JPH0991376A - Image data input processing method and its device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To correct the slanting and zigzagging of input image data by correcting the tilt of image data in an area encircled with reference ruled lines according to a corresponding estimated tilt angle. SOLUTION: An area division processing block 101 divides image data inputted from a scanner or a FAX by the prescribed number of divisions. A tilt angle estimation processing block 102 detects lateral ruled lines and estimates the tilt angle of the detected ruled lines as to the respective image data areas divided by the area division processing block 101. A rotation center coordinate estimation processing block 103 calculates correction reference coordinates for correcting the slanting and zigzagging in two modes according to the estimated tilt angle of the reference lateral ruled lines detected from adjacent divided areas. A rotation correction processing block 104 performs correction processing on the basis of the processing mode decision result of the rotation center coordinate estimation processing block 103. Consequently, the slanting and meandering of the input image data can precisely be corrected.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a process of inputting a form or the like as image data from a scanner or a facsimile, and more particularly, by correcting inclination and meandering when inputting a form in which ruled line frames are arranged. BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image data input processing method and an apparatus for realizing high-precision cutting of character image data for character recognition.

[0002]

2. Description of the Related Art A character recognition technique for converting character image data input from a scanner or FAX into a character code that can be processed by a computer as text data is a useful technique for reducing manual character input operation. It is believed that.

In the character recognition technology, the basic processing is to identify which character the input character image data is, based on the similarity with the previously learned character pattern. Therefore, accurately cutting out the character area in the input image data is the first condition for performing character recognition with high accuracy.

Techniques for cutting out a character area are roughly classified into two methods. The first method is a method in which information on character positions (format information) is defined in advance and character cutting is performed according to this format definition information. The second method is a method of cutting out an arbitrarily arranged character area without using any format information.

Of these methods, the second method is an ideal method as a final goal, but there are many problems that are technically difficult to solve. Therefore, a character cutting method based on the first method has been devised. .

[0006] In the first method using the format definition information,
It is important to identify which form the input form image data has, or to determine whether the form image data matches the predefined form.

Conventionally, for these reasons, a method of printing an identification mark on a form has been used. However, there are problems such as inefficient use of space on the form and a special technique for printing the mark. there were. Therefore, it has been considered effective to use a method of performing format identification by detecting a ruled line in a form without using a special identification mark.

[0008]

As described above, a method of using ruled lines in a form is promising for format identification for accurate character cut-out. However, in this method, the ruled lines in the reference vertical or horizontal direction are used. The condition is that the ruled line provided can be accurately detected. In general, image data input from a scanner or FAX is often inclined or meandering, and in this case, there is a problem that ruled lines cannot be detected correctly.

The present invention has been made in view of the above circumstances. An object of the present invention is to solve the above-mentioned problems in the prior art and to correct an inclination or meandering of input image data. A data input processing method and an apparatus therefor are provided.

[0010]

According to the present invention, in the process of inputting form image data in which ruled line frames are arranged, the sub-scanning direction is divided into one or more areas, and the longest horizontal ruled line is detected in each divided area. And the inclination angle of the horizontal ruled line is estimated, and this horizontal ruled line is used as a reference horizontal ruled line. When two adjacent reference horizontal ruled lines are not parallel, the reference horizontal ruled line is extended and the intersection point is defined as the center of rotation coordinates. Then, the process of horizontally correcting the position of the image data of the area sandwiched between these two reference horizontal ruled lines is repeated for all the divided areas, and two adjacent reference horizontal ruled lines are parallel to each other. In this case, the process of correcting the inclination of the image data of the area sandwiched by these two reference horizontal ruled lines based on the corresponding estimated inclination angle is repeated for all the divided areas.

According to the present invention, it is possible to accurately correct the inclination and meandering of the image data input from the scanner or FAX, and it is possible to perform the format identification based on the ruled line detection of the entry frame and the cutout of the character image data with high accuracy. Can be realized.

[0012]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a processing block diagram of an image data input processing method and apparatus according to an embodiment of the present invention.

In the figure, 101 is an area dividing processing block for dividing input image data, 102 is an inclination angle estimating processing block for detecting a horizontal ruled line included in each divided image data and estimating an inclination angle, and 103 is an adjacent division. A rotation center coordinate estimation processing block for calculating a rotation center coordinate when an intersection of these horizontal ruled lines, that is, a meandering of image data from the estimated inclination angle of the horizontal ruled line detected in the area, 104 is based on the rotation center coordinate. It is a rotation correction processing block that corrects the position of a pixel in image data.

