JPH03214380A - Character recognizing device - Google Patents

Abstract

PURPOSE:To substantially erase the part which does not become the object of character recognition in an original document without spoiling its original document by moving the prescribed part of an original character signal stored in a first memory to a second memory at any time. CONSTITUTION:The device is provided with a first memory for storing the prescribed range portion of an original document 14, for instance, an original character signal S1 of a one-page portion and supplying it to its character discriminating parts 16, 19, and a second memory 23 for backing up a first memory 22. In such a state, the prescribed part of the original character signal S1 stored in the first memory 22 is moved to the second memory 23. In such a way, it becomes equal to the case when the part of the original document 14 corresponding to the prescribed part is erased substantially without spoiling the original document 14, and also, becomes equal to the case when its erased part is restored substantially by returning again the original character signal S1 moved to its second memory 23 to the original area of its first memory 22.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a character recognition bag holder suitable for use, for example, in recognizing printed characters and converting them into character codes.

[Summary of the invention]

The present invention provides a character recognition device that includes a document reading section that generates an original character signal corresponding to the density of the original document, and a character identification section that identifies characters corresponding to the original character signal. A first memory that stores the original character signal of the minutes and supplies it to the character recognition unit, and a second memory that backs up the first memory, and the original character signal stored in the first memory is provided. By moving a predetermined portion of the signal to the second memory at any time, it is possible to substantially erase portions of the original document that are not subject to character recognition without damaging the original document.

[Prior Art] For example, in order to automate the process in which a worker picks up type in letterpress printing, a character recognition device is required that recognizes each character in a manuscript created by type printing and converts it into a character code. .

FIG. 6 shows a conventional character recognition device disclosed in Japanese Unexamined Patent Publication No. 62-74181, and in this FIG.
(1) is a document reading section, and from this document reading section (1), an original character signal S1 corresponding to the shading of one page of the document is supplied to a character string cutting section (2). This original character signal S1
The original is divided into dots at a predetermined density, and black dots are expressed as high level ``1'' and white dots as low level ``0.'' However, when the density of each dot is expressed as a multi-bit binary number, There is also.

The character string extraction unit (2) is composed of a first stage preprocessing unit (3), a second stage preprocessing unit (4), and a third stage preprocessing unit (5). The preprocessing unit (3) removes noise and corrects the rotation of the document, and the second stage preprocessing unit (4) separates the character area AR (see Figure 7) from other areas (areas of photographs, drawings, etc.). Only the image data included in the character area AR is extracted, and the third
The character area AR extracted in the pre-processing section (5)
A character string signal S4 corresponding to the character strings API, AR2, . . . included in the character strings is extracted.

In order to extract this character string signal S4, as shown in FIG. )
Expressed in coordinates, the value of “1” or “0” of each dot is expressed as Y
A Y projection signal Sy is generated by projecting onto the axis and calculating the sum. Then, when this Y projection signal Sy is binarized at a predetermined dark value level, sections of high level "l" in this binarized signal are respectively character strings AR1. AR2,...
The character string signal S4 is supplied to the subsequent character cutting section (6).

In the character cutting section (6), for example, the character string signal S4 of the i-th character string AR i shown in FIG. 8A is projected onto the X axis to generate an X projection signal Sχ, and this ×
at the minimum level (value 1) threshold THI is 2{! ! 6 to obtain a coarse cutout signal DTI (Fig. 8C),
By binarizing this X projection signal Sx with a medium level darkness value TH2 (Fig. 8D), a finely cut signal DT2 (
Figure 8E) is obtained. Similarly, by individually generating the Y projection signal Sy only in the section where the coarse cutting signal DTI is high level "1°", the cutting signal in the Y direction can be generated.

Finally, as shown in FIG. 8A, for example, the character "te" becomes a high level "1" inside the circumscribing frame (9) that circumscribes this character, and the separated character "i"
Regarding, the circumscribing frame (II
), (12), a signal with a high level of "1" is obtained, and the basic signal is a signal obtained by successively cutting out only the parts where the signal has a high level of "1°" from the input character string signal S4. This becomes a rectangular cut-out character signal S7.

Incidentally, the fine cutting signal DT2 in FIG. 8E is used when examining the finer structure of each character. In addition, for the separated character “i” in Figure 8A, the circumscribing frame (11), (
12), it is necessary to integrate them later at the character identification stage.

