KR101233424B1 - System for recognizing character and method thereof - Google Patents

Abstract

PURPOSE: A writing recognizing system and a writing recognizing method using the system are provided to increase the recognition accuracy of an inputted character and reduce recognition time by setting an input pattern of a user in advance. CONSTITUTION: A position calculating unit(12) calculates a touch position of a character inputted to a touch panel. A pattern recognizing unit(13) divides the touch panel into areas with X/Y axes and obtains first data formed on each area divided with an X axis in order of touches and second data formed on each area divided with an Y axis in order of the touches. The pattern recognizing unit obtains data about a slope pattern from the touch position of the character. A recognition control unit(15) confirms a recognition character corresponding to the data about the slope pattern and the first and the second data from sample data stored in a memory unit(14). [Reference numerals] (11) Touch panel; (12) Position calculating unit; (13) Pattern recognizing unit; (14) Memory unit; (15) Recognition control unit; (16) Display driver

Description

Handwriting Recognition System and Handwriting Recognition Method Using the Same {SYSTEM FOR RECOGNIZING CHARACTER AND METHOD THEREOF}

The present invention relates to a handwriting recognition system and a handwriting recognition method using the same, and more particularly, a handwriting recognition system and a handwriting recognition using the same to increase the recognition accuracy of a character input by a user and to reduce the time required for recognition. It is about a method.

In recent years, portable terminals have provided various functions and services such as chatting, photographing, multimedia data transmission, online games and the like in order to meet the needs of users. However, it is difficult to properly support various functions of a portable terminal by using a general user interface device based on a keypad.

That is, the user interface device based on the keypad has a complicated user interface structure, which deteriorates the user's convenience, and it is difficult to overcome the space limitation of the portable terminal which is getting smaller and smaller. On the other hand, in the case of a touch panel of a touch-type user interface for generating an input signal by touching a point on the screen, for example, a touch screen, a touch pad, etc., Minimizing the spatial constraints of the user interface and improving the user interface.

Therefore, a large number of portable terminals employ a touch type user interface, which includes a position sensor that outputs coordinate values of a contact surface when a point on the screen is touched. Here, the position sensor is applied with a technique such as a pressure-sensitive resistive film type, a capacitive type, a surface ultrasonic wave conduction type, and an infrared type. In particular, the touch-type user interface has an advantage in that character input is much easier. That is, the user interface of the touch-type allows the character input device such as a portable terminal to recognize a character even if the user simply writes a character on the touch input unit (e.g., a touch screen, etc.) Convenience.

However, in the case of recognizing a character input to the touch panel in the conventional touch type user interface, the recognition accuracy of the character input by the user is not high, and it takes a long time to recognize the character.

In order to solve the conventional problems as described above, the present invention to increase the recognition accuracy of the character input by the user, and to reduce the time required to recognize.

Other objects of the present invention will be readily understood through the following description of the embodiments.

In order to achieve the above object, according to an aspect of the present invention, an apparatus for recognizing a character written on the touch panel, the touch panel for inputting a character of the user; A position calculator for calculating a touch position of a character input to the touch panel; The touch panel is divided into a plurality of areas by the vertical X axis, and is divided into a plurality of areas by the horizontal Y axis, and is divided by the X axis from the touch position of the character calculated from the position calculator. Acquiring first data in the order of touching each divided area and second data in the order of touching each area divided by the Y axis, and obtaining data about an inclination pattern from the touch position of the character. Pattern recognition unit; A memory unit for storing in advance a sample data consisting of an order of touching each region divided by the X axis, an order of touching each region divided by the Y axis, and an inclination pattern for each character of a recognition range; And a recognition control unit which checks the recognition characters corresponding to the first and second data acquired by the pattern recognition unit and the data for the inclination pattern from the sample data stored in the memory unit and displays the recognition characters on the touch panel. A recognition system is provided.

