JPH0454268B2 - - Google Patents

Description

[Detailed description of the invention] [Technical field of invention] The present invention relates to a character recognition device.

[Prior art]

In recent years, various character recognition devices have been developed that recognize characters, figures, etc. that are handwritten on a doublet using a pen-shaped jig or the like and convert them into input information. In this type of character recognition device, when a character pattern is inputted incorrectly, it is cleared by operating a correction key, and then the same pattern is inputted again. Furthermore, if the input character pattern is incorrectly recognized, the user operates the correction key in the same way and inputs it again.

[Problems with conventional technology]

However, since each person has a different way of writing letters and numbers, the above-mentioned incorrect recognition of the character pattern may be repeated several times in a row, in which case you may have to press the correction key many times. It is necessary to input a new character pattern, which reduces efficiency as the input operation takes time, and also has the disadvantage that key operations are complicated.

[Purpose of the invention]

The present invention has been made against the background of the above-mentioned circumstances, and its purpose is to provide character recognition that, when a character pattern is misrecognized, can be corrected quickly and that the correction operation is simple. The goal is to provide equipment.

[Key points of the invention]

In order to achieve the above-mentioned object, this invention
When a misrecognition occurs, the character pattern input by the next correction operation is recognized from among the characters excluding the misrecognized character, so that misrecognition is not repeated several times in a row. The main points are the main points.

〔Example〕

Hereinafter, one embodiment of the present invention will be specifically described with reference to the drawings. FIG. 1 is a top view of an electronic wristwatch equipped with, for example, a character recognition device. in this case,
The input section 1 consists of transparent touch electrodes arranged in, for example, a 4x4 matrix on a transparent glass surface fixed to the top surface of the watch case. The touch electrodes are arranged on the XY coordinate system, and for example, 16×16=
256 coordinate positions 1A are formed by electrical processing. When a human body such as a finger touches the electric touch electrode, the contact capacitance component generated in the touch electrode at that time is detected and the coordinate position 1A is input, thereby inputting a character pattern. This type of technology may be utilized in a patent application (Japanese Patent Application No. 55-35660, title of invention: touch switch device) already proposed by the present applicant. The input unit 1 is provided with an input end key 1B that is operated when inputting one character pattern is finished, and a correction key 1C that clears the recognized character when the inputted character pattern is incorrectly recognized.

Next, the circuit configuration will be explained with reference to FIG.
In the figure, reference numeral 2 denotes a display section consisting of a liquid crystal display device, which displays character patterns, time data, date data, etc. from the input section 1 in a matrix.

ROM (read only memory) 3 stores microprograms that control all operations of this electronic wristwatch, and includes microinstructions AD, DA, OP, and NA.
Output in parallel. Therefore, microinstruction AD is
The data is applied to the ROM 4 and RAM (random access memory) 5 as address data, respectively. Further, the microinstruction DA is applied to the RAM 5 or the arithmetic unit 6 as data. Further, the microinstruction OP is applied to the operation decoder 7, and the operation decoder 7 accordingly outputs the control signal.
Outputs CS ₁ , CS ₂ , X, Y, Z, R, S, G, etc. The microinstruction NA is applied to the address section 8, and in response, the address section 8 extracts the microinstruction necessary for the next process from signals d, c, etc., which will be described later.
Outputs address data for reading AD, DA, OP, and NA and supplies it to ROM3.

Vector strings of standard character patterns for characters such as numbers and alphanumeric characters are stored as data in the ROM 4, and are compared with vector strings of character patterns input from the input section 1 to perform character recognition. Note that the ROM 4 receives the control signal
Data is read by _CS1 .

The RAM 5 has various registers, and is used in various processes such as time measurement processing and character recognition processing performed by the arithmetic unit 6, and data is read and written under control signals CS ₂ and R/W.

The calculation unit 6 executes the various calculations described above under the control signal X. The resulting data is input part 1,
It is applied to the display unit 2 and RAM 5. When the jump calculation is still executed, a signal d indicating the presence or absence of the data of the calculation result, and a signal c indicating the presence or absence of carry occurrence.
are output, respectively, and supplied to the address section 8.

