JPH11232386A - Picture processing method and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve recognition precision of a ruled line and a character by deciding a thinned picture that is one of the features of an input picture and extracting a thinned area as a pre-processing of recognition processing of the ruled line and the character. SOLUTION: A dotted line element selection part 6 selects a rectangle of a dotted line element size out of rectangles extracted from a binary picture. A combination processing part 8 integrates dotted line elements and holds them in a ruled line memory 9. Dotted line elements that cannot be combined are counted (11) and, when there are more than a specified number of such dotted line elements, it is judged to be a thinned document, marked (12) and is stored in a document kind memory 13.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an image processing method and a recording medium having improved ruled line identification accuracy.

[0002]

2. Description of the Related Art As a method of recognizing dotted ruled lines constituting a table, there is, for example, a ruled line recognizing method described in JP-A-7-230525. According to this method, a rectangle having a predetermined threshold value or less is extracted as a dotted line element, and a rectangle obtained by integrating elements having an interval between the elements within a predetermined threshold value is extracted as a dotted ruled line. In addition, the validity of the ruled line is determined based on the respective variances of the size of the rectangle and the interval between the rectangles.

[0003] By the way, when the characteristics of the image to be processed are, for example, in a dark state or a faint state when recognizing a ruled line or a character, the algorithm or threshold value used in the recognition processing is not applicable. Otherwise, recognition accuracy may decrease. In addition, the image characteristics can be corrected by changing the binarization threshold when inputting with an input device such as a scanner, thereby correcting the density of the input image and obtaining image characteristics adapted to a recognition algorithm. It is.

[0004]

In the method described in the above-mentioned publication, when a rectangle extraction process is performed at a predetermined threshold, for example, a rectangle constituting a character is erroneously identified as a broken line component. May be extracted. Also, it is very troublesome to re-input an image because the binary data once input has characteristics that do not match the algorithm.

[0005] Therefore, if the characteristics of the processed image can be grasped and the characteristic information can be used as preprocessing of the ruled line and character recognition processing, it is possible to change to an algorithm or a threshold value corresponding to the information. And the recognition accuracy can be improved.

SUMMARY OF THE INVENTION The present invention has been made based on the above considerations, and an object of the present invention is to determine a faint image, which is one of the characteristics of an input image, as preprocessing of a ruled line or character recognition process. It is an object of the present invention to provide an image processing method and a recording medium in which the blurred area is extracted to improve the accuracy of identifying ruled lines and characters.

[0007]

In order to achieve the above object, according to the present invention, a rectangle of a black pixel continuous component is extracted from binarized image data, and a dotted line is drawn from the extracted rectangle. A rectangle corresponding to the element is extracted, and for the extracted dotted line element, the dotted line elements within a predetermined distance are combined, and as a result of the processing, the unconnected dotted line elements are counted. When the value is equal to or greater than the value, the image is determined to be a blurred image.

According to the second aspect of the present invention, a rectangle of a black pixel continuous component is extracted from the binarized image data, a rectangle corresponding to a dotted line element is extracted from the extracted rectangle, and the extracted dotted line is extracted. The method is characterized in that blurred areas are extracted from the image by combining dotted elements within a predetermined distance with respect to the elements and integrating unconnected dotted elements as a result of the processing.

According to the third aspect of the present invention, a rectangle of a continuous component of black pixels is extracted from the binarized image data, a rectangle corresponding to a dotted line element is extracted from the extracted rectangle, and the extracted dotted line is extracted. For the element, the dotted line elements within a predetermined distance are combined, and as a result of the processing, the uncombined dotted line elements are counted.When the counted value is equal to or more than a predetermined value, the image is a blurred image. It is characterized in that a blur region is extracted by integrating the uncombined dotted line elements with respect to the determined blurred image.

The invention according to claim 4 is characterized in that the dotted line existing in the blurred area is removed as a pseudo dotted line.

