JPS62281092A - Pattern information recognition method - Google Patents

Abstract

PURPOSE:To correctly recognize a pattern in a very short time by deciding the central value of divided areas based on the maximum value of a balck density every divided area. CONSTITUTION:A reading pattern is divided into the respective prescribed areas 1-10 the maximum value of the number of the black density every line in the prescribed area is obtained and this value is stored in the area histogram buffer 23 of a RAM 57 as the central value of the area. Similarly, the average value of the black density every line of the prescribed area is obtained and this value is stored in the area histogram buffer 23 as the central value of said area. Then, one of the maximum values and the average values of the respective areas stored in the area histogram buffer 23 is selected, the selected value is multiplexed according to a set threshold to obtain the central value every area and stored in a central value buffer 25. Accordingly, the areas 1, 3, 5, 6, 8, 10, the maximum value is taken and in the areas 2, 4, 7, 9, the average value is taken, thereby, the influence of dusts or the like is eliminated.

Description

Detailed Description of the Invention 3. Detailed Description of the Invention [Industrial Application] The present invention relates to a pattern information recognition method for automatically reading and recognizing unknown characters such as alphabetic characters and numbers.

[Prior Art] FIG. 10 shows pattern information recognition processing of a conventional character recognition device of this type.

The characters on the manuscript paper P are read character by character and photoelectrically converted as shown in step S81, and this is further converted into a binary data pattern of °'1'' and 'O' in step S82.Subsequent steps In S83, pre-processing is performed to make the processing to be described later effective, that is, in step S82, 2
Based on the digitized pattern, a series of processes including noise processing such as black dots on paper P on which characters are recorded and smoothing of character/figure boundaries are performed. Next step S84
A feature extraction process is performed to extract several features (intersections, branch points, number of loops, stroke length information, etc.) necessary for character recognition. Depending on this extraction result, some characters with common characteristics are selected from a large number of literatures. Next, in step 385 and subsequent steps, dictionary collation processing and recognition processing are performed as identification processing for selecting a unique character from among the characters.

First, it is checked in step S85 whether or not it is possible to guide (search) the dictionary according to the extracted features. If the feature extracted here is not worthy of guiding a dictionary, the process advances to step 388, and unrecognizable is output. On the other hand, if dictionary guidance is possible based on the extracted feature points, step 38
In step 6, the prepared dictionary is searched and sequentially compared with the previously extracted features. If a match is found as a result of the comparison in step S87, the matching result is outputted as a recognition output in step S88. If a match cannot be found, it is output as unrecognizable.

[Problems to be solved by the invention] However, according to this conventional recognition method, simple characters (
Even in the case of only characters (characters that are easy to recognize), alphabets, and numbers, the above-mentioned complicated processing is performed, which has the drawback of taking too much processing time.

Further, the configuration for realizing the above processing is also complicated, and there are various problems in terms of increased cost and reliability.

[Means for Solving the Problems] The present invention has been made in view of the problems of the prior art described above, and includes the following configuration as a means for solving the above problems.

That is, a reading means for optically reading pattern information on a reading surface, an area dividing means for dividing the pattern information read by the means into predetermined areas, and a black area for each area divided by the area dividing means. The apparatus includes a detection means for detecting the amount of density, and a representative value determination means for determining a representative value of the divided area based on the maximum value of the black density detected by the detection means.

[Operation] In the above configuration, the pattern information read by the reading means is divided into predetermined regions by the dividing means, and the maximum value of the black density of each region divided by the dividing means is detected by the detecting means, The representative value determining means determines the representative value of the divided area based on the maximum value of the black density detected by the detecting means.

[Example] Hereinafter, an example according to the present invention will be described in detail with reference to the drawings.

FIG. 1 is a block diagram of one embodiment of the present invention.
2 is an optical disk that stores the image information read by the reader 1; 3 is a host computer that controls the entire embodiment; 4 is a keyboard; 5 is a A CRT displays image information, operation information, etc., and 6 is a printer that prints out the image information. Further, reference numeral 7 denotes an auto feeder that automatically feeds originals one by one to the original reading surface of the reader 1.

In the host computer 3, 50 is a CPU that controls the entire apparatus according to the control program shown in FIG. 4 stored in the ROM 51. The CPU 50 is preferably configured with a microcomputer MC68000 manufactured by Motorola, for example. 51 is a ROM;
51 includes a standard feature pattern storage area 51a.

52 is a CRT interface that controls the interface with the CRT 5; 53 is a keyboard interface that controls the interface with the keyboard 4; and 54 is an optical disk interface that controls the interface with the optical disk. Further, 55 is a reader interface that controls the interface with the reader 1, 56 is a printer interface that controls the interface with the printer 6, 57 is a RAM that stores the processing progress, the reading mark recognition process progress, etc., and 60 is each A bus that connects components.