The procedure for correcting the inclination and meandering of the input image data by these processing blocks will be described below. The area division processing block 101 divides image data input from a scanner or a FAX into a predetermined division number n. The dividing direction is a direction in which the dividing boundary is the main scanning direction (horizontal direction) of the image data. This division of the image data area is carried out for the purpose of detecting the horizontal ruled lines over the entire surface of the image data without any shortage, regardless of the length thereof.

That is, in the method of detecting horizontal ruled lines having a predetermined length or more for all regions without performing region division, for example, relatively long horizontal ruled lines are concentrated near the upper end of the image data and near the lower end of the image data. This is because, when relatively short horizontal ruled lines are concentrated on, only the horizontal ruled lines near the upper end are detected, and it is impossible to correctly estimate the inclination or meandering condition of the image data.

The inclination angle estimation processing block 102 detects horizontal ruled lines and estimates the inclination angle of the detected ruled lines for each image data area divided by the area division processing block 101. In detecting the horizontal ruled line and estimating the inclination angle, for example, the detection of the horizontal ruled line can be realized by a method of tracking black pixels continuous in a certain direction or detecting a peak of the black pixel distribution. Further, the inclination angle can be estimated by a method such as estimating the continuous direction of the detected horizontal ruled line or estimating a parallel line that maximizes the distance distribution to the black pixel.
Specific examples of these will be described later in detail with reference to FIG.

In the inclination angle estimation processing block 102, the maximum length horizontal ruled line in each divided area is selected, and finally the inclination angle of this maximum length horizontal ruled line is set as the estimated inclination angle.
In the following description, this selected horizontal ruled line will be referred to as a reference horizontal ruled line.

The rotation center coordinate estimation processing block 103 calculates corrected reference coordinates for correcting inclination and meandering in two processing modes according to the estimated inclination angle of the reference horizontal ruled line detected from the adjacent divided areas.

First, the first processing mode is a processing mode in which the reference horizontal ruled lines of two adjacent divided areas are parallel to each other. In this case, the rotation center coordinate estimation processing block 10
In No. 3, it is determined that the image data surrounded by the two reference horizontal ruled lines is simply inclined.

The second processing mode is a processing mode when the reference horizontal ruled lines of two adjacent divided areas are not parallel. In this case, the rotation center coordinate estimation processing block 10
In No. 3, it is determined that the image data surrounded by the two reference horizontal ruled lines meanders, and the coordinates of the intersection of the two reference horizontal ruled lines are calculated as the rotation center coordinates.

The rotation correction processing block 104 performs the following correction processing based on the processing mode determination result in the rotation center coordinate estimation processing block 103. First, when the image data between the reference horizontal ruled lines of interest is simply inclined, the inclination is corrected based on the estimated inclination angle. Although a description of a specific method of tilt correction is omitted here,
For example, it can be realized by a method of rotating the image data to be corrected around an arbitrary point by the estimated tilt angle in the direction opposite to the tilt.

If the image data between the reference horizontal ruled lines of interest meanders, the coordinates of each pixel in the correction target image data are centered on the rotation center coordinates estimated by the rotation center coordinate estimation processing block 103. The correction is performed by rotating in a direction opposite to the meandering, that is, the rotation of the pixel of the coordinate of interest, at a rotation angle determined by. The method of correcting the meandering will be described later in detail with reference to FIGS. 5 and 6.

FIG. 2 is a diagram for specifically explaining the pattern of the area division of the input image data performed by the area division processing block 101 shown in FIG. In FIG. 2, 201 shows the entire input image data.
Generally, input image data 2 input from FAX etc.
The horizontal direction of 01 is called the main scanning direction, and the vertical direction is called the sub scanning direction. N in FIG. 2 represents the number of divisions and is a numerical value that can be set arbitrarily. For example, by specifying a numerical value of about 4 to 10 as the value of n, it is possible to achieve the purpose of area division of detecting horizontal ruled lines from all areas of the input image data.

FIG. 3 is a sub-process block diagram for explaining the tilt angle estimation process block 102 shown in FIG. 1 in detail. In FIG. 3, 301 is a sub-processing block for detecting horizontal ruled lines, 302 is a sub-processing block for selecting the longest horizontal ruled line, 303 is a sub-processing block for extracting the coordinates of two points on the longest horizontal ruled line, 304 Is a sub-processing block for calculating the value of tan θ from the coordinates of two points on the longest horizontal ruled line.

