JPS63211480A - Optical character reader - Google Patents

Abstract

PURPOSE:To obtain only a correct recognition result by fetching selectively a result of recognition of a character when a speed by which a character coordinate is varied is within a limited range. CONSTITUTION:An image of a form 3 is inputted by an image sensor 6, and a binary signal is obtained by a control/binarization circuit 7. By an each character recognizing means 51, each character in a visual field is recognized and sent to a conformity speed result selecting means 54. The each character recognizing means 51 derives a character coordinate of a recognized character, as well, and it is sent to a character coordinate memory 52 and a speed deciding means 53. A speed deciding means compares a character coordinate P2 at the time point T2, and a character coordinate P1 at the time point T1 obtained through the character coordinate memory 52, and when a speed V12 which is varied from P1 to P2 is within a limited range, a signal of OK is sent to a conformity speed result selecting means 54, and the conformity speed result selecting means 54 outputs the corresponding recognition result. When the signal of OK from the speed deciding means 53 is not obtained, the conformity speed result selecting means 54 throws away the recognition result.

Description

[Detailed Description of the Invention] [Field of Industrial Application] The present invention is capable of scanning characters, symbols, etc. (hereinafter, only characters will be described as a representative, but the same applies to symbols as well) by scanning paper with a hand-held scanner. The present invention relates to an optical character reading device that reads ``characters''.

[Conventional technology]

At supermarkets, department stores, etc., PO3 (Point of
5ales) system is widespread. Hand-held optical character readers are often used in this POS system.

As such a device, the present applicant has filed a patent application for the device shown in FIG. 2 as Japanese Patent Application Laid-open No. 41474/1983.

In FIG. 2, reference numeral 1 is a scanner, and with hand 2, paper 3 is
It reads the characters stored on the paper 3 just by placing it on the paper. The paper 3 is, for example, a price tag on which information for a POS system is stored. 4 is a light source, 5 is a lens system, and 6 is an image sensor, which requires a field of view for at least one line of characters stored on paper 3, and in the illustrated example, one line horizontally and one vertically. The field of view is about three times that of text. Reference numeral 7 denotes a control/binarization circuit that converts the analog signal that is the output signal of the image sensor 6 into binary signals corresponding to the character area and the background area, respectively, and sends the signals to the memory 8. The memory 8 stores the binarized signal of the entire field of view of the image sensor 6.

Confirmation processing is performed from the binarized signals stored in the memory 8, but in the illustrated example, only the binarized signals in which the characters are correctly within the visual field are subjected to the confirmation processing. That is, the third
The figure shows an example of scanning with the image sensor 6 and converting it into binarization, and this figure shows a case where characters are correctly included in the field of view 17. FIG. 4 shows a case where scanning is performed with characters protruding from the visual field 17. In this case, the recognition process described in detail later is not performed, and as the scanner 1 moves, the image sensor 6 scans again, binarizes it, and stores the binarized signal in the memory 8 to improve the reading speed. ing. Note that in FIGS. 3 and 4, some vertical lines indicating pixel divisions are omitted.

The visual field position detection circuit 9 determines whether or not to perform recognition processing. That is, the visual field position detection circuit 9 operates in parallel with storing the binary signal into the memory 8, and it is determined whether or not recognition processing is performed almost at the same time as the storage of the binary signal into the memory 8 is completed. is making a judgment. Furthermore, when performing recognition processing, the visual field position detection circuit 9 does not process the entire visual field;
The recognition area is determined so that only the area where characters exist is recognized.

An example of a specific configuration of the visual field position detection circuit 9 is shown in FIG.
The determination circuit 22 includes a ROM 25 and a register 26.

Each row OR circuit 21 performs an OR operation for each row between the second-order pixels (19 in FIG. 3, from column Bt to column 13u) approximately in the horizontal center of the field of view of the image sensor 6. That is, when a binarized signal as shown in FIG. 3 is sent from the control/binarization circuit 7, first, the binarized signals corresponding to columns Bq of rows t and p are sequentially output from column B1 of row 51. memory 8
At the same time, the logical sum of the binarized signals in each row from the Bt column to the Bu column is calculated by each row logical sum circuit 21.

