JPS6068480A - character recognition device - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

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

[Prior art]

In recent years, character recognition devices (IT) have been developed that recognize characters, figures, etc. that are handwritten on a doublet using a pen-shaped jig, and convert them into input information. In this type of character recognition device, if a character pattern is input incorrectly, the user clears it by operating a correction key, and then inputs the opposite character pattern 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 erroneous recognition of the character pattern may be repeated several times in a row. It is necessary to re-enter the 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]

This invention was made against the background of the above-mentioned circumstances, and its purpose is to provide a character pattern that can be quickly corrected when a character pattern penalty occurs, and that also allows easy correction operations. The objective is to provide a recognition device.

[Key points of the invention]

In order to achieve the above-mentioned object, the present invention is configured such that when an erroneous recognition occurs, the character pattern input by the next correction operation is recognized from among the characters excluding the erroneously recognized character, and The main point is to prevent repeated misrecognitions.

〔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 is formed by further arranging transparent touch electrodes in, for example, a 4x4 matrix on a transparent surface glass fixed to the top surface of the watch case. The 16 touch electrodes are arranged on the XY coordinate system, and are
16=256 coordinate positions fEjlA are formed by electrical processing. Also, if you touch the touch electrode with your finger or other human body, will it touch? The contact capacitance component generated at the L pole is detected, and the coordinate position IA is determined by human power, thereby inputting a character pattern.

This type of technology may be utilized in a patent application already proposed by the present applicant (Patent No. 11i'355-35660, title of invention: touch switch device). The input unit 1 is provided with an input end key IB that is operated when inputting one character pattern is completed, and a correction key IC that clears the input character when the inputted character pattern is misrecognized. There is.

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 input s1 in a matrix.

ROM (read only memory) 3 stores a microprogram that controls all operations of this electronic wristwatch, and outputs microinstructions AD, I) A, OP, and NA in parallel. , are respectively applied to the RAM (random access memory) 5 as address data. Further, the microinstruction DA is applied to the processor AM5 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 signals O8,
, O82, X, YlZ, 几, S%G, etc. are output. The microinstruction NA is applied to the address unit 8, and in response, the address unit 8 generates address data for reading microinstructions AD, DA, OF, and NA necessary for the next process from signals d, c, etc., which will be described later. is output and supplied to ROM3.

Vector strings of standard character patterns for characters such as numbers and alphabets are stored as data in the OM 4, and are compared with vector strings of character patterns input from the input section 1 to perform character recognition. In addition, R.O.
Data is read from M4 in accordance with the control signal C8.

The RAM 5 has various registers and is used in various processes such as time measurement processing and character recognition processing performed by the calculation section 6, and data is read and written under control signals O82 and R/W.

The calculation unit 6 executes the various calculations described above under the control signal X. The resulting data is sent to input section 1, display section 2, and RA.
Give it to M5. Also, when executing the janji operation,
A signal d1 indicating the presence or absence of data as a result of the operation and a signal C indicating the presence or absence of carry generation are outputted and supplied to the address section 8.

The SR type flip-flop 9 is set or reset by control signals S and H, respectively, and the control signal S is output at the start of input of each stroke of a character pattern, and the control signal hole is output at the end of input. The set output signal is then input to the AND gate 10 as a control signal. The other end of this AND gate 10 is input with a constant frequency clock output from an oscillation circuit 11, and the clock output from the AND gate 10 is input into a timer section 12 consisting of a counter. This timer unit 12 measures the input time of each stroke (08 hours) and the OF IF period from the end of input of each stroke to the time of input of the next stroke.

The ON time and OFF time obtained in this way are controlled by R and AM5, respectively, through gates 13 that are opened when the control signal G is output.
, are given to 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 z1 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 3 (A), when the character pattern "2" is input, the target Position data is sequentially written into RAM5. And Figure 3 (
As shown in B), when the finger leaves the touch electrode after inputting the character pattern "2", the stroke length is calculated from the coordinate position data written in the RAM 5, and then divided into six equal parts. Then, as shown in Figure 3 (0), 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 operating the input end key IB, the calculated vector string is compared with the coordinate vector string in the ROMJ, and a character pattern that is nl-incrementally similar is output.

5, 6, 7, and 8 respectively show standard vector sequences for each character pattern with a stroke count of 1, 2, 3, and 4, which are stored in the ROM 4. .

Next, the operation of this embodiment will be explained with reference to FIG. 9. When the power is turned on, the operation according to the flow shown in FIG. 9 is executed. First, in step S1, initialization processing,
That is, the flag register F and the stroke number counter S in the box A 1115 are cleared. The flag register F is set to "1" by operating the 1 primary key IC, and the stroke number counter S counts the number of strokes of the - character.