Reference numeral (7) indicates a character recognition section, and this character recognition section (7) takes in the basic rectangular cut-out character signal S7 for each circumscribed frame and performs character recognition. Specifically, first, classification is performed by position, and characters existing in the upper half range (such as "", """, "゜", etc.) and characters existing in the lower half of the character example ARi in Figure 8 are classified. characters (such as ``.'', r.'', r,'') as the first
Pattern matching is performed as a characteristic character, and a corresponding character code (JIS code, etc.) is assigned. If identification is not possible, the width of the circumscribing frame is set to W, the height is set to h, and classification is performed based on the aspect ratio h/w and relative size. That is, classification is performed depending on whether the aspect ratio h/w falls within the range of Q<h/w<0.5 or 1.5<h/w. Furthermore, the width of the average size circumscribing frame is w
R, the height is hR, and the values of vertical relative ratio h/h and horizontal relative ratio W/WR are 0<h/hl<0.5 and 0<
w/WR<0. Classification is performed based on whether or not it falls within the range of 5. Pattern matching is performed using characters that fall within the above range as second characteristic characters.

Further, for characters that are not classified as the first or second characteristic characters, pattern matching is performed with individually stored dot patterns, and if a predetermined degree of matching is obtained, the character code is assigned.

If a character that cannot be recognized still remains, the operations of re-cutting the circumscribing frame to separate it into a plurality of minute circumscribing frames and merging them with the subsequent circumscribing frame are performed. still,
If an unrecognized character ultimately remains, a reject code is given to that character to indicate that it is an unrecognized character.

The character code for one page of the manuscript generated by the character identification section (7) is stored in a predetermined storage device along with information indicating the position and size of the character. Furthermore, the video signal of the character corresponding to the character code is displayed on a display unit (8) such as a cathode ray tube so that the operator can judge whether the recognition result is correct or not.
A group of characters as a recognition result is displayed on the display screen of the display unit (8) in a format corresponding to the document. In this case, a high-intensity rectangular blank is displayed in the portion of the character that cannot be recognized. Therefore, if a character to be corrected or a character that cannot be recognized exists, the operator can input the desired character into that part in the same way as a word processor.

As described above, an original character signal S1 corresponding to the shading of the original is generated, and this signal S1 is cut out using a circumscribing frame circumscribing one character to generate a cutout character signal S7, and a cutout character signal S7 corresponding to the cutout character signal S7 is generated. It can be said that the character recognition algorithm itself, which specifies the characters that are used, is basically established.

[Problem to be solved by the invention]

However, when a character recognition device using this character recognition algorithm was actually set up in an office and used by an operator, it was found that there were various inconveniences in operability.

One of the inconveniences is that if the manuscript contains noise, ruled lines, figures, photographs, etc. that are unnecessary for character recognition, the unnecessary parts must be erased in advance using correction paint, etc. , in order to preserve the original manuscript, it was necessary to make a copy. Furthermore, when it is desired to restore a portion erased by retouching paint or the like, it is necessary to re-centre the original manuscript, which is inefficient.

In view of the above, it is an object of the present invention to make it possible to substantially erase unnecessary portions of a document without damaging the document, and to restore the erased portions at any time.

[Means for Solving the Problems] A character recognition device according to the present invention includes a document reading unit (13) that generates an original character signal Sl corresponding to the shading of an original document (14).
and a character identification unit (16.19) that identifies the character corresponding to the original character signal S1, the original character signal of a predetermined range (for example, one page) of the original document (14) is used. S1 is stored and its character identification section (16.
19), and a second memory (23) that backs up this first memory (22).
), and a predetermined portion of the original character signal S1 stored in the first memory (22) is transferred to the second memory (22) at any time.
23).

[Operation] According to the present invention, the original document (l4) is damaged by moving a predetermined portion of the original character signal S1 stored in the first memory (22) to the second memory (23). This is essentially equivalent to erasing the portion of the original document (14) corresponding to the predetermined portion. Also, the original character signal S1 transferred to the second memory (23) is transferred to the first memory (23) again.
By restoring the erased portion to its original area in the memory (22), it is essentially equivalent to restoring the erased portion.

