JP2001101338A - Picture processor, picture processing method and computer readable memory - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a picture processor and a picture processing method, which can efficiently execute a post-processing on a character recognition result, and to provide a computer readable memory. SOLUTION: A character recognition circuit 109 recognizes a character in an inputted original picture. A character code corresponding to the recognized character and plural candidate character codes corresponding to an indefinite character having plural recognition candidates are stored in a picture buffer memory 118. A character pattern corresponding to the character code and plural candidate character patterns corresponding to the plural candidate character code are generated in a image data coversion part 110. The character pattern and plural candidate character patterns are stored in the picture buffer memory 118. A content stored in the picture buffer memory is displayed. An operation part 116 designates the desired candidate character pattern from the plural displayed candidate character patterns. The designated candidate character pattern and the character pattern are outputted from a recording part 117.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus and method for recognizing characters in an input document image, and a computer-readable memory.

[0002]

2. Description of the Related Art Generally, in an image processing apparatus for recording an image on a recording sheet based on information obtained by recognizing characters in a document image, a document image to be recognized is read, and a predetermined area image in the read document image is read. And character recognition of the predetermined area image is performed.

[0003]

However, if a character in a predetermined area image cannot be recognized, or if a plurality of recognition candidates at the same level are generated and the recognition result cannot be specified, the predetermined area image cannot be identified. Has been displayed, and a formal character code for the character image has been input using a keyboard or the like. In this case, especially when there are many character images for which the recognition result cannot be specified, a number of operations must be performed in order to input a proper character code for each character image, which is very troublesome. Further, if a dedicated display device or keyboard is provided to reduce the number of operations, the device becomes complicated and costs increase.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and provides an image processing apparatus, a method thereof, and a computer-readable memory capable of efficiently and at low cost performing post-processing on a character recognition result. The purpose is to do.

[0005]

An image processing apparatus according to the present invention for achieving the above object has the following arrangement.
That is, an image processing apparatus for recognizing characters in an input document image, a recognition unit for recognizing characters in the input document image, and a character code corresponding to the recognition character recognized by the recognition unit First memory means for storing a plurality of candidate character codes corresponding to uncertain characters having a plurality of recognition candidates, and a character pattern corresponding to the character code;
Generating means for generating a plurality of candidate character patterns corresponding to the plurality of candidate character codes; second memory means for storing the character pattern and the plurality of candidate character patterns;
Display means for displaying the contents stored in the second memory means; designation means for designating a desired candidate character pattern from a plurality of candidate character patterns displayed on the display means;
A candidate character pattern designated by the designation means; and an output means for outputting the character pattern.

Preferably, the display means displays the candidate character patterns of the plurality of candidate character patterns in descending order of their recognition probabilities in accordance with the designation by the designation means.

[0007] Preferably, the display means displays the candidate character pattern by synthesizing a predetermined image indicating the candidate character pattern.

Preferably, the predetermined image is an inverted image of the candidate character pattern.

Preferably, the predetermined image is a halftone image.

Preferably, the predetermined image is an underline.

Preferably, the first memory means further stores a predetermined character code indicating an unknown character which cannot be recognized by the recognition means, and the generation means further includes a predetermined character code corresponding to the predetermined character code. A character pattern is generated, and the second memory means stores the predetermined character pattern and a partial image in the original image corresponding to the unknown character.

Preferably, the display means displays the predetermined character pattern at a display position of the unknown character,
The partial image is displayed according to the designation by the designation means.

Preferably, the output means further outputs the partial image in accordance with the designation by the designation means.

[0014] Preferably, the display means includes a character pattern and a candidate character included in a predetermined area of the second memory means, which are determined based on a position of a noticeable candidate character pattern among the plurality of candidate character patterns. Display a pattern.

Preferably, the designation means has at least a first key, a second key, a third key, a fourth key, and an enter key, and when the first key is pressed, the display means is provided. Displaying the candidate character pattern located behind the displayed candidate character pattern, and when the second key is pressed, the display means displays the candidate character pattern located before the displayed candidate character pattern. Is displayed, and when the third key is pressed, the display means displays a candidate character pattern next to the displayed candidate character pattern,
When the fourth key is pressed, the display unit displays a candidate character pattern before the displayed candidate character pattern, and when the enter key is pressed, the display unit is a display target. Each candidate character pattern is determined as an output target of the output means.

[0016] Preferably, the designation means can further designate the number of candidate character patterns to be displayed on the display means.