To further comment, the register 24 is first cleared, and when the signal in the Bt column of the 51st row is input to the OR gate 23, it is ORed with the output signal of the register 24, and the result is stored in the register 24. , Bu columns, the result of the logical sum operation of 51 rows will be stored in the register 24. When the logical sum of up to column 13u is determined, the contents of the register 24 are sent to the determination circuit 22, and at the same time, the register 24 is cleared. As a result, 51
The result of the logical sum from row t to row p will be sent to the determination circuit 22. Based on the result of the logical sum for each row, it can be determined whether or not there is a binarized "black" in each row.

The configuration and operation of the determination circuit 22 to which a signal representing the result of the logical sum is supplied are as follows.

That is, the signal representing the result of the logical sum of each row in the determination circuit 22 is input to the ROM 25, and the contents successively output from the ROM 25 are stored in the register 26. Since the state transition indicating a change in the black and white state is coded and written in the ROM 25, the register 26 stores the black and white state up to that row. Signals from the register 24 indicating the result of the logical sum of the next row and the register 26 indicating the previous state are input to the ROM 25, and the signal of the new state is stored in the register 26. SET, EN in ROM25
D. A code corresponding to the CLEAR signal is written. When the signal SET changes from white to black, EN
D is output when there is black (responsible for the height of the character) and then changes to white, and the character position is from the SET line to the END line. On the other hand, when the signal SET and the signal END are not output up to the Lp row, which is the bottom row, the C
The LEAR signal is output to the control circuit 16 and the control circuit 1
6 clears memory 8. In this way, subsequent recognition processing is not performed, and a new binarized signal is acquired by scanning again.

In the above example, when calculating the logical sum for each row,
The reason why only the central part of the field of view is used instead of the signals of all horizontal rows is to prevent the influence of noise, such as when the paper 3 is smaller than the field of view or when black marks are printed on the paper 3 outside the characters to be read. This is to minimize it as much as possible. When the white of the paper 3 is sufficiently larger than the field of view, the logical sum of all horizontal columns may be taken.

The new line detection circuit 10 determines the character position from the signals SET and END sent from the visual field position detection circuit 9, and compares it with the character position determined by the SET and END signals sent in the next scan, and determines the amount of change in the character position (in pixels). number) or signal CLEA
A judgment is made based on whether the character string has protruded once from the field of view 17 using R, and if it is determined that a new character string exists, a signal NEW is sent to the recognition processing circuit 15. After the signal NEW is sent, the next recognition process is performed.

With this new line detection circuit 10, when reading a character string with more lines than the field of view, it is only necessary to move the scanner 1 from top to bottom or from bottom to top.

That is, since the scanner 1 is placed on the paper 3 and the characters are read,
If left in place for a long time, the same portion will be scanned and read over and over again, but the breakage detection circuit 10 prevents this.

Next, cutting out one character will be explained.

Since the binarized signal stored in the memory 8 is the entire field of view of the image sensor 6, the amount of data has a larger number of pixels both vertically and horizontally than the number of pixels that can be processed by the recognition processing circuit 15 that recognizes and processes one character. In other words, it is necessary to convert each character into a binary signal.

The number of pixels that can be processed by the recognition processing circuit 15 will be explained assuming that the number of pixels that can be processed by the recognition processing circuit 15 is n horizontally and m vertically (column direction) in FIG.

First, a disulfide signal of P pixels in the total field of view 17 (n horizontally and vertically) is transferred to the one-digit buffer 11 . That is, the binary signals from the B1 column to the Bn column in the L1 to Lp rows are one-digit buffer 1.
It is stored in 1.

The vertical position detection circuit 12 detects the vertical position of one character in the binary signal of the one-digit buffer 11 to reduce the number of recognition processes. The vertical position detection circuit 12 determines the vertical position of the character,
The number m of vertical pixels that can be processed by the recognition processing circuit 15 (determined so that the character position is located approximately in the center) is determined. As a result, the vertical direction m is determined from the binary signal stored in the - digit bus sofa 11, and 1 character data mxn is determined.
Transfer to character buffer 14. In the example shown in Figure 3, L
The binarized signal contained in the area from rows I to Lm and columns B1 to Bn is transferred to the single-character bath sofa 14 as one-character data.

The lateral position detection circuit 13 determines the horizontal position of the binarized signal to be stored when the next binarized signal is stored in the negative digit buffer 11. At this time, the characters may be moved horizontally one pixel at a time and stored in the minus digit buffer 11, but the same character may be stored many times, which takes a long processing time. Therefore, the horizontal position detection circuit 13 detects the number of pixels up to the next character, shifts it horizontally by this number of pixels, and
, the binarized signals of the vertical p pixels are stored in the one-digit bath sofa 11.