According to another aspect of the present invention, in a method for recognizing a character written on a touch panel, the touch panel is divided into a plurality of areas by a vertical X axis and a plurality of areas by a horizontal Y axis. Splitting, acquiring first data in an order of touching each region divided by the X axis by a character input to the touch panel, and second data in an order of touching each region divided by the Y axis; A recognition character corresponding to the first and second data from sample data consisting of an order of touching each region divided by the X axis and an order of touching each region divided by the Y axis with respect to each character of a recognition range. Identifying first and second data; And a character display step of displaying, on the touch panel, a recognition character corresponding to the first and second data from the sample data.

In the first and second data checking steps, the touch panel is divided into a plurality of areas by a vertical X-axis, and the touch panels are touched for each area divided by the X-axis by a character input to the touch panel. A first data acquiring step of acquiring first data made; Second data for dividing the touch panel into a plurality of regions by a horizontal Y axis, and obtaining second data in an order of touching each region divided by the Y axis by a character input to the touch panel; Obtaining step; And a recognition character corresponding to the first and second data from sample data consisting of an order of touching each region divided by the X axis and an order of touching each region divided by the Y axis for each character in the recognition range. And a character checking step of finding a letter, wherein the letter is an English letter and a special character, wherein the X axis is made of one axis to divide the touch panel into two, and the Y axis is divided into three pieces. It may consist of two axes.

An error determination step of determining whether the first or second data is normally acquired after the second data obtaining step; And an initializing step of initializing the first and second data for input of a corresponding character when the first or second data is not normally acquired in the error determining step.

A setting character checking step of determining whether the first and second data correspond to preset data when the first or second data is normally acquired in the error determining step; And displaying the special characters on the touch panel when the first and second data correspond to the preset data in the setting character checking step so that the user can select any one of the special characters to be displayed on the touch panel. May include a special character selection step.

A stroke checking step of determining whether a stroke to be input after the second data obtaining step corresponds to a part of a character immediately inputted; A dot checking step of determining whether a dot is included in the letter when the input stroke corresponds to a part of the letter in the stroke checking step; And a dot character distinguishing step of displaying “i” or “j” determined by the inclination pattern of the character when the dot includes the dot in the dot checking step on the touch panel by the character displaying step. can do.

In the stroke checking step, if the input stroke is not part of the letter, the letter checking step is performed, and after the letter checking step, there is only one letter matching the first and second data from the sample data. The determination may further include a single character determination step of performing the character display step if there is only one.

In the single character determination step, when there are a large number of characters that match the first and second data from the sample data, or when the character does not include a dot in the dot checking step, each character of a recognition range is obtained. An inclination pattern checking step of finding a recognition character corresponding to the inclination pattern of the character input to the touch panel from the inclination pattern data; And a stroke unit determining step of determining whether a recognized character matching the inclination pattern is a character to which a stroke can be added, and if the stroke unit is not a character to which a stroke can be added in the judging step, perform the character display step. If the character is capable of adding the stroke, the first data acquiring step may be performed.

According to the handwriting recognition system and the handwriting recognition method using the same according to the present invention, it is possible to increase the recognition accuracy of the character input by the user and to reduce the time required for the recognition.

1 is a block diagram showing a handwriting recognition system according to an embodiment of the present invention,
2 is a flowchart illustrating a handwriting recognition method according to an embodiment of the present invention;
3 and 4 are diagrams for describing a handwriting recognition method according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but is to be understood to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention, And the scope of the present invention is not limited to the following examples.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like or corresponding elements are denoted by the same reference numerals, and redundant explanations thereof will be omitted.

1 is a block diagram illustrating a handwriting recognition system according to an embodiment of the present invention.

As shown in FIG. 1, the handwriting recognition system 10 according to an exemplary embodiment of the present invention may include a touch panel 11, a position calculation unit 12, a pattern recognition unit 13, and a memory unit 14. ), And a recognition controller 15.

The touch panel 11 is an input device that detects which section is in contact with or pressure from a user by touching a flat panel for inputting characters, and outputs the position information. The display driver 16 performs display operation .

The position calculator 12 may calculate a touch position of a character input to the touch panel 11 as a vector value.