[Example] Hereinafter, the first example of the character recognition device according to the present invention will be described.
This will be explained with reference to FIGS.

FIG. 1 shows the system configuration of the character recognition device of this example. In FIG. (13
) is the entire page of manuscript (14), for example, 400X40
The dots are separated at a reading density of 0 dpi (dots/inch) to generate an original character signal S1 corresponding to the shade of each dot.

(15) is an image data input/output board, (16) is a host computer, (2l) is a printer, and the image data input/output board (15) supplies a predetermined portion of the original character signal s1 to the host computer (16). At the same time, a printing signal output from the host computer (16) is supplied to the printer (16). (17) is a keyboard for operating the host computer (16);
(18) is a coordinate input unit for inputting various coordinates to the host computer (16), and (19) is a character identification board, in which the host computer (I6) extracts the circumscribed frame of one character from the original character signal S1. The basic rectangular cut-out character signal S7 cut out using the cut-out signal that becomes high level "'l゜" internally is sequentially passed through the character identification board (
19), the character identification board (19) detects the character code C of the character corresponding to the extracted character signal s7.
(or eject code if the character cannot be recognized) is supplied to the host computer (16).

(20) indicates a display device made of a cathode ray tube, and a predetermined area on the display screen of this display device (20) displays the results of recognizing characters for one page of the manuscript (14) in a format corresponding to the manuscript (14). Do as shown in . In addition, this display device (2
The display screen 0) is arranged so that the dot pattern itself of one page or a predetermined portion of the original (14) can be displayed as necessary.

FIG. 2 shows a more detailed configuration of the printer (21) shown in FIG. 1, excluding the processing part. In the image data input/output board (15) shown in FIG. The image data input section (23) has a memory that can store dot patterns for more than one page, and the image data input section (23) is a Pasokanop memory that can also store dot patterns for more than one page of the original (14).
3) Store the original character signal S1 for one page of the original document (14) outputted from the image data input section (22). Further, a desired portion of the original character signal SL stored in the image data manual section (22) is transferred to the hang-up memory (23) at any time, and the desired portion corresponds to a blank sheet with no characters. The original character signal S1 with this desired portion replaced is called the original character signal S2, and a predetermined portion of this original character signal S2 is replaced with an original character signal (for example, zero level "0°"). It is called S3.

In the host computer (16), (24) is a central processing unit (hereinafter referred to as rcPUJ), (25) is a main memory, and (26) is a video signal RAM for the display device (2o) (hereinafter referred to as rVRAM). ”)
, (27) shows a font table consisting of a character ROM that manually inputs a character code and outputs a dot pattern, that is, a font, of a predetermined font corresponding to this character code, and the operator uses the keyboard (17) and the coordinate input unit (18). When various commands, data, and coordinate data are supplied to the CPU (24) via the CPU (24), the CPU (24)
4) controls the overall operation of the character recognition device of this example.

Further, the original character signals S2 and S3 are supplied to the main memory (25) and VRAM (26), respectively, as needed. In this case, CPU (24) and main memory (25)
) corresponds to the character string cutting part (2) and character cutting part (6) in the example in FIG. 6, and is the basic rectangular cut-out character signal S7 corresponding to the inside of the circumscribed frame of one character read from the main memory (25). are sequentially supplied to the character identification board (19),
The character code C transmitted from the character identification board (19) is supplied to the address bus of the font table (27) via the main memory (25), and the font data appearing in the data bus of this font table (27) is sent to the V R It is written in a predetermined area of A M (26). Furthermore, the system comprising the host computer (16), keyboard (17), coordinate system (18), and display device (20) of this example also has the function of a word processor.

In the character identification board (19), (28) indicates a character recognition section, (30) indicates a recognition dictionary section that stores font data of various fonts in correspondence with character codes (JIS codes in this example), The recognition section (2nd) and the recognition dictionary section (30) basically correspond to the character identification section (7) in FIG. The recognition dictionary section (30) of this example is divided into a large classification dictionary section for large classification characters and a subclassification dictionary section for subclassification characters, and the main classification dictionary section has first features classified by position as described above. Relative size of characters and circumscribing frame (aspect ratio h/w
), font data normalized to, for example, 24 dots vertically x 24 dots horizontally, are stored for second characteristic characters classified according to values of vertical relative ratio h/h, I and horizontal relative ratio w/w. . Generally, the general characteristics of a character are also expressed by the dot patterns near each side of the circumscribing frame of the character, so the dot patterns near the four sides of the circumscribing frame of each character are digitized as four-side data (or peripheral data). hand,
The font data of characters (major classification characters) whose four side data fall within a predetermined range may be stored in the major classification dictionary section.