An image processing method according to the present invention for achieving the above object has the following arrangement. That is, an image processing method for recognizing characters in an input document image, a recognition step for recognizing characters in the input document image,
A first storage step of storing, in a first memory, a character code corresponding to the recognized character recognized in the recognition step and a plurality of candidate character codes corresponding to an uncertain character having a plurality of recognition candidates; Generating a plurality of candidate character patterns corresponding to the plurality of candidate character codes, a second storing step of storing the character pattern and the plurality of candidate character patterns in a second memory, A display step of displaying the content stored in the second memory; a designation step of designating a desired candidate character pattern from a plurality of candidate character patterns displayed in the display step;
A candidate character pattern designated in the designation step; and an output step of outputting the character pattern.

A computer readable memory according to the present invention for achieving the above object has the following configuration. That is,
A computer-readable memory storing a program code for image processing for recognizing characters in an input document image, wherein a program code for a recognition step for recognizing characters in the input document image; A character code corresponding to the recognized recognized character, a plurality of candidate character codes corresponding to an uncertain character having a plurality of recognition candidates in a first memory, a program code in a first storage step, and a code corresponding to the character code. A character pattern, a program code of a generating step of generating a plurality of candidate character patterns corresponding to the plurality of candidate character codes, and a second storage step of storing the character pattern and the plurality of candidate character patterns in a second memory. A program code, a program code of a display step of displaying contents stored in the second memory, and the display step A program code of a designation step of designating a desired candidate character pattern from a plurality of displayed candidate character patterns, a candidate character pattern designated in the designation step, and a program code of an output step of outputting the character pattern are provided. .

[0019]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will be described below in detail with reference to the drawings. <First Embodiment> FIG. 1 is a diagram showing a functional configuration of an image processing apparatus according to a first embodiment.

An original 1001 is converted into an image signal from a lens 101 of an image reading unit 1002 through an image sensor (CDD) 102. Next, the image signal is input to the A / D converter 103, A / D converted, and then input to the image processing unit 1003. The image processing unit 1003 applies a shading correction circuit 104 to the input image signal.
After the shading correction is performed, the mode switching circuit 10
Enter 5

In the mode switching circuit 105, an operation unit 116
, The output destination is switched based on the character recognition copy mode or the normal copy mode. When the normal copy mode is set, the light density conversion circuit 106 converts the luminance data into recording density data. The image editing unit 107 performs an editing process on the recording density data based on the settings of the image processing stored in the RAM 115 in the CPU 113. Then, the edited recording density data is output to the image recording unit 1004.

An image recording unit 1004 includes a control circuit such as a motor for transporting transfer paper and the like, a laser recording circuit unit for writing a video signal input from the image processing unit 1003 to a photosensitive drum, and a development control circuit for performing development. The recording unit 117 is configured to record an image on a recording medium such as recording paper.

On the other hand, when the character recognition copy mode is set by the mode switching circuit 105, the output destination of the mode switching circuit 105 is switched to the image recognition unit 4000. In the image recognition unit 4000, first, the pattern recognition unit 108 performs pattern recognition using the image buffer memory 118. Here, an area such as a pattern for re-inputting an unrecognizable character, a plurality of option patterns, and a plurality of candidate display request markings is recognized. Then, the character recognition circuit 10
In step 9, an image (character pattern) of each character is cut out from the input image signal to perform character recognition.

The character recognition circuit 109 has a built-in recognition dictionary for character recognition. The recognition result by the character recognition circuit 109 is stored in a character code information storage area on the image buffer memory 118, and the image data conversion unit 1
Passed to 10. The image data conversion unit 110 converts the character code of the recognition output into an output image and stores it in the image information storage area on the image buffer memory 118. Here, for unrecognizable characters, the image information is stored as it is, and for characters having a plurality of candidates, a plurality of pieces of character code information are stored in the order of higher recognition probability. At the time of correcting an uncertain character, the pointer image generation unit 111 adds on a pointer image indicating that the character is a correction target character, and displays the pointer image on a display unit provided in the operation unit 116.

The operation unit 116 is connected to the image processing unit 100.
It has various key groups and various LED groups for instructing an image copy operation such as image editing contents, the number of copies, and a magnification ratio for 3 and a display unit for displaying the contents at the time of operation.

Next, a hardware configuration of the image processing apparatus according to the first embodiment will be described with reference to FIG.

FIG. 2 is a sectional view showing the hardware configuration of the image processing apparatus according to the first embodiment.