The contents of the one-digit buffer are, for example, in Figures 6(a) and (b).
), (C1).

The recognition processing circuit 15 recognizes a single character from the binary data stored in the single character basso 14, and may be a known one such as that described in Japanese Patent Publication No. 59-6418. extracts feature data of character constituent parts for each row or column in the vertical and horizontal character areas, and outputs character recognition results corresponding to the type and appearance order of this feature data.

[Problem that the invention seeks to solve]

In conventional optical character reading devices, when reading a character string with more lines than the field of view, it is sufficient to simply move the scanner 1 from top to bottom or from bottom to top, but the movement speed at that time is too fast. In this case, the character image captured by the image sensor 6 may become blurred, and correct recognition results may not be obtained. Inability to obtain a correct recognition result is due to unreadable results (generally called rejects) and misreadings (generally called rejects).
misrecognition). If the sheet cannot be read, the recognition processing circuit 15 outputs a code indicating the beam jet, and the operator can immediately recognize the sheet by applying the scanner to the sheet again. In the case of incorrect recognition, for example, even if the character "7" is written on the paper, the recognition processing circuit 15 outputs a code indicating "1", so the operator can read the recognition result from the recognition processing circuit 15. You cannot tell that it is a misrecognition just by observing it. Therefore, in order to obtain a reliable recognition result, when reading paper 3 while moving the scanner, the operator must perform the recognition process to check whether erroneous recognition has occurred due to the movement speed being too high. The operator must compare the output results of the circuit with the paper, which places a heavy burden on the operator.

The present invention was devised in view of this point, and aims to obtain only correct recognition results by discarding recognition results obtained when the moving speed is so high that it may cause erroneous recognition.

Depending on the use of the optical character reading device, the present invention can also be used for the following purposes. The purpose is to limit the movement direction of the scanner to one direction when reading a character string with more lines than the field of view. In conventional optical character reading devices, the lines captured by the scanner are read and output in order, so the output order of the lines is different when the scanner is moved from top to bottom and when it is moved from bottom to top. From the standpoint of using the scan results, it is easier to process them if the output order of the lines is uniquely determined.
If it is moved in the opposite direction, it must be made so that it cannot be read.

[Means for solving problems]

FIG. 1 shows the configuration of the present invention.

Reference numeral 1 denotes a scanner, which is placed on paper 3 with hand 2.

4 is a light source, 5 is a lens system, 6 is an image sensor, and at least one line of characters written on paper 3 is required. Reference numeral 7 denotes a control/binarization circuit which converts an analog signal, which is an output signal of a photoelectric conversion element in the image sensor 6, into a binary signal corresponding to a character area and a background area, respectively. Reference numeral 51 denotes a means for recognizing a character included in the field of view from a recognition signal and determining the position (character coordinates) of the character within the field of view. Reference numeral 52 denotes a character coordinate memory, which stores the character coordinate P at a certain time point T+, and sends Pl to the speed determining means 53 at a time point T2 different from T.

The speed determination means compares the character coordinates P2 and Pl at T2, thereby changing the speed from P+ to P! Speed of change to ■1.
This is a means of determining whether or not the value is within the limit range. The suitable speed result selection means 54 is means for selectively taking out the character recognition results when V+Z is within the limit range, and
When t is not within the limit range, the recognition result of is discarded. Reference numeral 55 denotes a means for outputting 56 only once for each line of characters that has come into view.

Regarding the specific example of the one-line output means, in addition to the method of repeatedly obtaining recognition results from the matching speed result selection means 54 for characters in the - line and obtaining the output 56 only - times from among them,
As described in the embodiment, there is also a method of stopping the operation of each character recognition means once a recognition result is obtained from the suitable speed result selection means 54.

[Effect]

An image of the paper 3 is captured by the image sensor 6,
A binary signal is obtained by the control/binarization circuit 7. Each character recognition means 51 recognizes each character within the field of view and sends the result to the matching speed result selection means 54.

Each character recognition means 51 also obtains the character coordinates of the recognized character, and the processing of 0 or more is carried out multiple times, which is sent to the character coordinate memory 52 and the speed determination means 53.
The character coordinate P8 at time t is compared with the character coordinate P at time T1 obtained through the character coordinate memory 52, and Pl
It is determined whether the speed V12 changing from to P2 is within the limit range. If VI! If it is within the limit range, the speed determination means 53 sends an OK signal to the adaptive speed result selection means 54, and the adaptive speed result selection means 54 outputs the corresponding recognition result. The suitable speed result selection means 54 discards the recognition result when an OK signal is not obtained from the speed determination means 53.