An example of a specific method for estimating the tilt angle with respect to the division target area will be described below with reference to FIG. The horizontal ruled line detection sub-processing block 301 detects horizontal ruled lines included in the target divided area. Various methods can be used to detect the horizontal ruled lines. For example, a method of searching for black pixels continuous in a certain direction and using a continuous ruled line longer than a predetermined length as the horizontal ruled line, or a reference with various slopes is used. It can be realized by taking a distribution of the number of black pixels having the same vertical distance with respect to the ruled line and defining the portion showing the maximum pixel number distribution among these distributions as the horizontal ruled line.

In the sub processing block 302, the horizontal ruled line that is the longest in the direction of each detected ruled line is selected from the horizontal ruled lines detected in the sub processing block 301. In the sub processing block 303, the coordinates of any two points on the detected longest horizontal ruled line are extracted. This is a process for estimating the inclination angle of the straight line from two points on the straight line. In the sub processing block 304, the value of tan θ is calculated from the coordinates of the two points on the extracted longest horizontal ruled line. The value of tan θ has the same meaning as the tilt angle and is used for tilt correction and meandering correction later.

FIG. 4 is a diagram for explaining the principle of the rotation center coordinate estimation by the rotation center coordinate estimation processing block 103 shown in FIG. Note that FIG. 4 shows an example in which all the adjacent reference horizontal ruled lines are not parallel and the input image data meanders.

In FIG. 4, reference numerals 401 to 403 are reference horizontal ruled lines detected from the first to third divided areas, 404 and 405 are ruled lines 401 and 402, and ruled lines 402 and 403, respectively. The estimated rotation center point is shown. The correction target area 1 is the entire area from the extension of the reference horizontal ruled line 402 to the upper end of the input image data 201, and the correction target area 2 is the reference horizontal ruled lines 402 and 403.
It is the area surrounded by the extension line with. The method of setting the correction target area is the same when the input image data is simply inclined and when it is meandering.

As shown in FIG. 4, first, the rotation center point can be calculated as a point where the adjacent reference horizontal ruled lines are extended and intersect. If adjacent reference horizontal ruled lines are parallel and the correction target area is simply tilted, it can be considered that all the image data in the correction target area of interest are tilted at a uniform tilt angle. .

As for the correction target area, as shown in the example of FIG. 4, for the rotation center point 404, the area from the upper end of the input image data to the extension line of the reference horizontal ruled line 402 is the rotation center point 40.
For 5, an area surrounded by an extension of the reference horizontal ruled lines 402 and 403 is set.

FIG. 5 is a drawing for explaining a specific procedure of rotation correction by the rotation correction processing block 104 shown in FIG. In FIG. 5, reference numeral 501 is a sub-processing block that determines the sub-scanning direction address that is the reference for correction, 502 is a sub-processing block that determines the correction address, and 503 is a sub-processing block that moves the target black pixel to the corrected coordinates. is there. Note that FIG. 5 shows one rotation center point (origin O in FIG. 5).
The procedure example of the meandering correction based on n) is shown.

A specific procedure for rotation correction will be described below with reference to FIG. In the sub-processing block 501, the Y coordinate (Ey) of the pixel at the right end or the left end of the input image data on the straight line connecting the pixel to be corrected and the origin On is calculated. In the sub processing block 502, the coordinates (Ox, Oy) of the origin On and the coordinates (Px, P) of the pixel to be corrected are set.
y) and Ey, the coordinates after the meandering correction (Xc, Y
c) is calculated. The actual calculation formulas are, for example, formulas (1) and (2) when the origin On is on the right side of the input image data.
It is as follows.

Xc = Px + (Ox−Px) − ((Ox−Px) ² + (Oy−Py) ² ) ^1/2 Equation (1) Yc = Ey Equation (2) Calculation sub-processing In block 503, the pixel to be corrected is moved to the corrected coordinates.

FIG. 6 is a diagram for explaining the principle of the rotation correction shown in FIG. In FIG. 6, 601 is the origin On, 602
Shows the right end of the input image data, and 603 to 605 show examples of straight lines connecting the pixel to be corrected and the origin On. In FIG. 6, a diagram above the center arrow shows an example of pixels before correction, and a diagram below the center arrow shows an example of pixels after correction. Also, in the example of the pixel in the figure above the central arrow,
For simplification of description, description of pixels other than the pixels on the straight lines 603 and 604 and the rightmost pixel is omitted.

