JPS6224382A - Method for recognizing handwritten character - Google Patents

Abstract

PURPOSE:To eliminate the need for special designation for types of input characters and also to improve the easy recognizing efficiency of handwritten characters, by using information which is less than a prescribed number of strokes and supplied in a prescribed area of an input area to recognize the types of input characters. CONSTITUTION:Strokes supplied onto an input tablet 1 by an input pen 2 are compared with the reference stroke stored previously in a template memory 4 through a stroke discriminating part 3. As a result, the strokes are sorted into a similar group and the number of input strokes are decided together with the types of input strokes used to specify the intended characters and the position information, etc. in combination with other input strokes. These decided factors are supplied to a character recognizing part 6. The part 6 compares those information with the character pattern information stored in a character dictionary memory 7. Then the types of characters are decided through a character type control part 70 and with reference to an input area discriminating part 5 in case the recognition is required for small letters. Thus it is possible to omit the special designation for types of input characters and also to improve the easy recognizing efficiency of handwritten characters.

Description

DETAILED DESCRIPTION OF THE INVENTION [Industrial Application Field] The present invention relates to a method for recognizing handwritten characters, for example, a method for recognizing handwritten characters including hiragana, katakana, and foreign characters.

[Prior art and its problems] In a conventional handwritten character recognition device, the character type of the input character is completely different from the handwritten character input area where the character is recognized every time it is input or every time the input character type is changed. Specify the input character type by pressing the character type specification key on the keyboard, or use a dedicated input provided in another specific area separate from the character input area on the handwritten character input area. The input character type was selected and specified by inputting to the character type specification area.

Therefore, when inputting characters that include foreign characters such as 11-kana, katakana, or alphaben, which have a mixture of different character types, such as uppercase and lowercase, the character type must be specified frequently. It is very troublesome for people who use handwritten character recognition devices, and it is extremely inconvenient to input characters, and there are many cases of erroneous input and re-input due to forgetting to specify or malfunctioning of the specifying means, which wastes a considerable amount of time. This had the disadvantage that they were forced to waste a lot of time.

On the other hand, a handwritten character recognition device has been proposed that uses means for handling all handwritten input character types in exactly the same mode and automatically distinguishing and recognizing the input character types.

However, because these devices simply write lowercase letters smaller, the recognition rate for distinguishing between uppercase and lowercase letters is low, and the recognition rate for distinguishing between uppercase and lowercase letters is low, and the recognition time for input characters is low. Also, since there are many erroneous recognitions, manual correction work after inputting also takes a long time.

For this reason, in addition to requiring a lot of input time for the user, it is essential to be constantly careful about misrecognition in order to be able to input with peace of mind, which has the major disadvantage of increasing psychological fatigue. .

[Object of the Invention] The present invention aims to eliminate the problems of the prior art described in 1. The present invention identifies the input character type based on input stroke information within a predetermined number of strokes input in a predetermined area within a handwritten character input area. , there is no need to specify the input character type,
Another object of the present invention is to provide a handwritten character recognition method that has a high recognition rate and facilitates handwritten input.

[Summary of the Invention] The above-mentioned object of the present invention is to provide an input area discrimination step for determining whether or not handwritten input has been performed within a predetermined area of the input area for one character (for example, the lower half of the input area), and one handwritten input. In addition to determining the type of each stroke and the relationship between each stroke, the number of strokes of -character character is determined by a predetermined number of strokes (
It includes a stroke determination process that determines whether the number is within 4 strokes (for example, 4 strokes) and a character type limit process that determines whether a lowercase letter exists or not. Among the character candidates that are preferred and recognized based on the information, for hiragana, katakana, and alphabet character types, the discrimination results in the character type restriction step, the results of determining the number of strokes for one character in the stroke discrimination step, and the results of the discrimination in the input area discrimination step. This is achieved by a handwritten character recognition method that determines the input character type based on the input area discrimination result.