Through the above processing, a recognition result can be obtained from the adaptive speed result selection means 54 only when the moving speed of the scanner is within the limit range. When the scanner continues to be applied to the same line, the binarized signal is output by the single line output means 55 which repeatedly contains the same line, and the recognition result is obtained as an output 56 only once for each line on the paper.

〔Example〕

FIG. 7 shows an embodiment of the present invention. In the figure, the parts numbered 1 to 16 have the same functions as the parts with the same numbers in the description of the prior art in FIG. However, 8.11.12.
13.14.15.16 are each character recognition means 51 in FIG.
This is an example of S
While the R flip-flop 75 outputs the NEW' signal, the process of recognizing each character in the field of view is repeated. The image sensor has a long field of view in the horizontal direction, and when the number of lines written on the paper 3 is greater than the number of lines that can be seen at one time, the scanner 1 is moved up and down (in the Y direction) to read the paper. In this case, since there is no need to move the scanner 1 left and right (in the X direction), the speed determining means also compares and considers only the Y coordinate of the character. Therefore, the Y coordinate of the character is taken out from the vertical position detection circuit 12 and sent to the character coordinate memory 71 and the speed determination section 72.

74 and 75 are gates and SR flip-flops for outputting the recognition result - times for one line of characters that come into view. Explain what happens when a character enters your field of vision, following +@.

When a character enters the field of view, its position is determined by the field of view position detection circuit 9, and in response to the 5ET-END signal, the new line detection circuit 10 determines that a new line has entered the field of view and outputs a NEW signal. The NEW signal is transmitted to the set input of the SR flip-flop 75, and the NEW' signal is output from 75. 11.12.13.1 by the NEW' signal.
The sections 4.15.16 operate to recognize each character in the field of view from the binarized signal stored in the memory 8. The process of capturing the binarized signal of the entire field of view into the memory 8 and recognizing each character is performed repeatedly while the NEW' signal is output.The Y coordinate of the 0 character is transferred from the vertical position detection circuit 12 to the character coordinate memory 71. and is sent to the speed determination section 72. The speed determination unit 72 compares the Y coordinate Y1 of the character at the time T stored in the character coordinate memory with the Y coordinate Y2 of the character directly obtained from the vertical position detection circuit 12, and determines the speed ■1 at which the character changes from Y to Y2. If □ is within the limit range, an OK signal is output.

In response to the OK signal, the adaptive speed result selection unit 73 outputs the corresponding recognition result. Further, the OK signal is transmitted to the set input of the SR flip-flop knob 75 via the OR gate 74. As a result, the NEWo signal stopped and 11
．． Each part of 12, 13, 14, 15, and 16 stops operating. In other words, after the recognition result that has entered the field of view is output once from the adaptive speed result selection section, 11.12.13.14
．． 74.75 Since each part of 15.16 is not working, the recognition results for that line are not duplicated.
realizes the function of the one-line output means 55 in FIG. A line appeared in the field of view, but the scanner was moving too fast.
If the line moves out of the field of view before an OK signal is received from the speed determination section 72, the field of view position detection circuit 9 sends C
The output of LEAR is transmitted to the reset input of SR flip-flop 75 via OR gate 74 . As a result, the NEW' signal stopped and 11.12.13.14
．． Each part of 15.16 stops working.

The adaptive speed result selection section 73 can be realized by, for example, a FIFO buffer memory. The recognition result from the recognition processing circuit 15 is temporarily stored, and when an OK signal is received from the speed determination section 72, the recognition result is output. If no OK signal is received from the speed determination unit 72, the FIFO buffer memory is reset,
All you have to do is erase the contents of the FIFO buffer memory.

An embodiment of the character coordinate memory 71 and the speed determination section 72 is shown in FIG. The Y coordinate of the character is obtained for each character in the visual field, but here, the Y coordinate L7 of the leftmost character in the visual field is stored in the register 81, and the Y coordinate tlRv of the rightmost character is stored in the register 82.
Take it out and proceed with processing.