The procedure of rotation correction when the pixels on the straight line 603 are to be corrected will be described below. First, all the corrected Y coordinates of the pixels on the straight line 603 to be corrected are the Y coordinates of the points where the straight lines 602 and 603 intersect. The corrected X coordinate is calculated using the above equation (1).

In the example of FIG. 6, the pixels on the straight line 603 are corrected to the positions on the straight line 604. Pixels below the central arrow in FIG. 6 show the state of the corrected pixels when the processing corresponding to the correction of the pixels on the straight line 603 is repeated. That is, in the example of FIG. 6, the pixels existing on the extension of the straight line connecting the origin On and the pixels lined up in the vertical direction on the right end 602 of the image data are sequentially corrected, and the corrected pixels are accumulated. The meandering correction can be performed.

[0037]

As described above in detail, according to the present invention, the horizontal ruled lines included in the image data input from the scanner or the FAX are detected, the inclination angles of these horizontal ruled lines are estimated, and the meandering rotation is performed. Estimate the center coordinates,
From these estimation results, it is possible to realize the image data input processing method and device capable of accurately correcting the inclination and meandering of the input image data.

[Brief description of drawings]

FIG. 1 is a diagram illustrating a processing block of an image data input processing method and apparatus.

FIG. 2 is a diagram for specifically explaining a pattern of area division of input image data.

FIG. 3 is a diagram for explaining a tilt angle estimation processing block 102 in detail.

FIG. 4 is a diagram illustrating the principle of estimation of rotation center coordinates.

FIG. 5 is a diagram for explaining a specific procedure of rotation correction.

FIG. 6 is a diagram for explaining the principle of rotation correction.

[Explanation of symbols]

101 area division processing block 102 inclination angle estimation processing block 103 rotation center coordinate estimation processing block 104 rotation correction processing block 201 input image data 301 horizontal ruled line detection sub-processing block 302 sub-processing block for selecting the longest horizontal ruled line 303 on the longest horizontal ruled line Sub-processing block for extracting the coordinates of two points 304 Sub-processing block for calculating the value of tan θ 401-403 Detected reference horizontal ruled lines 404-405 Rotation center point 501 Sub-processing block for determining reference sub-scanning direction address 502 Correction target Sub-processing block 503 for determining correction coordinates in the main scanning / sub-scanning direction of a pixel Sub-processing block for moving pixels to correction coordinates 601 Rotation center point 602 Input image data right end 603 to 605 Origin On and input image data right end pixel Do it straight

Claims (2)

[Claims] 1. In a process of inputting form image data in which a ruled line frame is arranged, the sub-scanning direction is divided into one or more regions, and the longest horizontal ruled line is detected in each divided region and the inclination angle of the horizontal ruled line is determined. Estimate this horizontal ruled line as the reference horizontal ruled line, and if two adjacent reference horizontal ruled lines are not parallel, extend the reference horizontal ruled lines and set the intersecting point as the center of rotation coordinates, and use these two reference rules. The process of horizontally correcting the image data of the area sandwiched by the horizontal ruled lines with respect to the center of rotation coordinates is repeated for all the divided areas, and when two adjacent reference horizontal ruled lines are parallel, these two
An image data input processing method, wherein the process of correcting the inclination of image data in an area sandwiched by reference horizontal ruled lines of a book based on a corresponding estimated inclination angle is repeated for all divided areas. 2. A device for inputting form image data in which a ruled line frame is arranged, divides the sub-scanning direction into one or more areas, and detects the longest horizontal ruled line and the inclination angle of the horizontal ruled line in each divided area. If the means for estimating this horizontal ruled line as the reference horizontal ruled line and two adjacent reference horizontal ruled lines are not parallel to each other, extend the reference horizontal ruled line and set the intersecting point as the rotation center coordinate, and When the image data of the area sandwiched by the reference horizontal ruled lines of the book is horizontally corrected with respect to the rotation center coordinates for all the divided areas, and when two adjacent reference horizontal ruled lines are parallel to each other. These two
An image data input processing apparatus comprising: a unit that repeats a process of correcting inclination of image data in an area sandwiched by reference horizontal ruled lines of a book based on a corresponding estimated inclination angle for all divided areas.