According to a fifth aspect of the present invention, when the size of the blurred image is equal to or larger than a predetermined value, a warning that the image is a blurred image is issued.

According to the present invention, a function of extracting a rectangle of a continuous component of black pixels from the binarized image data;
A function of extracting a rectangle corresponding to a dotted line element from the extracted rectangle, a function of combining dotted line elements within a predetermined distance with respect to the extracted dotted line element, A function of counting the dotted line elements, a function of determining that the image is a blurred image when the counted value is equal to or more than a predetermined value, and extracting a blurred area by integrating the unconnected dotted line elements. A function, a function of removing a dotted line existing in the blurred area as a pseudo dotted line, and a function of warning that the image is a blurred image when the size of the blurred image is a predetermined value or more to the computer. It is a computer-readable recording medium on which a program for realizing the program is recorded.

[0013]

DESCRIPTION OF THE PREFERRED EMBODIMENTS One embodiment of the present invention will be specifically described below with reference to the drawings. Before describing each embodiment of the present invention, first, terms used in the present invention will be defined. Rectangle: A continuous image or a continuous image portion (for example, a continuous black pixel portion or a continuous white pixel portion in the case of a binary image) which is continuous or more than a predetermined threshold in the image, and Is defined as a rectangle that is enclosed by a circumscribed rectangle so that is included in contact.

Rectangle extraction: Extracting the position coordinates of a rectangle is defined as rectangle extraction. Single element dotted line: A dotted line with one dotted element, that is, the same as a dotted element that could not be combined. Dotted line: This is obtained by combining dotted elements.

<Embodiment 1> When determining whether or not a blurred image is based on the binary input data, the features of the blurred image include:
The ruled lines and characters are blurred, resulting in discontinuity, and thus a large number of rectangles. By the way, even if the image includes dotted lines and halftone dots, the number of rectangles increases, and simply counting the number of rectangles makes it possible to determine whether the image is a blurred image or a clear image including many dotted lines. Can not. Therefore, if the dotted line element rectangle and the blurred rectangle can be distinguished from each other, it can be determined that the image is a blurred image when the number of blurred rectangles is larger than a threshold value.

Therefore, in the first embodiment, a rectangle that is discontinuous due to blurring is distinguished from a dotted line element or a halftone dot rectangle by using the feature that the number of rectangles in the blurred image is large. Count the number,
It is determined whether the image is a blurred image based on the count value.

FIG. 1 shows the configuration of the first embodiment of the present invention.
FIG. 2 shows a processing flowchart of the first embodiment of the present invention. An image such as a document is input by a binary image input unit 1 such as a scanner and stored in a binary image memory 2 (step 101). The rectangle extraction unit 3 extracts a rectangle of a black pixel continuous component from the binary image memory 2 and stores it in the rectangle memory 4 (step 102).

The dotted line extracting section 5 comprises a dotted line element selecting section 6 and a dotted line element combining section 8. The dotted line element selecting section 6 selects a rectangle having a size corresponding to the dotted line element from the rectangles stored in the rectangular memory 4. The selected item is stored in the dotted line element memory 7 (step 103).

Subsequently, the dotted line element combination processing unit 8 combines the dotted line elements located within a certain value in the processing direction. That is, when combining the dotted line elements arranged in the horizontal direction, the dotted line elements existing within a certain value in the horizontal direction (processing direction) are combined. The combined and extracted dotted lines are stored in the ruled line memory 9 (steps 104 and 109). Also, the dotted line elements that have not been combined with two or more dotted line elements by the dotted line element combination processing unit 8 are stored in the ruled line memory 9 as single element dotted lines (steps 104 and 105).