The pattern recognition unit 13 divides the touch panel 11 into a plurality of areas by the vertical X axis, and also divides the touch panel 11 into a plurality of areas by the horizontal Y axis, and is calculated from the position calculation unit 12. The first data in the order of touching for each area divided by the X-axis and the second data in the order of touching for each area divided by the Y-axis are obtained from the touch position of the character, and the inclination from the touch position of the character is obtained. Acquire data about the pattern. Meanwhile, the characters to be recognized by the pattern recognition unit 13 are lowercase letters and uppercase letters, and special characters such as!, @, #, $,%, ^, &, *, (,),-, +, Etc. The X axis may be formed of one axis to divide the touch panel 11 into two, and the Y axis may be formed of two axes to divide the touch panel 11 into three. Here, the X axis and Y axis are axes which serve as a reference of an area for acquiring the first and second data on the touch panel 11, and the position thereof can be preset in the pattern recognition section 13 as a vector value or the like have. In order to increase the accuracy of character recognition, the X-axis and Y-axis can divide the touch panel 11 into equal areas.

The memory unit 14 includes sample data consisting of an order of touching each region divided by the X-axis, an order of touching each region divided by the Y-axis, and an inclination pattern for each character of the recognition range, for example, English characters and special characters. Save in advance.

In addition, the sample data can be set for the user's customization at the time of setting, for example, by inputting the character when the user first executes the character recognition program, and classifying the pattern in the manner input by the user. Therefore, by setting the pattern input by the user in advance, the recognition rate for the user can be increased, and the problem of not recognizing the character by the first and second data is eliminated.

The recognition controller 15 checks the recognition characters corresponding to the first and second data acquired by the pattern recognition unit 13 and the data of the inclination pattern, from the sample data stored in the memory unit 14 to the touch panel 11. ) Is displayed.

The handwriting recognition system 10 according to an embodiment of the present invention having such a configuration will be described in more detail together with the handwriting recognition method according to an embodiment of the present invention.

2 is a flowchart illustrating a handwriting recognition method according to an embodiment of the present invention.

As illustrated in FIG. 2, the handwriting recognition method according to an embodiment of the present invention may include first and second data verification steps S12, S13, and S19 and a character display step S26.

In the first and second data checking steps S12, S13, and S19, the touch panel 11 is divided into a plurality of areas by the vertical X axis, and is divided into a plurality of areas by the horizontal Y axis. Acquisition of the first data in the order of touching each area divided by the X axis by the character input to the touch panel 11 and the second data in the order of touching each area divided by the Y axis, the recognition range Recognizing characters matching the first and second data are found from the sample data consisting of the order of touching for each area divided by the X axis and the order of touching for each area divided by the Y axis for each character of.

On the other hand, the sample data can be set for the user's customization at the time of setting, for example, by inputting the character when the user first executes the character recognition program and classifying the pattern in the manner input by the user. Therefore, by setting the pattern input by the user in advance, the recognition rate for the user can be increased, and the problem of not recognizing the character by the first and second data is eliminated.

In the character display step S26, the recognition characters corresponding to the first and second data are displayed on the touch panel 11 from the sample data.

Meanwhile, in the first and second data checking steps S12, S13, and S19, the touch panel 11 is divided into a plurality of areas by the vertical X axis, and the touch panel 11 is operated by the character input step S11. The first data acquiring step (S12) of acquiring the first data in the order of touching each area divided by the X axis by the character input to the X axis, and the touch panel 11 by the horizontal Y axis A second data acquiring step (S13) of dividing into regions and obtaining second data in the order of touching each region divided by the Y axis by characters input to the touch panel 11; and characters of the recognition range, respectively. The character verification step (S19) of finding a recognition character matching the first and second data from the sample data consisting of the order of touching for each area divided by the X axis and the order of touching for each area divided by the Y axis with respect to Can include . Here, the character and the recognition range character to be recognized may be a variety of special characters, including uppercase and lowercase English letters and!, @, #, $,%, ^, &, *, (,),-, +, Etc. As shown in FIG. 3, the X-axis consists of one axis to divide the touch panel 11 into two, and the Y-axis consists of two axes Y1 and Y2 to divide the touch panel 11 into three. Can be done.

As illustrated in FIG. 3, the acquisition of the first and second data will be described using, for example, p, first, the left side of the touch panel 11 as "1" and the right side to "2". In the touch panel 11, when the upper side is "1", the middle is "2", and the lower side is "3" on the Y1 and Y2 axes, the first data is 1-2-. 1, and the second data is 1-2-3-2-1-2.