Next, the process proceeds to step S, where it is determined whether or not a character pattern is input from the input unit 1, in other words, whether or not the touch electrode is touched. When a character is removed by touching the touch electrode of the input unit 1 with a finger, the process proceeds to step Ss, and an increment process is executed to add 1 to the contents of the stroke number counter S. Initially, it becomes "1", and one stroke is counted. ■It becomes the value of the minus mark. Next, each coordinate position is sequentially detected as the character is written, and the data of the detected coordinate position is stored in the RA.
Sequentially written to the first stroke area in M5 (
Step S4, S's). And the next step S
In step S6, it is determined whether or not the first stroke has been written and the finger has left the touch electrode. As a result, if writing is in progress, the process returns to step S4 and the operation of acquiring the coordinate position is repeated. Also, when you release your finger after writing the first stroke, this is determined in step S6,
Proceed to step S. Here, RA1vI501
The stroke length l (length) is calculated from each coordinate position data written in the stroke area.

The stroke length calculated in this way is divided into six equal parts in the next step S, six equal points are extracted, and the vectors of each part are determined according to the vectors in Figure 4, and a vector sequence is calculated. (step S). and,
After this vector string is stored in a predetermined register in the RAM 5 (step S+o), the process returns to step S2.

Therefore, a character with a stroke count of 1, for example the number "2"
etc., inputting a character pattern can be completed with one stroke, so the manual end key IB is then operated. As a result, the result in step S2 is No, and the process proceeds to step 812 via step 81-1 in which it is determined whether or not the input end key IB is operated. On the other hand, for each character with a stroke count of 2, 3, and 4, each process of 1 step 82 to S1° is performed twice, three times, and
After the process is repeated four times, the process proceeds to step St2 by operating the input end key IB. For example, the number "2"
As can be seen from FIG. 3(0), the vector sequence obtained from steps 82 to StG when n is input is [175570J.
Then, it is determined whether the contents of the flag register F are "0" or not. Since the initial value of flQ is "0", the process proceeds to step S13, and the memory area M in RAM 5 is cleared. M is a character that is erroneously recognized in the previous character recognition process.
In the next step 81m, input character recognition processing is executed. That is, in this recognition process, the vector string obtained as described above is classified by number of strokes, and the vector string by number of strokes is compared with the standard vector string in ROMJ. The most similar character pattern is extracted from among the characters excluding the 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 rl-7557oJ (see FIG. 3 (0)) obtained by inputting the number "2" as described above, @
As a result of comparison with the standard vector sequence of stroke 1 shown in FIG. 5, the character pattern "2" of standard vector r175500J is extracted. In this case, in the previous character recognition process, when inputting the number "2", it was incorrectly output as "7", and characters excluding this "7" are extracted.
Initially, the contents of memory area M are cleared, so
Recognition processing is performed on all characters.

Therefore, the character pattern extracted as described above is
This is displayed on the display unit 2 (step S1.), and the process proceeds to the next step 816, where it is determined whether the correction key IC has been operated. In this case, if the displayed character is different from the input character and has been misrecognized, the correction key IC is operated. By operating the correction key 10, the process advances to step S1, and after setting the flag register F to 1'', the process returns to step S2.

When the input character pattern is recognized as 'lil mg', the user operates the correction key IC, inputs the character pattern again, and then operates the input end key IB. This causes steps 82 to BHo as described above.
A vector string of the input character pattern is calculated, and then the process proceeds to the state Sst via step 811, but in this case, it is determined NO at step 812.
The process moves to step 818. Here, when a 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, the process proceeds to step SI9, and after clearing the display content, which is "7" in the above example, the recognition process of step 814 is executed.

Therefore, after writing the previous extraction character into the memory area M, step S14 is executed, so the correction key I
After operation C, characters that have been erroneously recognized will not be extracted, 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, hirazuna, 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〕

As explained in detail above, in the case where an erroneous recognition occurs, the character pattern input by the next correct operation is recognized from among the characters excluding the erroneously recognized character. This prevents the same recognition error from being repeated multiple times in a row, so even if each person has a unique way of writing characters, there is no need to hide the writing style when inputting corrections, reducing the burden on the user. , the correction process is performed quickly, and the correction operation is only ffM.

[Brief explanation of drawings]

The drawings show one embodiment of the present invention; FIG. 1 is a diagram of an electronic arm Tokita equipped with a character recognition device, FIG. 2 is a circuit diagram thereof, and FIGS. 1. If you input the number "2" as a character pattern, a diagram showing the difference between the vector string and the vector string. , Figure 5, Figure 6
In Figures 7 and 8, the number of strokes is 1, 2, and 3, respectively.
．． FIG. 9 is a flowchart for explaining the operation. 1...Input section, 3.4...ROM, 5
... HAMsb ... Arithmetic unit, IC...
...Correction key. Patent applicant: Casio Computer Co., Ltd. - Figure 5 Figure 6 Figure 7 Figure 8

Claims (1)

[Claims] a character pattern input means, a storage means for storing a standard pattern corresponding to a plurality of characters, and a character pattern inputted from the character pattern input means and a standard pattern in the storage means are compared to correspond to the character pattern. a correction means for clearing the characters recognized by this recognition means; and a correction means for clearing the characters recognized by this recognition means; A character evangelization device comprising a recognition control means for recognizing characters other than the evangelized characters.