The SR type flip-flop 9 is set or reset by control signals S and R, respectively. The control signal S is outputted at the start of inputting each stroke of a character pattern, and the control signal R is outputted at the end of inputting. And the set output signal is AND gate 1
0 as a control signal. A clock of a predetermined frequency output from an oscillation circuit 11 is input to the other end of this AND gate 10, and the clock output from the AND gate 10 is input to a timer section 12 consisting of a counter and counted. Ru.
This timer section 1 is the input time of each stroke (ON
time) and the OFF time from the end of each stroke input to the next stroke input.
The ON time and OFF time obtained in this way are determined through the gate 13, which is opened when the control signal G is output.
It is given to the RAM 5 and the arithmetic unit 6. Note that the timer section 12 is cleared by the control signal S. Note that the input section 1 and the display section 2 are controlled by a control signal Z or Y, respectively.

Next, the standard vector sequence and vector sequence will be explained. Figure 3 shows the situation when the number "2" with a stroke count of 1 is input from the input section 1. As shown in Figure 3A, when the character pattern "2" is input, its coordinate position data is RAM
5 are sequentially written. Then, as shown in FIG. 3B, after inputting the character pattern "2", when the finger leaves the touch electrode, the stroke length is calculated from the coordinate position data written in the RAM5, and then the stroke length is calculated from the coordinate position data written in the RAM5.
Divided equally. Then, as shown in Figure 3C, each equally divided point is approximated by a straight line from the starting point side to the ending point side, and the vector of each part is determined according to the vectors (8 types from 0 to 7) in Figure 4. , a vector sequence is calculated. Next, after the input end key 1B is operated, the calculated vector string is compared with the coordinate vector string in the ROM 4, and the most similar character pattern is output.

5, 6, 7, and 8 show standard vector sequences of character patterns having stroke counts of 1, 2, 3, and 4, respectively, and are stored in the ROM 4.

Next, the operation of this embodiment will be explained with reference to FIG. When the power is turned on, the operation according to the flow shown in FIG. 9 is executed. First, in step _S1 , initialization processing is performed, that is, the flag register F and the stroke number counter S in the RAM 5 are cleared. Note that the flag register F is set to "1" by operating the correction key 1C, and
The stroke number counter S counts the number of strokes of one character.

Next, the process proceeds to step _S2 , where it is determined whether or not a character pattern is input from the input section 1, in other words, whether or not the touch electrode is touched. Then, when you touch the touch electrode of input section 1 with your finger and draw a character, step _S3
, and the contents of the stroke number counter S are +1.
Increment processing is executed, and the value is "1" at first, which is the value of the first stroke. Next, as the character is written, each coordinate position is sequentially detected, and the data of the detected coordinate position is sequentially written into the first stroke area in the RAM 5 (steps S ₄ and S ₅ ). Then, in the next step _S6 , it is determined whether or not the finger has left the touch electrode after writing the first stroke.As a result, if writing is in progress, the operation returns to step _S4 and the operation of acquiring the coordinate position is repeated. It will be done. Also,
When the first stroke is finished and the finger is released, this is determined in step _S6 , and the process proceeds to step _S7 . Here, the stroke l (length) is calculated from each coordinate position data written in the first stroke area of the RAM 5. The stroke length calculated in this way is used in the next step.
Divide into 6 equal parts with S ₈ , extract 6 equal parts, and then
The vectors of each part are determined according to the vectors in Figure 4, and a vector sequence is calculated (step
_S9 ). After this vector string is stored in a predetermined register in the RAM 5 (step _S10 ),
Return to step _S2 .