Registers 83 and 84 are examples of the character coordinate memory 71, and 83 stores the Y coordinate of the leftmost character, and 84 stores the Y coordinate of the rightmost character. 85 to 94 is the speed determination section 72
This is an example. The timer 85 measures the elapsed time Tlt from the time when the Y coordinate of the character is written in the registers 83 and 84 until the coordinate value is used in the speed determination process. When the timer overflows, that is, Tlz is Ta a
When X is exceeded, the timer value becomes 0. 86 and 87 are subtracters, which determine the amount of change in the Y coordinate. register 8
3. Let the Y coordinates in 84 be L'1M, RV+,
The Y coordinate in register 8L 82 is Lv□, RV
□, the output Lv, t, RVlt of 86.87 is,
Lvrz −Lvz−Lv+ RV12 ”” Rvx Ry+. Now, the upper limit of the speed limit range is V 11aX,
Let V m i a be the lower limit, and let Tlz be the time from when the value is written to the Y coordinate in register 83.84 until the value of the Y coordinate of the character in another visual field is obtained in register 8L 82, then the Y coordinate is Upper limit D of the limit range of the amount of change
amx and the lower limit D atn are D 111111 =
V+ss* x T+zData −Vmrn
88.89, found by X T'+z, is this D□x
, D+mi*. 90.9L 9
1.92.93 is a comparator that determines whether the amount of change in the Y coordinate satisfies this limit range, and Lvrz <DIIIK RYI! It is determined whether <DII□ Darn <Lvrz Date <RV12. And when these four inequalities hold, it is OK by AND gate 94
signal is output. - When the determination process is completed, the contents of registers 81 and 82 are copied to registers 83 and 84, the timer is initialized, and the next speed determination process is prepared.

The upper limit T of the time that can be measured by the timer, □ is from 11 to 16 in Figure 7.
The time T CY CL a required for the means for recognizing each character to finish recognizing the front part of the line that comes into view is set to be slightly larger than the time T CY CL a. For example, TcycL* < T
Make sure that smx < 2 can be done.

When a line enters the field of view and is recognized for the first time, enough time has passed since the previous recognition, so the timer 85 has overflowed, and the timer records the elapsed time as Tlz-0. The time is output. in this case,
The outputs of the multipliers 88 and 89 become DII□-D, , l-0, and since one of the outputs of the comparators 90 and 93 is always false, no OK signal is output. That is, the recognition result for a row obtained only after the row enters the visual field is never output from the matching speed result selection unit 73.

In the above explanation, speed is judged using the Y coordinate LV of the leftmost character and the Y coordinate RY of the rightmost character in the field of view, but the change amount L□2 of the Y coordinate of the leftmost character and the rightmost character Y of
If it is expected that the change in coordinates i1R□2 is not significantly different, that is, if it is expected that the scanner can be moved vertically and almost parallel without rotating, then the amount of change in the Y coordinate of the leftmost character is LY12, Alternatively, the speed may be determined using only the change i1R□2 in the Y coordinate of the rightmost character.

The speed limit ranges V ++i++ and Vlllllll when the movement direction of the scanner 1 that can read characters is limited to one direction (from top to bottom or from bottom to top) will be explained. If the direction of the Y coordinate is taken from top to bottom, the amount of change in the Y coordinate when moving the scanner from top to bottom is positive. Therefore, when limiting the movement direction of the scanner 1 that can read characters from top to bottom, 0≦v11. It is sufficient to set ≦v11□ (set the limit range so that it is not negative)
. Conversely, if you want to limit the movement direction of the scanner 1 that can read characters from bottom to top, it is sufficient to set V-r, l≦Vaax≦0 (set the limit range so that it is not positive).
.

In the embodiment shown in FIG. 7, speed determination is performed only with respect to the amount of change in the Y coordinate. This is because when using the optical character reading device of this embodiment, the scanner is not moved in the X direction.

In an optical character reading device in which the scanner is used to move in the X direction as well, the present invention can be applied if the speed is determined also for the amount of change in the X coordinate of a character.

(Effects of the Invention) According to the present invention, it is possible to realize an optical character reading device that does not output recognition results even if the scanner moves too fast.Thereby, confirmation of recognition results when the moving speed is too fast can be realized. This eliminates the need for additional work and allows the scanner to be moved while reading characters with peace of mind, significantly reducing the operational burden.

Furthermore, by appropriately setting vll, 7, ■□, it is possible to realize an optical character reading device that can recognize characters only when they are moved in one direction. As a result, recognition results will not be output even if you make a mistake and move the scanner in the opposite direction, making it possible to uniquely determine the order in which recognition results are obtained, simplifying the processing system that uses recognition results, and reducing the number of blinds. be able to.