On the other hand, the minor classification dictionary section stores normalized font data of all other characters (minor classification characters) not included in the major classification dictionary section in correspondence with character codes.

(29) indicates a dictionary creation section, and this dictionary creation section (29)
When the dictionary creation mode is set by the operator, determines whether the font data represented by the supplied basic rectangular cutout character signal for one character corresponds to a major classification character or a subclassification character. , when corresponding to major classification characters, the font data is normalized and written into a predetermined character code area of the major classification dictionary section of the recognition dictionary section (3o), and when corresponding to subclassification characters, the font data is normalized. and write it in a predetermined character code area of the subclassification dictionary section of the recognition dictionary section (30). This allows the user to easily create a recognition dictionary section (30) that can handle various fonts.

When the character recognition mode is set by the operator, the recognition section (28) of the character identification board (19) changes the size of the recognition dictionary section (30) when the supplied basic rectangular cutout character signal S7 corresponds to a major classification character. The font data of the classified character section is sequentially sorted in first-in, first-out (F I F
O) Write to register, subclassification statement. When dealing with characters, the font data of the subclassified character part is sequentially stored in 2 FIFOs.
Write to register. Also, in parallel with this operation, the recognition unit (
28) normalizes the dot pattern corresponding to the basic rectangular cutout character signal S7 and sequentially writes it into the FIFO register 3. The recognition unit (28) then uses the dot pattern of the character to be recognized in the third FIFO register and the lth
A series of font data in the FIFO register and the second
By sequentially comparing a series of font data in the FIFO register of , 10 character codes corresponding to the font data closest to the dot pattern of the character to be recognized are generated in descending order of priority, and these character codes are is written into a predetermined area of the main memory of the host computer (16).

To determine the priority, for example, the dosoto pattern of the character to be recognized for each dot of 24 x 24 dots is compared with the font data read from the recognition dictionary section (30), and it is determined whether the values of the two are different. The total sum of the dots that exist is taken as an evaluation value, and the order of priority is set in descending order of the evaluation value. If the evaluation value of the character code with the highest priority is less than a predetermined value, it is assumed that character recognition has been performed, and the character code with the highest priority is set as the character code C of the character to be recognized. The data is written in a predetermined area corresponding to the original (14) in the main memory (25). At the same time, the recognition unit (28) stores the character code C, data indicating the size of the character, and data indicating the position of the character within the average circumscribing frame in the main memory (28).
Do as described in 5). On the other hand, if the evaluation value of the character code with the highest priority exceeds the predetermined value, the recognition unit (2
8) is assumed to be unable to recognize characters! The reject code is stored in the main memory (25) of the manuscript (14)
The data is written in a predetermined area corresponding to the data. The character recognition operation described above is executed in a pipeline manner.

To explain the operation of this example, as shown in FIG. ) shall be deleted.

In this case, the operator first selects C from the keyboard (17).
A command to display the original document is given to P U (24). In response, the CPU (22) writes the original character signal S1 for one page of the original (14) generated by the scanner (13) into the memory section of the image data input section (22), and The character signal S1 is supplied as is to the V RAM (26) as the original character signal S3. Accordingly, the display screen (2) of the display device (20)
In the area (31) of 0A), there is a manuscript (1) as shown in FIG.
The original image of 4) is displayed as a dot pattern.

Next, the operator displays a cross-shaped cursor on the display screen (2OA) at the position corresponding to the coordinate value specified by the coordinate system (18). coordinate person kayuni} (
For example, a pole with two rotation axes is arranged on the bottom of the ball 18), and by urging the coordinate person Kayunino (1B) against a table surface and moving it two-dimensionally, the ball rotates around the two rotation axes. The specified coordinate values are rotated to
It is designed so that it can be changed dimensionally. Then, the operator moves the coordinate operator (18) to move the cross-shaped cursor to the upper left point P of the word "Editorial" and operates the coordinate manual switch of the coordinate operator (7) (18). By doing so, the coordinates of the point P1 are taught to CPU (24). Similarly, the coordinates of point F2 at the bottom right of the word "editorial" are C P U (2
4).