If the sample data according to the X-axis pattern and Y-axis pattern for the lowercase letters of the recognition range characters are shown in Table 1 and Table 2, the sample data can be obtained by the above method for the special characters.

<Organization by character by X-axis pattern> text Test Model Prediction Pattern Test model exception patterns ‘A’ 2-1-2 'b' 1-2-1 ‘C’ 2-1-2 ' d ' 2-1-2 2-1-2-1-2 ' e ' 1-2-1-2 ' f ' 2-1-2 2-1-2-1-2 ' g ' 1-2-1-2 2-1-2-1-2 ' h ' 1-2 ' i ' 1-2 ' j ' 2-1 ' k ' 1-2-1-2 2-1-2 ' l ' 1-2-1-2 ' m ' 1-2 ' n ' 1-2 ' o ' 1-2-1 ' p ' 1-2-1 ' q ' 2-1-2 ' r ' 1-2 ' s' 2-1-2-1 ' t ' 1-2-1-2 ' u ' 1-2 ' v ' 1-2 ' w ' 1-2 ' x ' 2-1-2 ' y ' 1-2-1-2 ' z ' 1-2-1-2

<Y-axis pattern by letter> text Test Model Prediction Pattern Test model exception patterns ‘A’ 1-2-3-2-1-2-3 1-2-3-2-1-2 'b' 1-2-3-2-3 1-2-3, 1-2-3-2-1-2-3 ‘C’ 1-2-3 1-2-3-2 'd' 2-3-2-1-2-3 2-3-2-1-2 ' e ' 2-1-2-3 2-1-2-3-2, 1-2-3, 1-2-3-2 ' f ' 1-2-3-2 1-2-3-2-1 ' g ' 1-2-1-2-3-2 1-2-1-2-3-2-1 ' h ' 1-2-3-2-3 1-2-3-2-3-2 ' i ' 3-2-1-2-3 1-2-3 ' j ' 1-2-3 1-2-3-2 ' k ' 1-2-3-2-3 1-2-3 ' l ' 3-2-1-2-3 1-2-3 ' m ' 1-2-3-2-1-2-3-2-1-2-3 1-2-3-2-1-2-1-2-3 ' n ' 1-2-3-2-1-2-3 3-2-1-2-3 ' o ' 1-2-3-2-1 2-3-2-1-2 ' p ' 1-2-3-2-1-2 1-2-3-2-1 ' q ' 1-2-1-2-3 1-2-3 ' r ' 1-2-3-2-1 1-2-3-2 ' s' 1-2-3 ' t ' 1-2-3-2 1-2-3-2-1 ' u ' 1-2-3-2-1-2-3 1-2-3-2-1 ' v ' 1-2-3-2-1 ' w ' 1-2-3-2-1-2-3-2-1 ' x ' 1-2-3-2-1-2-3 ' y ' 1-2-1-2-3-2 1-2-1-2-3-2-1, 1-2-1-2-3 ' z ' 1-2-3 1-2-3-2

In addition, if the sample data by the X-axis pattern and Y-axis pattern is organized by group, as shown in Table 3 and Table 4 below, the special data can also be organized by group as shown below.

<Cleanup by X-Axis Pattern Group> Group pattern Test Model Prediction Group Test Model Exception Group 1-2 'H', 'i', 'm', 'n', 'r', 'u', 'v', 'w' 'a', 'd', 'l', 'y' 2-1 'j' 1-2-1 'b', 'o', 'p' 'y' 2-1-2 'a', 'c', 'd', 'f', 'k', 'q', 'x' 'h', 'o' 1-2-1-2 'e', 'g', 'k', 'l', 't', 'y', 'z' 'f', 'a' 2-1-2-1 's' 'o' 2-1-2-1-2 'd', 'f', 'g'