For a character with one stroke count, such as the number "2", the input of the character pattern is completed with one stroke, so the input end key 1B is then operated. As a result, the result in step _S2 is NO, and the step to determine whether or not the input end key 1B has been operated is performed.
Proceed to step _S12 via _S11 . On the other hand, for each character with a stroke count of 2, 3, or 4, steps _S2 to _S10 are repeated two, three, and four times, and then the step is returned by operating the input end key 1B.
Proceed to S ₁₂ . Thus, for example, when the number "2" is input, the vector sequence obtained through steps _S2 to _S10 is "175570", as can be seen from FIG. 3C. On the other hand, in the above step _S12 , it is determined whether the contents of the flag register F are "0" or not. Since it is initially "0", the process proceeds to step _S13 , where the memory area M in the RAM 5 is cleared. Note that this memory area M stores characters that were erroneously recognized in the previous character recognition process. In the next step _S14 , input character recognition processing is executed. That is, in this recognition process, the vector strings obtained as described above are classified by number of strokes, and the vector strings for each number of strokes are compared with the standard vector strings in the ROM 4. The most similar character pattern is extracted from the characters excluding characters. In this case, the direction difference between the vector string obtained by inputting the character pattern and each vector of the standard vector string is detected, and the smallest sum of these vectors is extracted as the most similar character pattern. Therefore, in the vector sequence "175570" (see Figure 3C) obtained by inputting the number "2" as described above, as a result of comparison with the standard vector sequence of stroke 1 shown in Figure 5, The character pattern "2" of the standard vector "175500" is extracted. In this case, in the previous character confirmation process, when the number "2" was input and it was incorrectly recognized as "7", characters excluding this "7" are extracted, but initially, the contents of memory area M are Since it is cleared, recognition processing is executed for all characters.

The character pattern extracted as described above is then displayed on the display section 2 (step _S15 ).
Proceeding to the next step _S16 , it is determined whether the correction key 1C has been operated. In this case, if the displayed character is different from the input character and has been misrecognized, the correction key 1C is operated. By operating this correction key 1C, the step
Proceeding to _S17 , the flag register F is set to "1", and then the process returns to step _S2 .

If the input character pattern is misrecognized in this way, press the correction key 1C, input the character pattern again, and then press the input end key 1.
Operate B. As a result, the vector sequence of the character pattern input in steps _S2 to _S10 is calculated in the same manner as described above, and the process then proceeds to step _S12 via step _S11 . ₁₂
If the answer is NO, the process moves to step _S18 . Here, when the previously extracted character, for example, the number "2" is input and recognized as "7", this erroneously recognized "7" is stored in the memory area M. Next, proceed to step _S19 , and after clearing the display content, which is "7" in the above example,
Recognition processing in step _S14 is executed.

Therefore, after writing the previously extracted characters into memory area M, step _S14 is executed.
After the correction key 1C is operated, a character that has once been erroneously recognized will not be extracted again, and as a result, the same mistake as the previous recognition mistake will not be repeated.

In the above embodiment, the types of character patterns are numbers and alphabets, but they may also be katakana, hiragana, kanji, symbols, etc.

Further, although a touch electrode is used as a character pattern input means, other input means may be used. Furthermore, the present invention is applicable not only to electronic wristwatches but also to other electronic devices.

〔Effect of the invention〕

In this invention, when an erroneous recognition occurs as described in detail above, the character pattern input by the next correction operation is recognized from among the characters excluding the erroneously recognized character, and the character pattern is recognized several times. Since the same recognition mistake is not repeated continuously, even if each person has a habit of writing characters, there is no need to change the writing style when inputting corrections, reducing the burden on the user and making corrections easier. This has advantages such as speedy processing and simple correction operations.

[Brief explanation of the drawing]

The drawings show one embodiment of the present invention, with FIG. 1 being a top view of an electronic wristwatch equipped with a character recognition device, and FIG.
The figure shows the circuit configuration diagram. Figures 3A to C show the process by which a vector sequence is obtained when the number "2" is input as a character pattern. Figure 4 shows the standard vector sequence. Figures 5, 6, 7, and 8, which explain the relationship between numerical values and vectors, show standard vector sequences of character patterns with stroke numbers of 1, 2, 3, and 4, respectively. The figure shown in FIG. 9 is a flowchart for explaining the operation. 1...Input section, 3, 4...ROM, 5...
RAM, 6...Arithmetic unit, 1C...Correction key.

Claims (1)

[Scope of Claims] 1. A character pattern input means, a storage means for storing standard patterns corresponding to a plurality of characters, and a character pattern input from the character pattern input means and the standard pattern are compared to determine the character pattern. a recognition means for extracting a character corresponding to the pattern; a correction means for instructing correction of the character recognized by the recognition means; and a correction means for instructing correction of the character recognized by the correction means; A character recognition device comprising: recognition control means for extracting a character corresponding to a character pattern input from an input means from a standard pattern of characters excluding the recognized character.