The single element dotted line is a dotted line which could not be combined by the combining process of the dotted element, that is, a rectangle selected as a dotted element size by the dotted element selecting section 6, but not a dotted element rectangle. Judgment is made, and it is regarded as a blurred rectangle. Here, the number of single element dotted lines can be assumed to be the number of rectangles generated by blurring. The blurred document determination unit 10 determines a blurred document as follows. The blurred document determination unit 10 includes a counter 11 that counts a single element dotted line, a marking unit 12 that gives a marking to a blurred document, and a document type memory 13.

As a result of counting the single element dotted lines by the counter 11 (step 106), if the number of single element dotted lines is equal to or more than a predetermined number, the image being processed is determined to be a blurred image (steps 107 and 108) and marking is performed. The unit 12 stores the input image in the document type memory 13 with information indicating that the input image is a blurred image.

<Embodiment 2> In the above-described embodiment 1, information on which part of the image is blurred in the image determined to be a blurred image cannot be obtained. If the blurred area in the image is known, it is possible to provide effective information for subsequent processing, for example, processing for executing blur correction processing on the extracted blurred area.

Therefore, the present embodiment is an embodiment in which a faint region in an image is extracted to give information effective for other processing.

FIG. 3 shows a configuration of a second embodiment of the present invention.
FIG. 4 shows a processing flowchart of the second embodiment of the present invention. The configurations up to the dotted line element combination processing unit 28 and the ruled line memory 29 are the same as in the first embodiment. In the present embodiment, a blurred area extraction processing unit 30 including a blurred area integrating unit 32 and a blurred area memory 3
3 is provided.

The single element dotted line combining unit 31 combines the single element dotted lines held in the ruled line memory 29 with the single element dotted lines located within a predetermined range to thereby reduce the size of the single element dotted line. A blur area is formed (steps 205 and 20).
6) Furthermore, the blurred area is extracted by causing the blurred area integrating unit 32 to grow the small blurred areas in the same manner (step 207).

FIGS. 5, 6, and 7 are diagrams for explaining generation of a blurred area. In FIGS. 5, 6, and 7, A, B, and C are single element dotted lines, and are dotted elements that could not be combined with two or more dotted elements. First, assuming that A in FIG. 5 is a processing reference, a range extended by an arbitrary value (width) in the vertical and horizontal directions around A is defined as A, and the range A is a processing range to be combined with A. FIG.
Since B exists in the processing range of A, A and B are combined to form a small fading area α as shown in FIG.

After the small blurred area is extracted, a connection range A is set based on the small blurred area α as shown in FIG. Since C exists in this set coupling range, when C is combined with a small blur area in the same manner as described above, a small blur area α is formed as shown in FIG.
Such processing is repeated until there is no single element dotted line in the connection range. When there is no single element dotted line in the combined range, the small blurred area extraction processing based on A is completed.

The single element dotted line combining section 31 executes the above processing for all the single element dotted lines. The extracted small blurred area is held in the blurred area memory 33. Next, the blurred area integration section 32 connects the single element dotted line connection section 3.
The integration process is performed on the small blurred area generated in step 1. Based on the small blurred area data held in the blurred area memory 33, the small blurred areas are combined with each other in the same manner as in the processing of the combining unit 31. That is, a process is performed in which the combining process of the single element dotted line in the combining unit 31 is replaced with a small fading region. Here, the integrated blurred area is held in the blurred area memory 33 again.

<Embodiment 3> When the blurred area processing of the embodiment 2 is executed for all images, it takes a long processing time. Therefore, the present embodiment is an embodiment in which the blurred area extraction processing of the second embodiment is executed only on the image determined to be the blurred image in the first embodiment, and the processing time is reduced.

FIG. 8 shows the configuration of the third embodiment. FIG. 9 shows a processing flowchart of the third embodiment. Example 3
Is a combination of the configurations of the first and second embodiments. That is, since the type of the image being processed is held in the document type memory 48 by the processing of the first embodiment, when the information that the image is blurred is obtained when the memory 48 is referred to (step 308), Example 2
A blurred area extraction process 49 is executed (step 30).
9).