[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 a handwritten character recognition device according to an embodiment of the present invention, in which 1 is an input tablet, 2 is an input pen for inputting handwriting onto the input tablet 1, and 3 is a process for executing a stroke discrimination step. 4 is a template memory. The sootloaf discriminator 3 compares the input strokes inputted on the input tablet l with the input strokes 2 with reference strokes stored in advance in the template memory 4, classifies them into one similar group, and classifies them into one similar group. The number of input strokes is determined together with the type of input strokes used to specify the characters intended in combination, the position information of the input strokes, etc.

Reference numeral 5 denotes an input area determination unit, which determines the position of a handwritten character input frame on the input tablet l and to which area of the character input frame, which will be described later, the input is to be made. 6 is a character recognition section,
7 is a character dictionary memory. Reference numeral 70 denotes a character type restriction unit that determines whether the character type includes lowercase letters.

The character recognition unit Q compares the input stroke information from the stroke discrimination unit 3 with the character pattern information held in the character dictionary memory 7, specifies the input character, and passes the input stroke information to the character type restriction unit 7.
0, and determines whether it is necessary to recognize "lowercase letters." For those that require "lowercase letters," the input region discriminator 5 determines the input character type by referring to the input region and performing character type identification processing, which will be described later. A character code corresponding to the determined and recognized character is generated and sent to the image converter 8. For example, the image converter 8 uses a built-in character font pattern ROM to
The character code is converted into a standard character pattern corresponding to the character code, sent to the character output device 9, and outputted from the character output device 9.

In addition, a plurality of character input frames are provided on the handwritten character input surface of the input tablet l, and the input user inputs characters to be input sequentially into the character input frames by writing them in sequence.

FIG. 2 shows an example of setting the input area within the character input frame by the input area determination unit 5.

As shown in FIG. 2, the character input frame 10 is divided into an area All which is an upper part area, an area B12 which is a lower part area, and
Area C13 which is the lower left 1/9 area of the character input frame lO
Three input areas are set, and the type of input character is specified depending on which of these three areas the input character is placed in, or over which area the input character is input.

Input character recognition processing including input character type identification processing in this embodiment will be described below with reference to the flowchart of FIG.

First, in step Sl, the non-stroke determining unit 3 checks whether there is a handwritten character stroke input on the input tablet 1 using the input bench 2, and if there is an input, in step S2, it refers to the template memory 4 and determines the input stroke. Identify. Then, in step S3, it is determined whether or not the handwritten input for one character has been completed, and if the handwritten input for one character has not been completed, the process returns to step S1, the stroke to be input subsequently is specified, and If the input of characters has been completed, the character recognition section 6 is notified of the completion of input, and the process advances from step S3 to step S4.

In step S4, the character recognition unit 6 recognizes the characters input by hand from the input strokes from the character dictionary memory 7 and the stroke determination unit 3, and identifies recognition candidates for the input characters. Then, in step S5, it is checked whether the recognized character type is a "kanji", and if it is a "kanji", the process proceeds to step S6, where a standard pattern of the "kanji" recognized by the 1-image converter 8 is generated and output to the 1-character output device 9. do. Then, the process returns to step 31 to prepare for the next input.

If the recognized character is not a "kanji" in step S5, that is,
If it is a "plain name" or "katakana" input, the process advances to step S7, and it is checked whether the number of strokes determined by the stroke discriminator 3 is equal to or less than "3'". If the number of input strokes is "3°' strokes or more," the process proceeds to step S8, where the recognized "flat name" or "katakana" input is treated as an input of the "capital" (regular character) type, and the process proceeds to step S6. Outputs the advance recognition character to the character output device.

In step S7, if the number of input strokes is within ``3'' strokes, the process proceeds to step S9, and in order to check whether it is necessary to recognize "lowercase letters", a character type restriction section having a right-hand character memory is used. 70, the necessity of recognizing "lowercase letters" is determined. In the case of a version that does not allow lowercase characters to be input, or when there is no need for recognition as "lowercase letters", the process proceeds to step S8, and the input characters are recognized as "uppercase letters".

If it is necessary to recognize it as a “lowercase letter”, step SIO
Then, processing is performed to identify whether the input character type is an uppercase character type or a lowercase character type. Specifically, this is performed by the processes listed below.

