JPS60246492A - Discriminating method of large character and small character in case of recognizing handwriting character - Google Patents

Abstract

PURPOSE:To simplify an operation of a recognizing device by constituting it so that it discriminated that a handwriting character is a small character, when a magnification in case of magnifying or reducing the handwriting character exceeds a value prescribed in advance. CONSTITUTION:A coordinate data of a character handwritten on a tablet 1 is brought to a smoothing processing, a sampling processing, an interpolation processing, etc. by a pre-processing program 31, and thereafter, delivered to a magnification processing program to a standard pattern of an input character. Subsequently, in accordance with a derived magnification K, an input character is magnified or reduced to a prescribed size, this magnified or reduced input character is collated with the standard pattern, and the input character is recognized. In this case, in case a large character/small character converting key is depressed, and also it is decided that a result of recognition is a small character, the small character being a result of recognition is changed to a large character by referring to a conversion table (2) of a data memory 22.

Description

DETAILED DESCRIPTION OF THE INVENTION Technical Field The present invention relates to a method for identifying uppercase and lowercase letters in handwritten character recognition.

<Prior Art> A handwritten character recognition device performs character recognition using a tablet that detects the coordinate values of the locus of characters written with an input pen. This handwritten character recognition device recognizes handwritten characters by comparing the strokes of the characters written within a predetermined frame on the tablet left with the standard pattern of the characters. The strokes are not necessarily the same size as the standard pattern. Therefore, it is impossible to distinguish between uppercase and lowercase letters when they are written, so in the past, it was necessary to provide a lowercase mode key and perform the troublesome operation of pressing the lowercase mode key every time a lowercase letter was entered. Ta.

<Object of the Invention> The present invention has been made in view of the above circumstances, and its purpose is to identify whether it is an uppercase letter or a lowercase letter by enlarging or reducing a handwritten character and comparing it with a standard pattern. It is an object of the present invention to provide a handwritten character tim device.

<Structure of the Invention> In the present invention, a pattern of handwritten characters inputted to a tablet left that detects the coordinate values of the locus of characters written by an input ben is enlarged or reduced to a predetermined size. , after determining the magnification or reduction ratio, the handwritten characters are compared with a predetermined standard pattern of characters, and the handwritten characters are identified as uppercase or lowercase according to the result of the comparison and the magnification or reduction ratio. shall be.

<Example> An embodiment of the present invention will be described below.

Figure j81 shows the appearance of a handwritten character recognition device to which the present invention is applied.

A former is provided on the tablet surface 1a of the tablet device 1.
/ ) A recess corresponding to the thickness of the sheet 10 is formed, and the format sheet 10 is fitted into this recess. The surface of this formant sheet 10 and the tablet surface 1a are substantially flat. An entry form 12 is placed on the format sheet 10, and characters to be entered are written on this entry form 12.

Input Ben 2 is input to tablet device 1 by curl code 3
A writing instrument 4 is attached to the tip of the input ben 2. The input ben 2 has a built-in stroke switch that is turned on and off by pushing down or releasing the writing instrument 4 onto the tablet surface 1a. and,
When characters, etc. are written on the entry form 12 placed on the tablet left surface 1a by the input ben 2, the tablet device 1 generates coordinate data Xb, Yi representing the locus of the written characters, etc. in response to the ON signal of the stroke switch, for example. Output at a density of 10 points/fi. The tablet device 1 is generally known as, for example, an electromagnetic induction type input device.

On the format sheet 10, a group of character entry frames 11.11° for growing predetermined coordinate values are arranged in a matrix, and above the entry frame group 11°11, -., when inputting characters, that is, Function key frames 14 that are infrequently used during editing processing are arranged horizontally. Also, on the right side of the entry frame group 11°11,-- (the left side is fine, but the right side is better from the viewpoint of operability), the function key frame 13, which is frequently used during editing processing, is arranged vertically. There is. This function key frame 13 is used to manually input the uppercase/lowercase conversion key, which will be described later.

This format sheet 100 characters writer frame group 11, 11
．． An entry form 12 with a length corresponding to the width of - is placed, and the characters to be input are entered in the character frame using the writing instrument 4 of the input ben 2. The tablet device 1 extracts the locus of each filled-in character frame as coordinate data and performs character recognition.