A detailed storage area of the RAM 57 is shown in FIG.

In FIG. 2, 21 is a pattern buffer, 22 is a line histogram buffer, 23 is an area histogram buffer, and 24 is a read pattern.

FIG. 3 shows an external view of this embodiment having the above configuration.

In the figure, the same components as in FIG. 1 are given the same numbers. 8
9 is an interface cable between the reader 1 and the host computer 3, and 9 is an interface cable between the printer 6 and the host computer 3.

The operation of this embodiment having the above configuration will be explained below with reference to the flowchart of FIG.

In FIG. 4, as in FIG. 10, the process of reading and recognizing a pattern indicated by P on a document set in the reader 1 will be described as an example.

First, in step S1, the CPU 50 activates the reader 1 via the reader interface 55, scans the surface of the document to be read, and reads image data on the surface of the document.

On the manuscript surface, for example, a mark is placed at the bottom of the OMR sheet shown in FIG. 8, and a type pattern is painted on the mark as shown in FIG. 9. The OMR sheet is used for registering keywords in an electronic file system, inputting a telephone number for a facsimile, and setting modes such as the number of copies and reduction ratio of an image forming apparatus such as a copying machine.

If the format shown in FIG. 9 is fixed and a fixed pattern of characters is written on it, subsequent processing becomes easier. In addition, FIG. 9 shows standard patterns of °A°' to "z" and "1" to "o".

The basic pattern of the format in Figure 9 is 3 trees in the X direction,
Direction 3 The character ``田'' composed of wooden strophes and diagonal 2
It is part of the shape that combines the stroke "X" on the other side.

The case where one character, for example A', written at the mark position on the document surface written in this manner is read as an example will be described below.

The signal photoelectrically converted and read by the reader 1 in step S1 is sent to the reader interface 55 as shown in step S2, and the analog-to-digital converter built into the reader interface 55 converts the signal into 1°', "o°'".
is converted into a digital signal with a binary pattern, and the converted digital signal is input to the CPU 50.

The CPU 50 sequentially stores the thus input digital data in the pattern buffer 21 of the RAM 57. In this embodiment, the character pattern is divided into areas of 48 bits x 48 bits per character, and FIG. 5 shows an example of storing read data in the pattern buffer 21 when "A" is read.

In step S3, the CPU 50 calculates "1 degree" in each of the horizontal direction (X direction) and vertical direction (Y direction) for each line.
′ is counted. Specifically, as shown in FIG.
The number of black density of the line is “48°°, the 4th line is 4°°
Therefore, the number of black densities of the first line and the next line in the vertical direction (in the Y direction) is °'48, and the number of black densities for the third line is °°4. Then, the number of black densities obtained in step S4 is stored in the RAM.
57 line histogram buffer 22.

In the next step S5, the reading pattern shown in FIG.
It is divided into each predetermined area shown in 1 to 10 in FIG. 6(A). Figures 6(B) and 6(C) show the results of counting the number of black densities for each region in the form of bar graphs.

Subsequently, in step S6, the maximum value of the number of black densities for each line within the predetermined area obtained previously is obtained, and this value is stored in the area histogram buffer 23 of the RAM 57 as a representative value of the area. In area 1, the maximum number of black density is 4
8°°, and this 48° is stored in the area histogram buffer 23. Similarly, in step S7, find the average value of the number of black densities for each line in the predetermined area found earlier,
This value is stored as a representative value of the area in the area histogram buffer 23 of the RAM 57, similarly to step S6. Assuming that area 2 is from the 10th line to the 20th line, even if the dust shown in 61 in FIG. The amount of black density in the area is (8X10-)-2)
82 bits, and the average black density in area 2 is 8.2.
becomes.

Next, in step S8, a threshold level is set for each region divided in step S5.

For example, xl in the horizontal direction.

X2. The longitudinal odor of X3'C is 3/l, y2゜y3
Set each threshold level.

Each of these values can be set arbitrarily, but for example, each value is 1.
It may also be 6,32.48.

Next, in step S9, one of the maximum value and average value of each area stored in the area histogram buffer 23 is selected,
The selected value is multi-valued according to the threshold level set in step S8 to obtain a representative value for each region. Then, the obtained representative value is stored in the tl value buffer 25.

When the area is divided as shown in FIG. 6(A), the maximum value of the manually applied stroke (black density) in area 1 ranges from 0 bit to a maximum of 48 bits over the entire area.

On the other hand, for area 2, as shown in FIG.
Four types of stroke force for four frames can be considered. Similarly, areas 3 and 5 have a maximum of 48 bits, and area 4 is similar to area 2. Therefore, if the width of the frame of the manual stroke shown in Fig. 9 is 4 bits, the maximum value of the stroke in each region is 48 bits in the region 1.3°5 and 16 bits in the region 2.4. . Therefore, in areas 1, 3, 5, 6, 8°10, the maximum value, and area 2
, 4, and 7.9, by taking the average value, it is possible to obtain high accuracy with less influence of dust and the like.