Embodiment 4 In the dotted line extraction processing, a dotted line element size rectangle is extracted, and a dotted line is formed by combining the dotted line element rectangles located within the threshold value. However, a false dotted line is generated in a faint region in an image by erroneously combining discontinuous rectangles.

Therefore, in the present embodiment, the faint area in the image is extracted by a simple method, and the dotted line extracted in the faint area is removed from the dotted line information as a pseudo dotted line, thereby improving the accuracy of the dotted line recognition. This is an example of the embodiment.

FIG. 10 shows the configuration of the fourth embodiment, in which a pseudo-dotted line removing section 51 is further added to the configuration of the third embodiment, and the other components are the same as those of the third embodiment. FIG.
1 shows a processing flowchart of the fourth embodiment. Example 2
Is stored in the blurred area memory 50, and the dotted line extracted by the dotted line extracting unit 45 is stored in the ruled line memory 46.

The pseudo-dotted line removing section 51 compares the position coordinates of the dotted line in the ruled line memory 46 with the blurred region in the blurred region memory 50, and determines whether a dotted line (pseudo dotted line) or a blurred region existing in the blurred region exists. The touching dotted line (pseudo dotted line) is removed from the ruled line memory 46 (step 41).
0).

<Embodiment 5> In order to improve the accuracy of recognizing ruled lines and characters in an image in which the degree of blur is remarkable, a method of modifying the algorithm of the recognition process can be considered. It takes time.

Therefore, in the following embodiments 5 and 6, in order to cope with the problem of the blurred image, in the case of the image in which the number or the area of the blurred region extracted in the embodiment 2 is larger than the predetermined value, the user is required. On the other hand, a process of warning that the image is a blurred image is performed. The user inputs the image again for the image for which the warning has been issued, or corrects the image.

FIG. 12 shows the structure of the fifth embodiment. When referring to the document type memory 48 and obtaining information that the document is a blurred document, the blurred image warning unit 52 issues a warning that the image is a blurred image. For example, a warning is displayed on the display screen, or the user is notified by using a method of notifying by voice.

<Embodiment 6> FIG. 13 shows the structure of Embodiment 6. Since the blurred area extracted in the second embodiment is held in the blurred area memory 50, the blurred area area calculator 53 calculates the sum of the areas of the blurred areas from the blurred area memory 50 or the sum of the number of blurred areas. When the threshold value is exceeded, the blurred image warning unit 52 warns that the image is a blurred image, as in the fifth embodiment.

<Embodiment 7> FIG. 14 shows the configuration of Embodiment 7 and is an embodiment realized by software. When the present invention is realized by software, FIG.
1, a computer system including a CPU, a memory, a display device, a hard disk, a keyboard, a CD-ROM drive, a mouse, and the like is prepared. CD-RO
On a computer-readable recording medium such as M, a program for realizing the image processing function and the processing procedure of the present invention is recorded. Images such as documents to be processed are stored in, for example, a hard disk. Then, the CPU reads a program for realizing the above-described processing functions and processing procedures from the recording medium, determines whether the image read from the hard disk or the like is a blurred image, and outputs the determination result on a display or the like. I do.

[0040]

As described above, according to the first and sixth aspects of the present invention, whether or not an input image is blurred is determined as preprocessing for ruled lines and character recognition. Effective information can be given to improve the accuracy of recognition of ruled lines and characters as processing.

According to the second and sixth aspects of the present invention, the blurred area in the input image is extracted, so that the recognition accuracy of ruled lines and characters can be further improved by using the area information. It becomes possible.

According to the third and sixth aspects of the present invention, the processing time is shortened because the blurred area extraction processing is performed only on the image determined to be a blurred image.

According to the fourth aspect of the present invention, since the dotted line existing in the blurred area has a high probability of being a pseudo dotted line, the dotted line extracted in the blurred area is removed to remove the pseudo dotted line from the image. Thus, the accuracy of extracting dotted ruled lines is improved.