The control unit 5 is connected to the tablet device 1 by a curl code 6, and further connected to the control unit 5 is an output device such as a CR7 display device (not shown) that outputs character information recognized by the curl code 7.

FIG. 2 shows the configuration of the control unit 5 of the above-mentioned handwritten character recognition device.

The CPU 20 performs sequence control of the process from recognizing the corresponding character based on the stroke data of the handwritten character input from the tablet to outputting this character information.
It is executed according to the system program stored in the ROM 21.

The ROM 21 stores five major classifications of system programs.

The preprocessing program 31 performs processing to remove stair-like or spike-like trajectory distortions in the trajectory of stroke data that is manually inputted in time series from the tablet, and interpolation between coordinate points of the trajectory input and imported from the tablet. interpolation processing to perform this, sampling processing to capture the necessary amount of each coordinate data input manually from the tablet, normalization processing to normalize the position and size of the input stroke by reducing/enlarging it, and It consists of programs that perform input completion processing for input characters, etc.

The stroke feature point extraction processing program 32 is a processing program that calculates the start point, end point, midpoint, etc. of the stroke by arithmetic processing based on the stroke data obtained by the above-mentioned processing, and extracts it as the feature point of the stroke. .

The distance calculation program 33 uses a standard pattern 23 described later.
This is a program for comparing the above feature points with the above feature points, calculating the distance between them, and calculating distance data.

! ! ! The recognition processing program 34 is a processing program that selects the most suitable character based on the distance data and uses it as a recognition character.

The output processing program 35 is a processing program that sends at least one character (JIS code) of a plurality of candidate characters to an output device, for example, a CRT display device, through the above-mentioned processes.

As described later, the magnification calculation processing program 36 calculates the center of gravity of each character stroke written in one entry frame 11, and further calculates the average value r of the character radius with the center of gravity of each character stroke as the center point. This is a processing program that calculates the value of rs and determines whether the letter is uppercase or lowercase by comparing it with a predetermined radius constant rs. In addition, the large/lower case conversion processing program 37 performs processing to convert the recognition processing result into its character code, and also handles cases in which the entire stroke of one character is written small and is output as a lower case character even though it is originally an upper case character. In the reverse case, this is a program for processing to convert into a corresponding character code by switching between uppercase and lowercase letters using a function key.

The data memory 22 is composed of a RAM, and is provided with the following various buffers.

The coordinate data buffer 41 temporarily stores coordinate data input from a tablet and performs preprocessing on the data. The feature point buffer 43 stores feature points such as the start point, end point, midpoint, etc. of the stroke from the stroke data obtained by the above-described preprocessing. The result buffer 43 is based on the data of the feature point buffer 43,
Check with the standard pattern and find the corresponding 1m character JIS
Store the codes in the lowest order as a result of distance calculation,
Furthermore, it is stored together with the distance data. data memory 2
In addition to the above-mentioned buffers, 2 also includes an area 42 consisting of various buffers for the above-mentioned processes and the above-mentioned large/
A conversion table 44 used for character code conversion between upper and lower case characters is provided in the small size conversion processing program 37.

This conversion table 44 includes a conversion table (11) for converting uppercase letters to lowercase letters and a conversion table (2) for converting lowercase letters to uppercase letters.

The standard pattern memory 23 stores standard patterns such as characters, and stores standard feature points such as the start point, middle point, and end point of each character for each stroke of each character, along with the JIS code of each character.

Output device 26 such as a tablet device 1 and a CRT display device
is connected to the CPU 20 via an interface device 24.

The operation of the handwritten character recognition device configured as described above will be described below with reference to the flowchart of FIG. 3.

First, coordinate data of a character handwritten on the tablet 1 is imported (steps SL, S2), and preprocessing such as the above-mentioned smoothing process, +sampling process, and interpolation process is performed by the preprocessing program 31 (step S3). ).

Next, magnification calculation processing in steps 84 to S6 is performed. In this magnification calculation process, the magnification for the standard pattern of input characters is calculated. That is, let the total number of coordinate values of the input character stroke be N, and let each coordinate value be xi, yi (t=1.--
, N), the coordinate value x of the center of gravity which is the center point of the input character
, y are determined by equation fl) and equation (2).

