JPS58225489A - Chinese character recognizing device - Google Patents

Abstract

PURPOSE:To obtain a sufficient rate of recognition by collating along the respective contour segment sequence obtained from KANJI (Chinese character) to be recognized with respective contour segment sequence read out of a dictionary. CONSTITUTION:An input character is inputted to a horizontal segment extracting circuit 12 and a vertical segment extracting circuit 13 to extract respective segments. Their outputs are passed through feature segment connecting circuits 14 and 15 and then inputted to decision making circuits 23-28 through a left contour segment sequence buffer 16, right contour segment sequence buffer 17, and center contour segment sequence buffer 18, and an upper contour segment sequence buffer 19, lower contour segment sequence buffer 20, and center contour segment sequence buffer 21 to be collated with contour segment sequences from the dictionary. A decision making circuit 29 recognizes the KANJI on the basis of the decision results of the decision making circuits 23-28.

Description

[Detailed Description of the Invention] Technical Field of the Invention The present invention uses a kanji recognition device, particularly when performing recognition processing for, for example, handwritten kanji, a series of line segments on the left, right, top, and bottom of a character outline. The present invention relates to a kanji recognition device that extracts the above-mentioned line segments and compares them along the series with a redundant series of the above-mentioned line segments stored in a dictionary.

(B) Technical Background and Problems The recognition process for kanji, especially for single handwritten kanji, is currently at a fairly difficult stage. As one such recognition process, a method is being considered that focuses on the background part of the kanji and makes a global judgment, but the two-dimensional characteristics of the background (or the space inside the character) are considered. If you try to capture this, the processing tends to become extremely complicated. For this reason, consideration has been given to focusing on the use of contour line segments, which has traditionally been applied to handwritten katakana.

(0) Purpose and Structure of the Invention The purpose of the present invention is to solve the above-mentioned problems. In a kanji recognition device that determines the category of the kanji character to be recognized by comparing the characteristics of the kanji character with the contents of a dictionary in which the characteristics are stored, the kanji character to be recognized is obtained by at least a search toward the left from a horizontal force. The left limb of the character, the right limb of the character obtained by searching horizontally from left to right, the character contour obtained by searching from top to bottom, and the character contour obtained by searching from bottom to top. Based on the above, there are a series of contour left line segments along the left ring of the character, a series of contour right line segments along the right ring of the character, a series of contour line segments that cut into the character contour, and the above. A series of line segments on the contour that follow the contour on the character are extracted, and each of the contour line segment series is stored in the dictionary with redundancy added to the series, so that the series of contour line segments that follow the contour of the character are stored in the dictionary, and The present invention is characterized in that each of the contour line segment series read out from the dictionary is compared with the contour line segment series read out from the dictionary. This will be explained below with reference to the drawings.

(Embodiment of the Paddy Invention Fig. 1 is an explanatory diagram for explaining the series of contour line segments according to the present invention, Fig. 2 is an explanatory diagram for explaining the series stored in the dictionary in the present invention, and Fig. 3 is an explanatory diagram for explaining the series of contour line segments according to the present invention. 1 shows a configuration of an embodiment of the invention.

Kanji 1 illustrated in Figure 1 (4) For example, the handwritten kanji ``Chi''
When given, scan 2 is performed in the direction of the arrow shown in the figure, and point A, which first reaches the black area from the left white area of the background, is extracted. 111
) Next, extract the point α that reaches the white area from the black area.

I) Next, extract the point B that reaches the black area from the white area.

Iv) Next, extract points that reach the white area from the black area.

V) Finally, extract the point n that reaches the right white area of the background from the black area.

Do it like this.

Then, for each point corresponding to the above-mentioned point A, the contour left line segments are connected in the vertical direction, for example, in Ll, L2, as shown in FIG. 1(B). Extract as follows. In addition, at this time, if the horizontal position of the point corresponding to the above-mentioned point A obtained corresponding to the two scans arranged above and below is heated by a threshold value or more, the line segment is considered to be discontinuous.

In addition, cases in which the start and end of each line segment are sealed by a black area of a character (black circles in the figure) and cases in which they are not sealed (white circles in the figure) are extracted separately.

Similarly to the above, the right line segment of the contour is created by connecting the points corresponding to the point n shown in FIG. 1, as shown in FIG.
Extract as follows. Of course, in this extraction, the scanning from the right side to the left direction may be slightly changed.

Furthermore, if necessary, in order to code the white area sandwiched by the stroke of the character, the point α shown in FIG.
The center point between and point B, the center point between point N and point N...
, and connect the center points of each of these in the vertical direction,
It is possible to extract the line segments in the contour according to the present invention, and to extract the series thereof.