[Brief explanation of the drawing]

FIG. 1 shows a configuration example of an optical character reading device according to the present invention, FIG. 2 shows a configuration example of an optical character reading device according to the prior art, and FIG.
5 and 4 are explanatory diagrams conceptually showing the field of view of the image sensor, FIG. 5 is a block diagram showing the specific configuration of the field of view position detection circuit, and FIG. 6 (from al (C1 is a single character) An explanatory diagram conceptually showing the contents of the memory, FIG. 7 is an embodiment of the present invention, and FIG. 8 is an embodiment of the character coordinate memory and speed determination section. 1. Scanner, 2. ...Hand, 3...
...Paper, 4...Light source, 5...Lens system, 6...Image sensor, 7...
Control/binarization circuit, 8...Memory, 9...
...Visual field position detection circuit, 10...New line detection circuit, 11...-digit buffer, 12...Vertical position detection circuit, 13...Horizontal position detection circuit, 14
...Character buffer, 15...Recognition processing circuit, 16...Control circuit, 17...
Field of view, 18...-Number of horizontal pixels in character recognition processing, 19...Pixels that are ORed in the visual field position detection circuit, 21...Normal sum circuit for each row, 22...
・Judgment circuit, 23...OR gate, 24...
...Register, 25...ROM, 28...
...Register, 51...Each character recognition means, 5
2...Character coordinate memory, 53...Speed determination means, 54...Applicable speed result selection means, 5
5...-Line output means, 56...Final output of recognition results, 71...Character coordinate memory,
72... Curving speed determination unit, 73... Applicable speed result selection unit, 74... OR gate, 75...
・SR flip-flop, 81.82.83.84・
...Register, 85...Timer, 86.8
7... Subtractor, 88.89... Multiplier, 5O19L 92) S3... Comparator, 94.
...and gate. Patent Applicant Sumitomo Electric Industries Co., Ltd. Agent Kama 1) Letter 2 1CI Figure 2 May 18, 1988 26 Name of Invention Optical Character Reader 3, Relationship with the Amendment Person Case Address of Patent Applicant 5-15, Kitahama, Higashi-ku, Osaka Name (8 Ne) (213) Taihide Denki Kogyo Co., Ltd. 4, Agent address: 1-18-12 Nihonbashi, Minami-ku, Osaka 542 "Detailed explanation of the invention in the specification""Confirmationprocessing" on the 10th and 12th lines of the 4th page of the detailed description will be corrected to "recognition processing". (2) "Recognition processing" on the 5th line of the 16th page of the details Correct "Single-line output means 55" to "Single-line output means 55". (3) "Set input of 75" on the 9th line from the bottom of No. 18
Correct it to "75 reset input". (4) Change “90, Sl, 91” in the fourth line of page 21 to “
Corrected to ``90, SL,''. (5) The missing "front section" on page 21 will be corrected to "all." (6) "90, S3's" on the 8th line from the bottom of No. 22
Correct it to "90 to 93".

Claims (4)

[Claims] (1) In a hand-held optical character reading device that optically reads characters, symbols, etc., an image sensor is formed by arranging photoelectric conversion elements in a planar manner, and can capture multiple characters, symbols, etc. for one line within its field of view. a binarization circuit that converts the analog signal output from the photoelectric conversion element into a binary signal corresponding to a character area and a background area; and a binarization circuit that recognizes each character in the visual field from the binarized signal. , means for determining the position of the character within the visual field (hereinafter referred to as character coordinates); a character coordinate memory that stores the character coordinate P_1 at a certain point in time T_1; A speed determination means for comparing character coordinate P_2 and character coordinate P_1 stored in a character coordinate memory and determining whether a speed V_1_2 changing from P_1 to P_2 is within a limited range; When V_1_2 is within the limited range, the character recognition result can be output, but when V_1_2 is not within the limited range, the character recognition result is output. An optical character reading device that is characterized by the fact that (2) In the optical character reading device according to claim 1, the character coordinates used in the speed determination means are the character coordinates of the rightmost character and the leftmost character of the character line in the field of view. An optical character reading device characterized by: (3) In the optical character reading device according to claim 1 or 2, the horizontal direction of the character line is the X direction, and
An optical character reading device characterized in that, assuming that the direction perpendicular to the direction is the Y direction, the character coordinate used in the speed determination means is only the Y coordinate. (4) In the optical character reading device according to any one of claims 1 to 3, the speed determining means has a speed limit range in the Y direction that is one of positive and negative directions. reading device.