<Arrangement by Y-axis pattern group> Group pattern Test Model Prediction Group Test Model Exception Group 1-2-3 'c', 'j', 'k', 's', 'z' 'b', 'q', 'e', 'i', 'l' 1-2-3-2 'f', 't' 'c', 'j', 'r', 'z', 'e' 1-2-1-2-3 'q' 'y' 1-2-3-2-1 'o', 'r', 'v' 'f', 'p', 't', 'u' 1-2-3-2-3 'b', 'h', 'k' 1-2-1-2-3-2 'g', 'y' 1-2-3-2-1-2 'p' 'a' 1-2-3-2-3-2 'h' 1-2-1-2-3-2-1 'g', 'y' 1-2-3-2-1-2-3 'a', 'n', 'u', 'x' 'b' 1-2-3-2-1-2-1-2-3 'm' 1-2-3-2-1-2-3-2-1 'w' 1-2-3-2-1-2-3-2-1-2-3 'm' 2-1-2-3 'e' 2-1-2-3-2 'e' 2-1-2-3-2-1 'e' 2-3-2-1-2 'd', 'o' 2-3-2-1-2-3 'd' 3-2-1-2-3 'i', 'l' 'd' 3-2-1-2-3-2-1-2-3 'm'

Meanwhile, the error determination step S14 and the initialization step S15 may be performed after the second data acquisition step S13.

The error determining step S14 is a step of determining whether the first or second data is normally acquired after the second data obtaining step S13, and fails to obtain the first and second data due to a system error, An error such as when there is no input enough to perform the step of acquiring the first and second data is determined.

If the first or second data is not normally acquired in the error determination step S14, the initialization step S15 initializes the first and second data for the input of the corresponding character to the touch panel 11. It is possible to obtain first and second data for input characters.

When the first or second data is normally acquired in the error determination step S14, the setting character checking step S16 may be performed to determine whether the first and second data correspond to the preset data. Here, the preset data is a character that is input when the character is input to the touch panel 11 by storing data about one of the specified characters, for example, special characters, in advance so that the user recognizes the predetermined character. And whether it is a character specified by the second data. If the first and second data correspond to the preset data in the setting character checking step (S16), the special characters are displayed on the touch panel 11 to display any one of the special characters to be displayed on the touch panel 11 by the user. A special character selection step (S17) may be performed to select by touch or input of a number indicated by the corresponding special character.

After the second data acquiring step S13, for example, when the first and second data are not preset data in the setting character checking step S16, it is determined whether the input stroke corresponds to a part of the character immediately input. The stroke checking step S18 may be performed, and when the stroke input in the stroke checking step S18 corresponds to a part of the letter, the dot checking step S20 may be performed to determine whether a dot is included in the letter. . In addition, when the dot includes the dot in the dot checking step S20, the dot “i” or “j” determined by the inclination pattern of the letter is displayed on the touch panel 11 by the character display step S26. The character distinguishing step S21 can be performed. Here, the inclination pattern will be described later. Thus, writing " l (L) " first recognizes " l (L) ", and next time a dot is taken, " i " or " j "

If the stroke input in the stroke checking step (S18) is not part of the character, the character checking step (S19) is executed, and after the character checking step (S19), there is only one character matching the first and second data from the sample data. The single character determination step S23 may be performed to determine whether the character is recognized and to perform the character display step S26.

When a single character determination step (S23) has a large number of characters that match the first and second data from the sample data, or when the character does not contain a dot in the dot check step (S20), for each character of the recognition range Inclination pattern checking step (S24) of finding the recognition character matching the inclination pattern of the character input to the touch panel 11 from the obtained inclination pattern data, and whether the recognition character matching the inclination pattern is a character to which a stroke can be added. The judging stroke portion can perform the judging step S254. As shown in FIG. 4, the inclination pattern enables data of a sequence of patterns indicating a direction from "1" to "8" in a character input to the touch panel 11 so that recognition of the character is used.

As shown in Figure 4, the angle range of the inclination pattern for the first to the eighth is shown in Table 5.