C P U (24) is the point P as shown in Figure 4A.
, and point P2 as diagonal points, and input the image data input section (2) as shown in FIG. 5A.
The part (33) corresponding to the rectangular area (32) of the original character signal S1 written in the memory section (22A) of 2)
) in the storage section (2) of the backup memory (23).
3A) to the corresponding portion (34), and write, for example, low level "0" data corresponding to a blank sheet in the transferred portion. After that, the image data input section (
By writing the original character signal S3 (signal in which part of the original character signal S1 is replaced with low level "0") written in the memory section of 22) to V R A M (26), The display screen (20^) of the display device (20) shows Fig. 4B.
As shown in 《From the manuscript (14) to the heading ``Editorial'' (1)
An image with 4A) erased is displayed.

Also, by writing the original character signal S3 as it is into the main memory (25) as the original character signal S2, the original in the form in which the heading "Editorial" (14A) has been deleted from the original (14) is processed for character recognition. be targeted.

Next, in order to restore the erased heading "Editorial" (14A), the CPU (22) uses a portion (34) of the storage section (23A) of the backup memory (23), as shown in FIG. 5B. The data written in is transferred to the part (33) of the memory part (22A) of the image data input part (22). Then, the original character signal 33 (original character signal S
1 itself) to VRAM (26),
The display screen (20A) shows the original (20A) again as shown in Figure 4A.
14) is displayed as is.

Further, by writing the original character signal S3 as it is into the main memory (25) as the original character signal S2, the entire original document (14) becomes the object of character recognition.

As described above, according to this example, an image data input section (22) having a memory section and a backup memory (23)
is provided, so the image data input section (22)
By simply transferring a portion of the original character signal Sl stored in the bank-up memory (23) and writing the corresponding data on a blank sheet into the transferred portion, the original character signal Sl can be effectively converted without damaging the original (l4). There is an advantage that a desired portion of the original (14) can be erased.

Furthermore, a desired portion of the data transferred to the backup memory (23) is input again to the image data input unit (22).
) There is an advantage in that a desired portion of the erased document can be substantially restored simply by returning it to the memory section.

In addition, in the past, one page of a manuscript had to be divided into multiple character areas to avoid irregular headings embedded in the character area of the manuscript, which sometimes resulted in poor work efficiency. According to the authors, by erasing such irregular headings, character recognition can be performed in principle by specifying one character area for a one-page manuscript (or even a two-page double-page manuscript). There is a benefit of improved efficiency.

It should be noted that the present invention is not limited to the above-described embodiments, and it goes without saying that various configurations may be adopted without departing from the gist of the present invention.

〔Effect of the invention〕

According to the present invention, unnecessary portions of a document can be substantially erased without damaging the document, and the erased portions can be restored at any time.

[Brief explanation of drawings]

FIG. 1 is a front view including a partial perspective view showing the system configuration of a character recognition device according to an embodiment of the present invention, and FIG. 2 is a partial perspective view showing a more detailed configuration of the main part of the example shown in FIG. A configuration diagram including
FIG. 3 is a line diagram showing an example of the original of one embodiment, FIG. 4 is a front view showing changes in the display screen (2OA), FIG. 5 is a line diagram for explaining the operation of one embodiment, and FIG. The figure is a block diagram showing the overall configuration of a conventional character recognition device, and FIGS. 7 and 8 are diagrams for explaining the conventional character string and original rectangle extraction operations, respectively. (13) is a scanner, (14) is a document, (15) is an image data input/output board, (16) is a host computer, (19) is a character identification board, (20) is a display device, (24) is a central processing The unit (25) is a main memory, (28) is a recognition section, and (29) is a recognition dictionary section.

Claims (1)

[Scope of Claims] A character recognition device comprising: a document reading unit that generates an original character signal corresponding to the shading of the original document; and a character identification unit that identifies characters corresponding to the original character signal; A first memory that stores original character signals for a predetermined range and supplies them to the character identification unit, and a second memory that backs up the first memory, and the original character signals are stored in the first memory. A character recognition device characterized in that a predetermined portion of an original character signal is transferred to the second memory at any time.