JPH0291788A - Character recognizing device - Google Patents

Abstract

PURPOSE:To hasten the processing time and to reduce the erroneous recognition ratio by jump-reading the character information up to the leading character information of a next line when the result of the character recognition is the jump-reading information. CONSTITUTION:A mark 102 shows a mark sheet detecting mark 101 or a reading starting position mark to instruct the reading starting position of respective lines to record the character information and a mark 103 shows a line termination mark to instruct the termination of respective lines to record the character information. A mark 104 shows the line termination identifying mark for jump- reading the succeeding character to instruct that the succeeding character information is not written in respective lines. Consequently, when the line termination identifying mark 104 is not written in the line, the information for 7 characters which can be written in the line becomes all the object of the character recognition. When the result of the character recognition is the jump-reading information, the character information is jump-read up to the leading character information of the next line. Thus, without executing the unnecessary character recognition, the erroneous recognition ratio is reduced.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a character recognition device, and for example, to a character recognition device that recognizes characters written on a sheet.

[Prior Art] Conventionally, in this type of device, when character recognition is performed based on character information written on a sheet, for example, a mark sheet, when an end mark is detected for each line, the process proceeds to character recognition on the next line. I have to.

[Problems to be Solved by the Invention] However, in the conventional example described above, character recognition is always performed for the number of digits set in one line determined by the format of the mark sheet. For this reason, there are drawbacks as described below.

, the unwritten portion after the last character in each line is also considered as a valid area for character recognition, which (1) increases the rate of misrecognition.

(2) Extra processing time is required.

Such a problem arises.

The present invention has been made in view of the above-mentioned drawbacks of the prior art, and its object is to provide a character recognition device that reduces the rate of misrecognition without performing unnecessary character recognition.

[Means for Solving the Problems] In order to solve the above-mentioned problems and achieve the purpose, a character recognition device according to the present invention is provided with a character recognition device in which at least an entry start position and an entry end position of character information are specified on a line-by-line basis. A character recognition device that performs character recognition using a sheet containing a sheet, the character recognition means performing character recognition based on character information including skip information of subsequent character information, and a case where the result of the character recognition is skip information. and a skipping means for skipping character information up to the first character information of the next line.

Further, it is preferably characterized by having a communication function.

[Operations] According to the above configuration, the character recognition means performs character recognition based on character information including skip information of subsequent character information, and the skip means recognizes the next character when the result of the character recognition is the skip information. Character information is skipped to the first character information of the line.

[Embodiment] Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings. In this embodiment, a character recognition device that is connected to a telephone network and is capable of transmitting and receiving image information will be described.

FIG. 1 is a block diagram schematically showing an embodiment of a character recognition device according to the present invention. In the figure, reference numeral 1 indicates the character recognition device of this embodiment.

2 indicates a CPU that controls the entire device. Reference numeral 3 indicates a ROM that stores a control program, an error processing program, and a program according to the flowchart shown in FIG. The RAM used is shown. Reference numeral 5 indicates an image scanner for optically reading a transmitted document such as a mark sheet, and 6 indicates a memory for storing image data read by the image scanner 5 and for storing received data. Reference numeral 7 indicates a character recognition unit that recognizes characters of image data stored in the memory 6 and encodes them. The code data character-recognized by the character recognition section 7 is temporarily stored in the memory 6 as transmission data. The character recognition unit 7 also stores matching data for matching with image data.

Further, 8 indicates an operation section equipped with various operation keys used during transmission, etc., and 9 indicates an I10 controller of the operation section 8. 1O indicates a printer section that records characters on recording paper based on the received data stored in the memory 6;
indicates a modem that performs data communication with a destination terminal via a subscriber line 20 of a telephone network. Reference numeral 12 indicates a path line for transmitting address signals, data, control signals, etc. within the device.

FIG. 2 is a diagram showing an example of a mark sheet of this embodiment. In the figure, 100 indicates the mark sheet of this embodiment. Reference numeral 101 indicates a mark sheet detection mark printed at the top of the sheet to indicate that the document is a mark sheet. Reference numeral 102 indicates the mark sheet detection mark 101 or a successive start position mark indicating the readout start position of each line in which character information is recorded. Further, 103 indicates a line end mark indicating the end of each line in which character information is recorded. Reference numeral 104 indicates a line end identification symbol (inverted characters are used in this embodiment) for skipping subsequent characters to indicate that no subsequent character information is written in each line. If this line end identification symbol 104 is not written in the line, 7
All character information is subject to character recognition.

