JP2578767B2 - Image processing method - Google Patents

Description

Description: TECHNICAL FIELD The present invention relates to an image processing method for inputting image information of a character and recognizing the character of the input image information.

2. Description of the Related Art Conventionally, this type of character recognition apparatus has performed very complicated recognition processing, and it has taken time to perform the recognition, and the apparatus has been expensive.

FIG. 9 is a flowchart showing an example of a conventional character recognition process. In the figure, the characters on the paper P are photoelectrically converted and read (step S81), and converted into a binary character pattern of logic "1" and "0" (step S82). Then, the character pattern is subjected to preprocessing for making the subsequent recognition processing easy and reliable (step S8).
3). The pre-processing is a series of processing including, for example, a processing of removing noise caused by a black point or the like on the paper P and a processing of smoothing a peak or a void generated at a boundary between character lines. Next, a feature extraction process for extracting some feature information (information such as intersection points, branch points, loop numbers, stroke lengths, etc.) is performed (step S84). When the recognition target is diverse, this feature information also has a considerable number. When a single character candidate is selected according to the result of the feature extraction, the character candidate becomes a recognition output (step S85 → step S88). That is, there is no need for dictionary guidance. However, in many cases, a plurality of character candidates having the same feature information are selected, and a detailed identification process for selecting only one character is performed (step S85 → step S86). This detailed identification processing is generally called dictionary collation processing, and when the recognition target is diversified, it becomes considerably complicated and requires time for collation. When a matching match is obtained by this matching process, a specific character candidate is selected. In addition, if the result of this collation is not a match, an unrecognizable result is finally output (step S87 → step S88).

As described above, the conventional character recognition apparatus performs the above-described complicated recognition processing even when recognizing simple characters (characters that are easy to recognize) such as alphabets and numbers in order to recognize various characters. become. Therefore, the processing takes too much time, and the cost performance is remarkably reduced for some tasks.

[Problems to be Solved by the Invention] The present invention has been made in view of the above conventional example, and has as its object to provide an image processing method for recognizing characters faster than input image information.

[Means for Solving the Problems] In order to achieve the above object, the image processing method of the present invention includes the following steps. That is, image information of characters is input, the input image information is divided into predetermined regions, and the number of black pixels appearing on each line is counted for each of the divided regions, and the number of black pixels in each region is counted. Find the maximum value of the number of black pixels for each line in the above, further divide each of the divided areas into small areas, and move the stroke in each of the areas in the direction passing through all the small areas in the area. Searching, find the position of the first small area where the stroke was found in the area and the number of strokes found in the small area, the maximum value of the number of black pixels for each line in each area and By comparing the position of the first small area in the area where the stroke was searched and the number of strokes in the small area with standard feature information stored in advance, the sentence of the input image information is compared. And recognizes the.

[Operation] In this configuration, character image information is input, the input image information is divided into predetermined regions, and the number of black pixels appearing on each line is counted for each of the divided regions. Calculating the maximum value of the number of black pixels for each line in each area, further dividing each of the divided areas into small areas, and dividing the strokes in each area into all the small areas in the area. Searching in the direction passing through, the position of the first small area where the stroke was found in the area and the number of strokes found in the small area,
The maximum value of the number of black pixels for each line in each area, the position of the first small area in the area where the stroke was searched, and the number of strokes in the small area are stored in advance as standard feature information. By performing the comparison, the operation of recognizing the characters of the input image information is performed.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. FIG. 1 shows a mark / character recognition device (OM) according to an embodiment.
It is a block diagram of R). The mark / character recognition device according to the embodiment is a recognition device having a general-purpose function capable of performing general image processing in addition to recognition of a handwritten mark and the handwritten character according to the present embodiment. It can also be realized as a simple recognition device that recognizes only characters of a specific group.

In FIG. 1, reference numeral 1 denotes a reader which reads a document image such as a handwritten mark and a handwritten character and converts the image into an electric signal.
Auto feeder feeds the reading section of the reader, 2 is the reader 1
An optical disk for storing the image information and information of the recognition result of the mark and the character read in step 3 is a host computer for controlling the entire mark / character recognition device, and 4 is for inputting various control commands and unrecognizable characters. A keyboard 5 is a CRT display device (CRT) for displaying image information, mark and character recognition result information, other operation information, and the like, and 6 is a printout of mark and character recognition result information and other image information. It is a printer.