Next, the center of gravity, each coordinate value, and the average value r of the distance are calculated using equation (3).

Set (3) where r is a function representing the size of the character, the center of gravity x,
A circle with radius r centered at y indicates the size of the character. If the radius of the standard pattern stored in advance in the control unit 5 for handwritten character recognition is rs, then the magnification is determined by equation (4).

Here, if k=l, the standard pattern and the input character have the same size, if k<l, the input character is larger than the standard pattern, and if k>1, the input character is smaller than the standard pattern.

It goes without saying that the value of the magnification for determining that an input character is a lowercase letter varies depending on the size rs of the standard pattern and the coordinate density of the tablet used. For example, the radius rs of a standard pattern with a coordinate density of 10 points/(0,1 m unit) and a character entry frame of 10 dragon angles = 35 (3,
5m), k≧1.25 is lower case, k<1
．． If 25 is an uppercase letter, the input character stroke “≦2
8 (less than 2.8w), it is determined to be a lowercase letter, and r>2
8 (larger than 2.8m), it is determined to be an uppercase letter (steps 87 to 39).

Next, the input character is enlarged or reduced to a certain size according to the requested magnification k (step 510).

Then, the enlarged or reduced input character is compared with the standard pattern to recognize the input character (step 511).
. At this time, if the lowercase flag is on and the recognition result is a character that corresponds to uppercase/lowercase conversion (steps 812, 313), the recognition result is converted to lowercase by referring to the conversion table (11) in the data memory 22. Then, the recognition result is output to the output device 26 (Step 816).

Here, the key strength of the uppercase/lowercase conversion key in the function key frame 13 is determined (step 317),
Furthermore, it is determined whether the recognition result is a lowercase letter (step 818). Then, if the uppercase/lowercase conversion key is activated and the recognition result is a lowercase letter, the lowercase letter that is the recognition result is changed to an uppercase letter with reference to the conversion table (2) in the data memory 22 (step S19). .52
0).

In addition, if the uppercase/lowercase conversion key is manually operated and the recognition result is an uppercase character, the uppercase character in the recognition result is changed to a lowercase character by referring to the conversion table +1 in the data memory 22 (steps S21 and 522). ).

Note that the fourth method for defining the size of handwritten characters is
As shown in the figure, when a polygon is formed that is in contact with an input character and all vertices have one coordinate value of the input character, the area of the polygon is taken as the character size, and the ratio (magnification) to the area of the standard pattern is You can also determine uppercase and lowercase letters.

<Effects of the Invention> As explained above, in the present invention, when the magnification when enlarging or reducing handwritten characters to a certain size is equal to or greater than a predetermined value, handwritten characters are

Since we have made it possible to identify that the letters are lowercase,
There is no need to perform a key operation each time a lowercase letter is input (this simplifies the operation of the handwritten character recognition device.In addition, by operating the case/lowercase conversion key, you can change from uppercase to lowercase or from lowercase to uppercase. can be done without having to re-enter the characters.

[Brief explanation of the drawing]

Figure 1 is a perspective view showing the appearance of the handwritten character recognition device;
3 is a block diagram showing the configuration of a control device of a handwritten character recognition device, FIG. 3 is a flowchart showing the operation of the device shown in FIG. 2, and FIG. 4 is a diagram showing another embodiment of handwritten character recognition. 1-=Tablet device 2-Manual pen 13-Function key frame Patent applicant Sharp Corporation agent Patent attorney Arata Nishida

Claims (1)

[Claims] ('') Enlarging or reducing the pattern of handwritten characters input to a tablet that detects the coordinate values of the locus of characters written with an input pen to a predetermined size,
The handwritten characters are compared with a predetermined standard pattern of characters after determining the magnification or reduction ratio, and the handwritten characters are identified as uppercase or lowercase according to the result of the verification and the magnification or reduction ratio. A method for distinguishing between uppercase and lowercase letters in handwritten character recognition. (2) Handwritten characters tBk according to claim 1, in which it is possible to convert uppercase letters to lowercase letters or vice versa for handwritten letters input manually using a predetermined key.
How to distinguish between uppercase and lowercase letters.