of the original from the original area designated by the frame line from the image data including the original and the frame line.

In step S91, a specific pattern of the frame line is extracted by the frame line extraction processing.

In step S92, a frame line image is created from the extracted specific pattern by the frame line reproduction processing described above.

In step S93, a logical operation is performed on the created frame image, the original image data of the original, and the image data including the frame.

In step S94, the image in the area not enclosed by the frame is erased to obtain the image data of only the original.

In step S95, a density histogram is calculated for the data of the extracted original only for each area surrounded by the specific pattern extracted in step S91.

In step S96, step S95
When the density histogram obtained in step 2 becomes equal to or larger than a value that is arbitrarily designated, the area is registered as an area in which a document is written. As the data to be registered, a specific pattern and its coordinates are registered.

FIG. 10 shows an example of image data including a document and a frame line. Original data 101 is included in the frame line data 102.

FIG. 11 shows the image data of the frame line obtained by the above processing from the image data shown in FIG.

FIG. 12 shows the image data shown in FIG. 10 and FIG.
It clearly shows the area 121 in which an arbitrary specified area of the original is extracted from the original area specified by the frame line obtained from the image data shown in FIG.

By the above processing, it is possible to extract an arbitrary designated area of the document designated by the frame line from the image data including the document and the frame line.

The frame line data can be corrected by the line portion deterioration correction process. Here, the correction method for deterioration has been described, but when there is a deviation in the line segment, the deviation is corrected for the extracted specific pattern. The line segment deviation correction processing for creating the frame line data corrected by using the specific pattern of the frame line including the deviation correction will be described below.

FIG. 14 is a flow chart showing the line segment deviation correction processing for correcting the deviation / deterioration of the frame line data and creating the frame line data by the specific pattern of the frame line data.
A specific pattern of the frame line is extracted from the image data including the frame line by the frame line extraction processing.

In step S141, if there is a deviation in the center coordinates of the extracted specific pattern, it is corrected.

In step S142, step S1
The specific patterns extracted in 41 are connected by a straight line.

FIG. 15 shows an example of extracting a specific pattern of a frame line. The patterns 151 to 154 are the extracted specific patterns, and the pattern 152 is the patterns 151 and 15
This is an example in which the positions are deviated from those of Nos. 3 and 154.

FIG. 16 is an example explicitly showing that a frame line image is created by adding a correction to the specific pattern of FIG. The patterns 151 to 154 are specific patterns of the frame line. The patterns 155 to 157 are straight lines connecting the specific patterns. The specific pattern of the pattern 152 is the pattern 15
It can be seen that the correction is made to the coordinates connected by the straight lines 1, 153 and 154. In this way, it is possible to correct the deviation by adding positional correction to the specific pattern of the frame line extracted with the deviation.

The horizontal and vertical positions of each specific pattern may be corrected by taking the average position of each specific pattern or by using the position with the highest frequency of appearance.

Even if the specific patterns are not arranged so as to be connected horizontally or vertically, if the specific patterns are connected by a straight line, there is a possibility that they are displaced as a whole. A method of performing coordinate conversion such as rotation on the frame line data is also available. When only one specific pattern is rotated and extracted, the coordinate conversion of the rotation of the specific pattern can be performed by referring to the positions of other specific patterns.

In order to create frame line data from the extracted specific patterns, the specific patterns shown in FIG. 2 are connected as follows. A specific pattern is drawn at the center point coordinates of each specific pattern, and the specific pattern 1 → 7 → 4 and the specific pattern 3 → in the horizontal direction from the central point of each specific pattern, respectively.
The pattern center points of 9 → 6 and the specific pattern 2 → 8 → 5 are connected by a straight line. Similarly, in the vertical direction from each specific pattern, a specific pattern 1 → 3 → 2, a specific pattern 4
A straight line is connected between the pattern center points of → 6 → 5 and the specific pattern 7 → 9 → 8. The above is a description of the positional deviation. When correcting deterioration such as line breakage, the frame line data may be simply created by the above method. By the line portion deterioration correction process, the figure in FIG. 8 can be corrected.