<English Alphabet Slope Pattern> direction Slope Pattern Angle Range Pattern number '↓'  337.5 degrees <0 degrees <= 22.5 degrees number 1 '↘' 22.5 degrees <45 degrees <= 67.5 degrees No.2 '→' 67.5 degrees <90 degrees <= 112.5 degrees number 3 '↗' 112.5 degrees <135 degrees <= 157.5 degrees 4 times '↑' 157.5 degrees <180 degrees <= 202.5 degrees 5 times '↖' 202.5 degrees <225 degrees <= 247.5 degrees 6th '←' 247.5 degrees <270 degrees <= 292.5 degrees No. 7 '↙' 292.5 degrees <315 degrees <= 337.5 degrees 8 times

<Cleanup by Slope Pattern Letters> text Test Model Prediction Pattern Test model exception patterns ' a ' 7-8-1-2-3-4-5-1-2 ' b ' 1-5-4-3-2-1-8-7 ' c ' 7-8-1-2-3-4 ' d ' 7-8-1-2-3-4-5-1-2 ' e ' 3-4-5-6-7-8-1-2-3 ' f ' 6-7-8-1-2-1-8-7-6-5-4-3 ' g ' 7-8-1-2-3-4-5-6-1-8-7-6-5-4-3 ' h ' 1-5-4-3-2-1 ' i ' 4-5-1-2 ' j ' 1-8-7-6 ' k ' 8-3-2-3 ' l ' 3-4-5-6-7-8-1-2-3 ' m ' 1-5-4-3-2-1-5-4-3-2-1 ' n ' 1-5-4-3-2-1 ' o ' 7-8-1-2-3-4-5-6-7 ' p ' 1-5-4-3-2-1-8-7 ' q ' 7-8-1-2-3-4-5-1 ' r ' 1-5-4-3 ' s' 7-8-1-2-3-2-1-8-7-6-5 ' t ' 1-2-3-4-5-6-7-3 ' u ' 1-2-3-4-5-1 ' v ' 1-2-4-5 ' w ' 2-1-4-5-2-1-4-5 ' x ' 8-5-2 ' y ' 1-2-3-4-5-1-8-7-6-5-4-3 ' z ' 3-8-3

If the stroke part is not a character that can be added to the stroke in the determination step (S25), the character display step (S26) may be performed, and if the character that can be added to the stroke may be performed after the first data acquisition step (S12). Character is recognized.

According to the handwriting recognition system and the handwriting recognition method using the same according to the present invention, it is possible to increase the recognition accuracy of the characters input by the user, reduce the time required for recognition, and classify the characters into patterns so that the handwriting input is performed. This eliminates the need for waiting time to speed up character recognition.

A summary of the execution speed of the algorithm according to the present invention is shown in Table 7 below, and it can be seen that the time required for recognition of the average average takes only 0.1 to 0.125 sec.

Test Criteria Model Android Galaxy S & Eclipse JUnit Test Case Algorithm average execution speed-0.00624 sec (1000 times per character)
Database Average Performance Speed-0.05 ~ 0.1 sec Overall average performance rate-0.1 to 0.125 sec text Algorithm execution speed text Algorithm execution speed ‘A’ 0.008583 sec ‘N’ 0.0058 sec ‘D’ 0.008150 sec ‘O’ 0.0056 sec ‘C’ 0.006594 sec ‘P’ 0.005249 sec ‘D’ 0.00652 sec ‘Q’ 0.0055 sec ‘E’ 0.0065 sec ‘R’ 0.0047 sec ‘F’ 0.006818 sec ‘S’ 0.0054 sec ‘G’ 0.0062 sec ‘T’ 0.0083 sec ‘H’ 0.0063 sec ‘U’ 0.00615 sec ‘I’ 0.0067 sec ‘V’ 0.00605 sec ‘J’ 0.0058 sec ‘W’ 0.01014 sec ‘K’ 0.0057 sec ‘X’ 0.0082 sec ‘L’ 0.00575 sec ‘Y’ 0.00545 sec ‘M’ 0.0066 sec ‘Z’ 0.0062 sec

Although the present invention has been described with reference to the accompanying drawings, it is to be understood that various changes and modifications may be made without departing from the spirit of the invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined by the equivalents of the claims, as well as the following claims.