In the host computer 3, 50 is a central processing unit (for example, a micro computer MC68000 manufactured by Motorola) for executing various programs, 5
Reference numeral 1 denotes a ROM which stores standard feature information 51a for character recognition in addition to the character recognition processing program shown in FIG. Further, 52 is a CRT interface, 53 is a keyboard interface, 54 is an optical disk interface, 55 is a reader interface, 56 is a printer interface, 57 is a program execution process, and 57 is a character recognition process for reading program pattern and other characters. And a RAM 60 for storing feature extraction information necessary for the CPU 50.

In the RAM 57, reference numeral 571 denotes a character buffer for storing the read character pattern data, and 572 stores stroke length information of the character pattern extracted by counting the number of black pixels in the character pattern of the character buffer in the horizontal and vertical directions. Area 573 is an area for storing the number of strokes of the character pattern crossing the horizontal area (or line) counted on a predetermined horizontal area (or line) set on the character pattern, and 574 is an area for storing the predetermined horizontal area. An area for storing stroke position information of the character pattern that first crosses the horizontal area (or line) extracted on the area (or line), and an area 575 stores a mark code, a character code, and the like as a recognition result.

FIG. 2 is an external view of a mark / character recognition device having the configuration of FIG. In the figure, the same components as those in FIG. 1 are denoted by the same reference numerals. Reference numeral 8 denotes an interface cable connecting the reader 1 and the host computer 3, and reference numeral 9 denotes an interface cable connecting the printer 6 and the host computer 3.

 Next, the principle of character recognition by the present embodiment will be described.

FIG. 7 is a diagram showing the character forms of the alphabets and numerals to be recognized by the embodiment device. In the figure, the characters of the embodiment are composed of a combination of elements consisting of 16 segments. A typical character stroke composed of a combination of these elements is, for example, a full-length or half-length character stroke written in the upper, middle, or lower row of the horizontal (x) direction, and similarly, the left side of the vertical (y) direction. , A full-length or half-length character stroke written in the middle or right, and a full-length or half-length character stroke in the oblique direction. For example, the alphabet “A” is shown in the first row and first column of FIG. The stroke length of the character in the x direction is “long”, “long”, and “short” in order from the top. Although a "short" stroke length does not actually exist, as will be described later, for example, a vertically long character stroke is recognized as "short" when viewed in the horizontal direction. The stroke length in the y direction is “long”, “short”, and “long” in order from the left. 1 line 2
The column shows the alphabetic letter "B". Similarly, the stroke length in the x direction is “long” “half” in order from the top.
The stroke length in the y direction is “short”, “long”, and “long” in order from the left. Therefore, such a combination of stroke lengths is unique to each character, and the character can be easily identified based on this difference.

However, some characters cannot be distinguished only by extracting the stroke length features described above. For example, in the number “2” in the fifth row and the fourth column and the number “5” in the sixth row and the first column, the stroke length in the x direction is “long”, “long” and “long” from above, and the stroke length in the y direction is Since they are both "half", "short" and "half" from the left, they are indistinguishable. The same applies to the alphabetical character "P" in the third row and the fourth column and the alphabetical character "R" in the third row and the sixth column.

Therefore, the difference between these characters is determined by, for example, setting predetermined lines 1 and 2 in the horizontal direction on the character pattern as shown in FIG.
Line 1 or line 2 as viewed from the number of vertical strokes that cross
Characteristic extraction is performed on stroke position information indicating where the vertical stroke first crosses the. In this case, the number of strokes crossing the line 2 for "P" and "R" is one for "P" and two for "R". In the case of "2", the distance from the left end until crossing line 1 for the first time is long,
"5" is short. The reverse is true for line 2. By combining the above feature extraction, all the characters in FIG. 7 can be recognized.