The values of each area identified in this manner are converted into three values according to the threshold level set in step S8.

That is, when the representative value P is (Xl>P), 1°°, (X2
When <P <x3), it becomes "2°", and when (X3 <P), it becomes "°3". Here, in regions 1 to 5 shown in FIG. 6(A), the representative values of each region are "3", "1"', and "3" as shown in FIG. 6(B).

"1", "1°°", and in regions 6 to 10, the representative values of each region are "3", as shown in FIG. 6(C).
``1'', ``1'', ``1°'', ``3''. Therefore, each (-1 value) stored in the reading pattern is as shown in FIG. 7(A).

In the following step S10, the standard feature pattern 5 of the ROM 51 is
The standard pattern stored in 1a is matched with the read pattern stored in read pattern 24.

As a result, if a pattern match is obtained in step Sll, the matched pattern is recognized as a manual effort in step 312, and the result is output. On the other hand, if a match cannot be obtained, the process advances to step S13, where an unrecognizable message is output and the process ends. Then, the next pattern reading process is executed again.

The standard pattern of A° of the input standard feature pattern 51a is the pattern shown in FIG. 7(B), which matches the reading pattern shown in FIG. 7(A), and also in FIG.
Similar to FIG. 0, the process of reading and recognizing the pattern indicated by P on a document set in the reader 1 will be described as an example.

As explained above, according to this embodiment, the following effects can be considered in recognizing the character pattern shown in FIG. 5, for example.

■By using the maximum value of black density (stroke density) in a predetermined area as a representative value and converting this value into three values at a predetermined threshold level, reading of dust etc. that is erroneous reading in the area is removed. It includes the effect of doing. Therefore, even if there is dust in the area and the number of black densities in the line changes slightly, as shown in 61 in Figure 6 (A), this effect can be prevented and accurate character recognition is possible. Become.

■Furthermore, since the amount of data to be compared is small, the processing time is significantly reduced, and the pattern shown in Figure 7 (A) and Figure 7 (
Recognition is possible only by collating a small amount of data, the standard feature no\turn shown in B).

In this way, the drawbacks of the character recognition device in recognizing simple characters can be overcome, the processing time required for simple character recognition can be shortened, and character recognition can be performed at high speed and with high accuracy.

Furthermore, it is possible to recognize numbers in a fixed pattern (printed type) or letters of the alphabet at high speed and with high precision.

[Effects of the Invention] As explained above, the present invention can achieve
Moreover, accurate pattern recognition processing can be performed.

[Brief explanation of drawings]

Fig. 1 is a block diagram of an embodiment according to the present invention, Fig. 2 is a detailed configuration diagram of the RAM shown in Fig. 1, Fig. 3 is an external view of this embodiment, and Fig. 4 is a pattern of this embodiment. Recognition control flowchart. FIG. 5 is a diagram showing an example of storing read patterns in the pattern buffer of this embodiment. FIGS.
7 (A, ) are diagrams showing representative values of the reading pattern when reading "A" in this embodiment. FIG. 7 (B) is a diagram for explaining the recognition process for "A" in the standard feature pattern. Figure 8 shows the OMR sheet used in this example. Figure 9 shows the standard cover pattern used in this example. Figure 10 shows the conventional pattern recognition process. It is a flowchart showing the following.In the figure, 1...reader, 2...optical disk, 3...
・Host computer, 4...Keyboard, 5...
CRT, 6...Printer, 7...Auto feeder,
50 ・CPU, 51 ・ROM, 51 a =
Standard feature pattern storage area, 52... CRT interface, 53... Keyboard interface, 54.
... Optical disk interface, 55 ... League interface, 56 ... Printer interface, 57
...RAM, 60...bus. Patent applicant Canon Co., Ltd. (A) No. (B) Figure i Figure 10

Claims (2)

[Claims] (1) A reading process that optically reads the pattern information on the reading surface, an area dividing process that divides the read pattern information into predetermined areas following this process, and each area divided in the area dividing process. pattern information recognition comprising: a detection step of detecting the amount of black density; and a representative value determination step of determining a representative value of the divided area based on the maximum value of the black density detected in the detection step. Method. (2) The representative value determination step is a first step of selecting a representative value of the divided region based on the result of comparing the maximum value of the amount of black density for each region detected in the detection step with a plurality of different threshold levels. a second selection step of selecting a representative value of the divided region based on the result of comparing the average value of the amount of black density for each region detected in the selection step and the plurality of threshold levels; 2. The pattern information recognition method according to claim 1, further comprising a recognition step of recognizing a pattern based on the representative value selected in the second selection step or the first selection step.