■The input is one stroke, and the input is only to the punctuation mark area of the character input box 10, that is, the area C shown in FIG.
Is it input only to 13?

■ Is the input only to the lower half area of the character input frame 10, that is, input only to the area B12? ■ The vertical size of the input character is (the vertical length and the vertical width of the character input frame 10)
't
Is the input within the horizontal length (horizontal @) ) x (0,4)?

An identification process is performed to determine whether or not all four conditions (1) to (4) are satisfied. The above conditions (■) and (■) have the effect of minimizing misperceptions when a character is intended to be written in capital letters but is mistakenly written in a slightly smaller size.

Then, in step Sll, it is checked whether or not all the processes in step 510 are satisfied. If all are satisfied, the process proceeds to step S12, the input character is identified as a "lower case" input, the input character is recognized, and then Proceed to step S6.

In addition, if all the requirements are not satisfied, please use the normal character type (uppercase type).
Then, the process proceeds to step S8, where the input character is identified as an "uppercase" input and the input character is recognized, and the process then proceeds to step S6.

By performing the recognition processing described above, in a sentence containing kanji and kana, it is possible to input these character types without specifying special character types for uppercase J input and lowercase input. A choice can be made.

In addition, in the above explanation, only the conditions of ``r people's stroke ≦ 3, input only to the lower half of the character input box 10'', the kana character ``
It is also possible to recognize "lowercase letter" input.

An example of input using the above method is shown in FIG. FIG. 4 shows an example in which "Nyuuryoku," is entered manually in the character input boxes 41 to 47.

As explained above, according to this embodiment, by simply inputting natural handwritten characters, "capital letters" in kana character input can be
It is possible to recognize the intended character type without special designation of the (regular character) type and the "lowercase character" type.

In addition, in the above explanation, the Japanese character "capital letter J"
Although we have explained an example of recognizing "lowercase letters", the recognition is not limited to this, and foreign characters such as the alphabetic alphabet /
It is also possible to recognize foreign characters such as .

In this case, the determination is made in step S7 in FIG.

If you change from determining whether it is within 3' strokes to determining whether or not it is within 4'' strokes, you can get the recognition output of ``lower case letters'' by inputting ``upper case letters''. can.

Therefore, regardless of whether it is a Japanese character or a foreign character, the intended character type can be recognized without reducing the recognition rate of handwritten human characters.

[Effects of the Invention] As explained above, according to the present invention, desired characters can be input naturally by handwriting, without needlessly inputting a character type specification key, etc. each time a different character type is input, or every time a different character type is entered It is possible to provide an easy-to-use handwritten character recognition device that can recognize various character types.

[Brief explanation of drawings]

FIG. 1 is a block diagram of a handwritten character recognition device according to an embodiment of the present invention, and FIG. 2 is a diagram showing an input frame for handwritten characters in this embodiment. FIG. 3 is a flowchart of handwritten character recognition processing in this embodiment, and FIG. 4 is a diagram showing an example of inputting handwritten characters into a character input frame in this embodiment. In the figure 1... input tablet, 2... input pen, 3...
...Stroke discrimination unit, 4...Template memory,
5... Input area discrimination unit, 6... Character recognition unit, 7...
-Character dictionary memory 70...Character type restriction section.

Claims (3)

[Claims] (1) An input area determination step that determines whether handwritten input is included in an input area for one character and is performed within a predetermined area specified by an area smaller than the input area, and the number of handwritten input strokes. a stroke determination step of determining whether or not the number of strokes is within a predetermined number of strokes; and a character type restriction step of determining whether or not the recognition candidate character of the input character is a character type that can exist. A handwritten character recognition method characterized in that an input character type is determined based on the determination result in the character type limiting step and the input area determination result in the input area determining step. (2) The handwritten character recognition method according to claim 1 or 2, characterized in that when the recognized character type is a Japanese character, the predetermined number of strokes is set to 3 strokes. (3) The handwritten character recognition method according to claim 1 or 2, characterized in that when the recognized character types include foreign characters, the predetermined number of strokes is set to 4 strokes.