Here, considering the problem of noise due to dust or the like on the paper, it is considered that the length of the character stroke does not affect the feature extraction even if a little dust is present. For each of the predetermined areas 1 to 6, a method is employed in which the number of black pixels is counted several times and the maximum value is obtained, and the maximum value is further set to a predetermined threshold level.
This is because x ₁ and x ₂ are binarized and roughly quantized into long, half, and short sections. On the other hand, if there is dust or the like inside the character pattern, there is a possibility that the number of strokes of the character is counted extra. Therefore, as shown in FIG. 6 (b), predetermined areas 7 and 8 are set in the horizontal direction on the character pattern, and the number of strokes is counted, for example, three times in the horizontal direction. The stroke number having the minimum value in the area is set as the stroke number. By doing so, the possibility of excessively counting the number of strokes due to the presence of noise such as dust can be reduced.

Further, using a line counting the minimum value of the number of strokes in the same area as above, the line is scanned from the base point at the left end of the character pattern, and the position of the stroke that first crosses the line is obtained. This is ternarized at the threshold levels d ₁ and d ₂ in FIG. 6 (b).
The line that counts the minimum value of the number of strokes is used because the line is considered to be unaffected by noise for the above-described reason. In the case of FIG. 6B, since the first character stroke is located at the base point, the information of the stroke occurrence position of both areas 7 and 8 is "1".
It is.

FIG. 3 is a flowchart of the character recognition processing procedure of the embodiment. In this process, characters on the sheet are read and 2
It is input after it has been value-processed and stored in the character buffer 571. In the binarization process, first, characters on the paper P are photoelectrically converted, for example, for each character. Here, as shown in FIG. 7, if 16-segment preprinting is performed using a dropout color having a high reflectance and characters are written on the segments, the subsequent recognition processing is easy. Next, the characters subjected to photoelectric conversion are further converted into binary patterns of "1" and "0". Thus, the character pattern stored in the character buffer 571 has a pattern size of 48 × 48 bits as shown in FIG.

In step S1, the number of black pixels in the x direction is first counted and stored in the RAM 57. For example, the first line in FIG. 4 constitutes a long stroke, and the number is 48.
The second line also constitutes a long stroke, and its number is 48. The third line crosses the long stroke twice in the y direction, and the number is four. Thus, the respective numbers up to the 48th line are counted and stored in the RAM 57. Next, similarly, the number of black pixels in the y direction is counted and stored in the RAM 57. The first and second rows in FIG. 4 constitute a long stroke, and the number of each is 48. The third column crosses the long stroke twice in the x direction, and the number is four. In step S2, the data stored in the RAM 57 is divided for each predetermined area, and the maximum value of each number is extracted. The predetermined area is, for example, areas 1, 2, and 3 divided into three in the vertical direction as shown in FIG. 5B, and FIG.
Areas 4, 5, and 6 divided into three in the horizontal direction as shown in FIG. Therefore, when the character "A" as shown in FIG. 5A is read, the maximum value of the area 1 is 48, the maximum value of the area 2 is 48, the maximum value of the area 3 is 4, and the maximum value of the area 4 is 48, the maximum value of the area 5 is 5, assuming that the noise at the center is counted, and the maximum value of the area 6 is 48. In step S4, the maximum value of each area is set to the slice levels x ₁ and x _{2 of} the number of pixels provided in the x-axis direction as shown in FIG. 5 (b) and y as shown in FIG. 5 (c).
It is ternary based on the slice levels y ₁ and y ₂ of the number of pixels provided in the axial direction. For example, in FIG.
Maximum number of black pixels 48 are quantized to "3" since it is x ₁ and x ₂ or more. Similarly, area 2 is "3" and area 3 is "1". Area 4 is “3”, area 5 is “1”, and area 6 is “3”. These values are stored in the area 572 and constitute a part of the feature extraction information.

In step S5, the number of character strokes crossing the predetermined areas 7 and 8 is counted. For the character "A" in FIG. 6B, the number of strokes crossing the area 7 is "2", and the number of strokes crossing the area 8 is also "2". Alternatively, in step S5, the number of character strokes crossing line 1 and line 2 may be counted as shown in FIG. For the character "A" in FIG. 6A, the number of strokes crossing line 1 is "2" and the number of strokes crossing line 2 is also "2". Either way, Stes S6
Then, the counted number of strokes is stored in the area 573.