According to the fifth aspect of the present invention, it is possible to alert the user that the input image is a blurred image.
The user can execute an appropriate treatment on the blurred image.

[Brief description of the drawings]

FIG. 1 shows a configuration of a first exemplary embodiment of the present invention.

FIG. 2 shows a processing flowchart of Embodiment 1 of the present invention.

FIG. 3 shows a configuration of a second exemplary embodiment of the present invention.

FIG. 4 shows a processing flowchart according to a second embodiment of the present invention.

FIG. 5 is a first diagram for describing generation of a blurred area.

FIG. 6 is a second diagram illustrating the generation of a blurred area.

FIG. 7 is a third diagram for describing generation of a blurred area.

FIG. 8 shows a configuration of a third embodiment of the present invention.

FIG. 9 shows a processing flowchart of Embodiment 3 of the present invention.

FIG. 10 shows a configuration of a fourth embodiment of the present invention.

FIG. 11 shows a processing flowchart of a fourth embodiment of the present invention.

FIG. 12 shows a configuration of Embodiment 5 of the present invention.

FIG. 13 shows a configuration of Embodiment 6 of the present invention.

FIG. 14 shows a configuration of Embodiment 7 of the present invention.

[Explanation of symbols]

 Reference Signs List 1 Image input unit 2 Binary image memory 3 Rectangle extraction unit 4 Rectangle memory 5 Dotted line extraction unit 6 Dotted line element selection unit 7 Dotted line element memory 8 Combination processing unit 9 Ruled line memory 10 Blurred document determination unit 11 Counter 12 Marking unit 13 Document type memory

Claims (6)

[Claims] 1. A rectangle of a black pixel continuous component is extracted from binarized image data, a rectangle corresponding to a dotted line element is extracted from the extracted rectangle, and a predetermined distance is extracted from the extracted dotted line element. The combining process is performed on the dotted line elements that are within, as a result of the process, the uncombined dotted line elements are counted, and when the counted value is equal to or greater than a predetermined value, the image is determined to be a blurred image. Image processing method. 2. A rectangle of a continuous component of black pixels is extracted from the binarized image data, a rectangle corresponding to a dotted line element is extracted from the extracted rectangle, and a predetermined distance is extracted from the extracted dotted line element. An image processing method for extracting a blurred area from the image by combining the dotted line elements within the image and integrating the unconnected dotted line elements as a result of the processing. 3. A rectangle of a continuous component of black pixels is extracted from the binarized image data, a rectangle corresponding to a dotted line element is extracted from the extracted rectangle, and a predetermined distance is determined for the extracted dotted line element. The dotted line elements within are combined, and as a result of the processing, the uncombined dotted line elements are counted.When the counted value is equal to or more than a predetermined value, the image is determined to be a blurred image, and the determination is performed. An image processing method for extracting a blurred area by integrating the unconnected dotted line elements in the blurred image. 4. The image processing method according to claim 2, wherein a dotted line existing in the blurred area is removed as a pseudo dotted line. 5. The image processing method according to claim 1, wherein when the size of the blurred image is equal to or larger than a predetermined value, a warning is issued that the image is a blurred image. 6. A function of extracting a rectangle of a continuous component of black pixels from binarized image data, a function of extracting a rectangle corresponding to a dotted line element from the extracted rectangle, and a function of extracting a rectangle corresponding to a dotted line element. A function of combining dotted line elements within a predetermined distance, a function of counting dotted line elements that have not been combined as a result of the processing, and when the count value is equal to or greater than a predetermined value, the image is a blurred image. A function to determine that there is, a function to extract a blurred area by integrating the unconnected dotted line elements, a function to remove a dotted line existing in the blurred area as a pseudo dotted line, A computer-readable recording medium storing a program for causing a computer to realize a function of warning that the image is a blurred image when the size of the image is equal to or more than a predetermined value.