Next, the operation of the character recognition device 1 according to this embodiment will be explained.

FIG. 3 is a flowchart explaining the operation of the CPUI of this embodiment. Note that this flowchart shows processing at the time of transmission.

First, when a document image is read by the image scanner 5, the read document image is stored in the memory 6 as image data (step St). Then, a mark sheet detection mark is searched from the image data in the memory 6 (step S2). If a corresponding mark is detected in this search, the process proceeds to step S5, and if not detected, facsimile communication is performed using a document other than a normal mark sheet, and the process ends (step S4).

Further, in step S5, the second reading start mark 102 is detected from the image data on the memory 6, and the successive image data start position is detected in the first column of the first line in the area where character information can be written. Set (step S5).

Then, image data is read from the successive start position (step S6). Since the read image data does not become the line end mark 103 at the beginning of the line, the character recognition unit 7 determines which character the image data in the first digit corresponds to.
The characters are recognized (step S8). Here, if the result of character recognition is an inverted character, this is identified as a line end identification symbol, and the process proceeds to step S12 (step S9). If it is recognized in step S9 that it is not a line end identification symbol but a normal character (numeric character), it is stored in the memory 6 as data for transmission. Then, set the successive output position of the image data from the memory to the next digit of the same (step 5).
IO). For example, in the case of the mark sheet 100 in FIG. 2, the character information "1" and "°2" start from the first column of the first row.
, and are recorded in reverse order. Therefore, image data is processed by this device.

1” and “2” as described above from step 86 to step SI.
The process of O is repeated, and when the reversed character in the image data is identified in step S9, the process proceeds to step S12 as a line end identification symbol. In step SL2, it is determined whether character recognition for -sheets has been completed. This determination method is based on the assumption that character recognition for one sheet is completed when the image data identified in step S9 is the final data in the seventh row at the end. For example, mark sheet 100
If the line end identification symbol is not entered as in lines 2, 4, and 6, the line end mark 103 is entered in step S7.
After detecting , the continuation start position 102 of the next line is detected and the continuation position is set in the first column of the line (step 512
). If the end mark 103 detected in step S7 is the mark of the last line, it is determined in step S11 that character recognition for -sheets has been completed. In this manner, when it is determined in step Sll that character recognition for -sheets has been completed, the transmission data in the memory 6 is read out and transmitted from the modem 11 to the destination terminal (step 513).

As described above, according to this embodiment, only necessary character recognition is performed without unnecessary character recognition on the sheet, so that it is possible to obtain the effects of speeding up the processing time and reducing the false recognition rate. can.

Now, in this example, the road end identification symbol is inverted, but
The present invention is not limited to this, but for example,
It may also be a character such as

Further, the number of digits to be skipped over several lines may be set by a combination of a path end identification symbol and a number. In this case, the path end identification symbol is expressed in reverse characters and the number of digits to be skipped is expressed as a natural number ``1'' to 9°.For example, if 8 digits are to be skipped, it is written as reverse characters +8.

[Effects of the Invention] As described above, according to the present invention, it is possible to obtain the effects of speeding up the processing time and reducing the false recognition rate.

[Brief explanation of the drawing]

FIG. 1 is a block diagram schematically showing an embodiment of a character recognition device according to the present invention, FIG. 2 is a diagram showing an example of a mark sheet of this embodiment, and FIG. 3 is an operation of the CPU 1 of this embodiment. It is a flow chart explaining. In the figure, 1...Character recognition device 1.2...CPU, 3.
...ROM14...RAM, 5...Image scanner, 6...Memory, 7...Character recognition unit, 8...Operation unit, 9...I/○ controller, 10...Printer part, 11... modem, 12... pass line, 20
...Subscriber line, 100...Mark sheet, 101
. . . mark sheet detection mark, 102 . . . reading start position, 103 . . . path end mark, 104 . . . path end identification symbol.

Claims (2)

[Claims] (1) A character recognition device that performs character recognition using a sheet in which at least the entry start position and entry end position of character information are specified on a line-by-line basis, 1. A character recognition device comprising: a character recognition device that performs character recognition based on the character recognition; and a skipping device that skips character information up to the first character information of the next line when the result of the character recognition is skipping information. (2) The character recognition device according to claim 1, characterized in that it has a communication function.