In step S7, the position of the character stroke that first crosses the predetermined areas 7 and 8 is detected. As for the letter "A" in FIG. 6 (b), the stroke position across the region 7 to the first value located between the base point and d ₁ is "1". Area 8
The value of the stroke position that first crosses is also “1”. Alternatively, in step S7, the position of a character stroke that first crosses line 1 and line 2 may be detected as shown in FIG. 6 (a). As for the letter "A" in FIG. 6 (a), the stroke position across the line 1 for the first time there its value between the base point and d ₁ is "1". The value of the stroke position that first crosses line 2 is also “1”. Step S8
Then, the characteristic information of the obtained stroke position is stored in the area 574. By the way, as for the number "2", area 7
First crossing stroke position is its value since than d ₂ on the right side is "3".

The ten pieces of information obtained in this manner become a feature pattern extracted from one character. In step S9, the contents of the areas 572 to 574 are compared with the standard feature information 51a of the ROM 5. If a matching match is obtained in step S10, the corresponding character code is extracted from the ROM 5 in step S11 and stored in the code buffer 575.
If no match is obtained in step S10, the reject code is stored in the code buffer 575 in step S12.

The mark / character recognition apparatus of the embodiment reads a mark and a handwritten character written on a mark sheet as shown in FIG. 8, for example. A wide timing mark is printed in the first column of the mark sheet, and the apparatus determines the reading timing of the handwritten mark or the handwritten character by reading the timing mark. A keyword mark is printed on the first line. From the second line, a data field follows, where a data mark is entered. The handwritten letters are entered in the lower two lines. Handwritten characters do not necessarily need to be accurately entered in the preprinted segment, but doing so facilitates entry and increases recognition accuracy. The mark sheet may be used for registering a keyword of an electronic file system, inputting a facsimile telephone number, setting the number of copies of an image forming apparatus such as a copying machine, and setting a mode such as a reduction ratio.

[Effects of the Invention] As described above, according to the present invention, since the amount of feature information collated in the feature collation processing is small, the processing time is significantly reduced. Moreover, each feature information amount can be obtained by simple processing.

Also, the configuration in which the stroke length is represented by the maximum value of the number of black pixels counted for a predetermined area reduces the influence of dust, peaks, and voids in that area.

In addition, since the feature amount is specified by the number of strokes and the position of the first small area where the stroke is searched, character recognition that is resistant to pattern fluctuations can be performed.

 As described above, the accuracy of character recognition is improved.

[Brief description of the drawings]

FIG. 1 is a block diagram of a mark / character recognition device (OMR) of an embodiment, FIG. 2 is an external view of a mark / character recognition device having the configuration of FIG. 1, and FIG. 3 is a character recognition process of the embodiment. FIG. 4 is a diagram showing the bit size of the character pattern, FIGS. 5 (a) to 5 (c) are diagrams for explaining the detection of the stroke length of the character pattern, FIGS. 6 (a) and 6 (b) FIG. 7 is a diagram for explaining the detection of the number of vertical strokes and the stroke position of a character. FIG. 7 is a diagram showing a character form of alphabets and numerals to be recognized by the embodiment device. FIG. FIG. 9 is a flowchart showing an example of a conventional character recognition process. In the figure, 1 is a reader, 2 is an optical disk, 3 is a host computer, 4 is a keyboard, 5 is a CRT display device, 6 is a printer, 7 is an auto feeder.

Claims (1)

(57) [Claims] 1. Image information of a character is input, the input image information is divided into predetermined regions, and the number of black pixels appearing on each line is counted for each of the divided regions. Obtain the maximum value of the number of black pixels for each line in each area, further divide each of the divided areas into small areas, and pass the strokes in each area through all the small areas in the area. The position of the first small area in which the stroke is searched in the area and the number of strokes searched in the small area are obtained, and the number of black pixels for each line in each area is calculated. By comparing the maximum value and the position of the first small area in the area in which the stroke was searched and the number of strokes in the small area with standard feature information stored in advance, the input image information is obtained. Image processing method and recognizes the characters.