The extracted contour left line segment L 1°L 2. as shown in FIG. 1(B). ...and contour right line segments R1, R2, ...
...K, as shown in FIG. 2(4), a contour left line segment series 4 and a contour line segment series 5 are created in the direction of the arrow 3. It goes without saying that this series represents the outline features of the kanji to be recognized 1.

In the case of the present invention, the contour line segment series obtained in this way is sequentially compared with the contour line segment series in the dictionary in the direction of arrow 36. The corresponding contour left line segment series 6 in the dictionary is shown. Illustrated code 7,
8 indicates that either is acceptable, codes 9 and 10 indicate abbreviation, and code 11 indicates the end point of the series. In series 6 in the dictionary, the reason for giving redundancy such as code 7.8 and code 9, 10 can be considered to be to cope with the deformation of characters.

The skirt and contour line segment series explained above using the contour left line segment series are, for example, (1) contour left line segment series, (11) contour line segment series, (town contour upper line segment series, (1v) Four types of line segment series on the contour are extracted.Four types of line segment series existing between character strokes are extracted. The streets are extracted, and the same matching as above is performed for each.

FIG. 3 shows the configuration of an embodiment of the present invention.

In the figure, reference numeral 12 is a horizontal line segment extraction circuit, 13 is a vertical line segment extraction circuit, and 14 and 15 are characteristic line segment series (i!
i! 1(B) is a concatenation circuit for obtaining a series such as line segments LL, L2, etc., 16 is a contour line segment series buffer, 1 and 7 are contour line segment series buffer, 18 is a line segment string buffer on the contour, 19 is a line segment series buffer on the contour, 20 is a line segment series buffer on the contour,
Reference numeral 21 represents a contour line segment series buffer, 22 a dictionary, 23 to 28 each a collation determination circuit, and 29 a determination circuit.

The illustrated characteristic line segment connection circuit 14 includes the line segments L1, L2, .・Song・YaR1,R2,...
Check the concatenation status of the respective buffers 16゜17
．． 18. The feature line segment connecting circuit 15 corresponds to vertical scanning and operates in the same manner as the circuit 14.

The contents of each buffer 16 to 21 are compared with each line segment series sequentially output from the dictionary 22 by matching determination circuits 23 to 28. In this case, arrow 3. You can think of it as being collated sequentially in the direction of .

The determination results from each of the collation determination circuits 23 to 28 are led to a determination circuit 29, which comprehensively examines them and determines the category of the kanji character to be recognized.

(lit) As described in detail, according to the present invention, a series of character outline segments can be used for recognition of handwritten kanji, etc.6゜1 It is easy to extract two-dimensional features of characters to be recognized. By preparing a dictionary with some redundancy, it is possible to obtain a sufficient recognition rate.

[Brief explanation of the drawing]

FIG. 1 is an explanatory diagram for explaining the series of contour line segments according to the present invention, FIG. 2 is an explanatory diagram for explaining the series stored in the dictionary according to the present invention, and FIG. 3 is an explanatory diagram for explaining the configuration of an embodiment of the present invention. shows. In the figure, 1 is a kanji to be recognized, 2 is a scanning line, 4, 5゜6 are contour line segment series, 12.13 are line segment extraction circuits, 14
．． Reference numeral 15 represents a line segment series concatenation circuit, 16 to 21 represent line segment series buffers, 22 represents a dictionary, 23 to 28 represent matching determination circuits, and 29 represents a determination circuit. Patent Applicant Fujitsu Ltd. Representative Patent Attorney Hiroshi Mori (1 other person)

Claims (1)

[Claims] The recognition is performed in a kanji recognition device that scans the kanji character to be recognized, extracts features, and determines the category of the kanji character to be recognized by comparing the characteristics with the contents of a dictionary that stores features corresponding to standard kanji characters. The target kanji character is at least the left contour of the character obtained by searching from the horizontal cloth to the left, the right limb of the character obtained by searching from the horizontal left to the right, and the right limb of the character obtained by searching from the top to the bottom. Based on the top contour of the character and the bottom contour of the character obtained by searching from the bottom to the top, a series of left contour line segments that follow the left contour of the character, and a right contour line segment that follows the right ring of the character. series, a series of line segments on the contour that follow the upper contour of the character, and a series of line segments on the contour that overflows the lower contour of the character, and in the dictionary, each contour line segment series is redundantly added to the series. Each contour line segment obtained from the recognition target kanji character, series 1 column j, and each contour line segment series read from the dictionary are stored in series. A kanji recognition device characterized in that it performs comparison.