[0078]

According to the image processing apparatus of the present invention, the frame line extracting means for extracting the specific pattern of the frame line from the image data, and the frame line specific pattern extracted by the frame line extracting means as the registration data are used as the frame lines. Since a frame line registration means for registering an image and a frame line reproduction means for reproducing a frame line image with a small amount of data are provided, in frame line extraction, it is determined whether a line segment or noise due to reasons such as deterioration of the image. It is not necessary to separately perform, and high-speed processing is possible. In the frame line registration, the image data of the frame line can be registered with a small data amount.

Further, when a line part deterioration correction means for correcting the deterioration of the line part of the image including the frame line is provided by the specific pattern of the frame line extracted by the frame line extraction means, frame lines other than the specific pattern are provided. Even if the image itself deteriorates, the frame line data can be corrected from the coordinates of the specific pattern.

Further, the apparatus includes an original designated area extracting means for extracting an arbitrary designated area of the original from the original area designated by the frame line by extracting the frame line data from the image data including the original and the frame line. In this case, the process of extracting an arbitrary designated area of the original from the original area designated by the frame line can be performed at high speed.

Further, when the line segment deviation correcting means for correcting the line segment deviation by the specific pattern of the frame line extracted by the frame line extracting means is provided, the deviation correction is performed only for the extracted specific pattern. Since the frame line data is created based on the corrected and corrected specific pattern, high-speed processing can be performed regardless of the quality of the original image.

[Brief description of drawings]

FIG. 1 is a flowchart showing a method for extracting a frame line from image data including the frame line.

FIG. 2 is a specific pattern to be extracted from image data including a frame line.

FIG. 3 is an example of image data of a frame line.

FIG. 4 explicitly shows a specific pattern of a frame line to be extracted from the image data of the frame line.

FIG. 5 is a pattern representing a straight line of a frame line.

FIG. 6 is a flowchart for registering a frame image.

FIG. 7 is a flowchart showing a method for correcting deterioration of a frame line.

FIG. 8 is a diagram explicitly showing a frame line with deterioration and a specific pattern of the frame line.

FIG. 9 is a flowchart showing a method for extracting an arbitrary designated area of a document from a document area designated by a frame line from image data including a document and a frame line.

FIG. 10 is an example of image data including a document and a frame line.

FIG. 11 is image data of a frame line.

FIG. 12 explicitly shows an arbitrary designated area of an original among original areas designated by a frame line.

FIG. 13 is a system block diagram showing an embodiment of the present invention.

FIG. 14 is a flowchart showing a method of creating image data by performing correction such as deterioration / deviation of a frame line.

FIG. 15 is an example of a specific pattern of a frame line with a shift.

FIG. 16 is an example in which frame line data is created by correcting a specific pattern of a frame line having a shift.

[Explanation of symbols]

 1-9 Specific pattern 131 CPU 132, 133, 136 Image memory 134 Input device 135 Output device 137 System bus 138 Pattern matching device

Claims (4)

[Claims] 1. An image processing apparatus for efficiently extracting a frame line from image data including a frame line and reproducing the frame line data, wherein the frame line extracting means extracts a specific pattern of the frame line from the image data. A frame line registration unit that registers a frame line image using the specific pattern of the frame line extracted by the frame line extraction unit as registration data, and a frame line reproduction unit that reproduces the frame line image with a small amount of data. A characteristic image processing device. 2. A line portion deterioration correction unit for correcting deterioration of a line portion of an image including a frame line based on a specific pattern of the frame line extracted by the frame line extraction unit. The image processing device according to item 1. 3. An original designated area extracting means for extracting an arbitrary designated area of the original from the original area designated by the frame line by extracting the frame line data from the image data including the original and the frame line. The image processing apparatus according to claim 1, wherein: 4. The image processing apparatus according to claim 2, further comprising a line segment deviation correction unit that corrects the line segment deviation based on the specific pattern of the frame line extracted by the frame line extraction unit.