11: Touch panel
12:
13: pattern recognition unit
14:
15:
16: Display driver

Claims (8)

In the device for recognizing a character written on the touch panel,
A touch panel for inputting text by a user;
A position calculator for calculating a touch position of a character input to the touch panel;
The touch panel is divided into a plurality of areas by the vertical X axis, and is divided into a plurality of areas by the horizontal Y axis, and is divided by the X axis from the touch position of the character calculated from the position calculator. Acquiring first data in the order of touching each divided area and second data in the order of touching each area divided by the Y axis, and obtaining data about an inclination pattern from the touch position of the character. Pattern recognition unit;
A memory unit for storing in advance a sample data consisting of an order of touching each region divided by the X axis, an order of touching each region divided by the Y axis, and an inclination pattern for each character of a recognition range; And
And a recognition control unit which checks the recognition characters corresponding to the first and second data acquired by the pattern recognition unit and the data for the inclination pattern from the sample data stored in the memory unit and displays them on the touch panel. Handwriting recognition system. In the method for recognizing a character written on the touch panel,
The touch panel is divided into a plurality of areas by a vertical X axis, and is divided into a plurality of areas by a horizontal Y axis, and each area divided by the X axis by a character input to the touch panel. Obtaining first data in the order of touching and second data in the order of touching for each area divided by the Y-axis, and touching each area divided by the X-axis for each character of the recognition range; First and second data checking steps of finding recognition characters corresponding to the first and second data from sample data in the order of touching for each area divided by the Y axis; And
And a character display step of displaying, on the touch panel, a recognition character corresponding to the first and second data from the sample data. The method of claim 2, wherein the first and second data checking steps include:
Acquiring first data by dividing the touch panel into a plurality of areas by a vertical X axis, and obtaining first data in an order of touching each area divided by the X axis by a character input to the touch panel. step;
Second data for dividing the touch panel into a plurality of regions by a horizontal Y axis, and obtaining second data in an order of touching each region divided by the Y axis by a character input to the touch panel; Obtaining step; And
For each character in the recognition range, recognition characters corresponding to the first and second data are selected from sample data consisting of an order of touching each region divided by the X axis and an order of touching each region divided by the Y axis. Include character verification steps to find,
The character is an English letter and a special character, and the X-axis consists of one axis for dividing the touch panel into two, and the Y-axis consists of two axes for dividing the touch panel into three. Recognition method. The method of claim 3, further comprising: an error determining step of determining whether the first or second data is normally acquired after the second data obtaining step; And
And initializing the first and second data for input of a corresponding character when the first or second data is not normally acquired in the error determining step. The method of claim 4, further comprising: a setting character checking step of determining whether the first and second data correspond to preset data when the first or second data is normally acquired in the error determining step; And
In the setting character checking step, if the first and second data correspond to the preset data, special characters are displayed on the touch panel so that the user can select any one of the special characters to be displayed on the touch panel. Handwriting recognition method comprising the step of selecting a special character. The method according to any one of claims 3 to 5,
A stroke checking step of determining whether a stroke to be input after the second data obtaining step corresponds to a part of a character immediately inputted;
A dot checking step of determining whether a dot is included in the letter when the input stroke corresponds to a part of the letter in the stroke checking step; And
And a dot character distinguishing step of displaying “i” or “j” determined by the inclination pattern of the letter when the dot includes the dot in the dot checking step on the touch panel by the letter displaying step. Handwriting recognition method, characterized in that. The method of claim 6, wherein the character checking step is performed when the input stroke is not part of the character in the stroke checking step,
And a single character determination step of determining whether there is only one character matching the first and second data from the sample data after the character checking step, and if so, the character display step. Handwriting Recognition Method. The recognition range according to claim 7, wherein in the single character determination step, when there are a plurality of characters that match the first and second data from the sample data, or when the character does not include a dot in the dot checking step, a recognition range An inclination pattern checking step of finding a recognition character corresponding to the inclination pattern of the character input to the touch panel from the data of the inclination pattern obtained for each character of the inclination pattern; And
The stroke unit may further include a judging step for determining whether the recognition character matching the inclination pattern is a character to which a stroke can be added.
And if the stroke is not a character that can be added to the stroke in the determining step, performing the character display step, and if the character is to be added to the stroke, performing the first data acquiring step.

Images