In FIG. 2, reference numeral 1 denotes a document feeder serving as a document feeder, which feeds the placed documents one by one or two.
The sheet is fed to a predetermined position on the platen glass surface 2 continuously. 4
Reference numeral denotes a scanner including a lamp 3, a scanning mirror 5, and the like, which is placed on the platen glass surface 2 by the document feeder 1. When, for example, a copy instruction or a character recognition instruction is given from the operation unit 116, the scanner 4 scans in a predetermined direction (left and right directions in the drawing) to pass the original reflected light through the lens 8 via the scanning mirrors 5 to 7. An image is formed on the image sensor unit 9.

Reference numeral 100 denotes a control unit on which the various circuits shown in FIG. 1 are mounted. Reference numeral 10 denotes an exposure unit that receives an image signal from an image signal control unit (not shown) that generates an image signal based on image data from the image editing unit 107 in the control unit 100, and a light beam corresponding to the image signal. Is irradiated on the photoconductor 11. Developing devices 12 and 13 visualize the electrostatic latent image formed on the photoreceptor 11 with a developer (toner) of a predetermined color. Reference numerals 14 and 15 denote transfer paper stacking units, which stack and store recording media of a fixed size. The recording medium is fed to the position where the registration roller is provided by driving the feeding roller, and is re-fed with the timing of aligning the leading edge of the image with the image formed on the photoconductor 11.

Reference numeral 16 denotes a transfer separation charger, which is a photosensitive member 11
After the toner image developed on the recording medium is transferred to the recording medium, the toner image is separated from the photoreceptor 11 and fixed by the fixing unit 17 via the transport belt. Reference numeral 18 denotes a paper discharge roller, which stacks and discharges the recording medium on which the image formation has been completed on the tray 20. Reference numeral 19 denotes a directional flapper, which switches the transport direction of the transfer-receiving sheet on which the image formation has been completed between the paper discharge port and the internal transport direction, and prepares for the multiplex / double-side image forming process.

Next, the appearance of the operation unit 116 according to the first embodiment will be described with reference to FIG.

FIG. 3 is a view showing the appearance of the operation unit according to the first embodiment.

Reference numeral 5001 denotes a power switch for controlling power supply to the apparatus main body. A reset key 5002 operates as a key for returning to the standard mode during standby. Reference numeral 5003 denotes a copy start key. 5004
Is a clear key used to clear numerical values such as the number of copies.

Reference numeral 5005 denotes an ID key. The ID key 5005 enables a specific operator to perform a copying operation.
005 makes it possible to prohibit a copying operation unless an ID is input. A stop key 5006 is used to interrupt or stop copying. Reference numeral 5007 denotes a guide key, which is used when the user wants to know each function.

An upper cursor key 5008 is a key for moving the pointer upward on each function setting screen. Reference numeral 5009 denotes a down cursor key which is used to move a pointer downward on each function setting screen. 501
A right cursor key 0 is a key for moving the pointer to the right on each function setting screen. A left cursor key 5011 is a key for moving the pointer to the left on each function setting screen. 5012 is an OK key,
This key is used to instruct the finalization of processing in each function setting screen.

In the first embodiment, in particular,
A specific action is assigned to the key of the key 5012,
Is a key for displaying a higher-order confirmed character when one of a plurality of candidate characters is displayed on a correction / decision screen for an undefined character. Reference numeral 5009 denotes a key for displaying a lower-order confirmed character when displaying one of the plurality of candidate characters on the correction and confirmation screen for an uncertain character. 5010 moves the pointer of the character to be corrected on the correction confirmation screen of the uncertain character to the next character in the lower right direction in the case of the horizontal writing document, and to the previous character in the upper right direction in the case of the vertical writing document, This key is used to display that character. 5011 moves the pointer of the character to be corrected on the correction confirmation screen for uncertain characters to the previous character in the upper left direction in the case of a horizontal writing document, and to the next character in the lower left direction in the case of a vertical writing document. This key is used to display characters. Reference numeral 5012 denotes an OK key for confirming the character to be corrected on the correction confirmation screen for the unconfirmed character with the currently displayed character.

An instruction key 5013 is a key for instructing execution of the contents of the image output to the lower right of the screen 5052 in each function setting screen. A standard size reduction key 5014 is used to reduce the standard size to another standard size. Reference numeral 5015 denotes a 1: 1 copy key, which is used to select 1: 1 copy. A standard enlargement key 5016 is used to enlarge the standard size to another standard size. A cassette selection key 5017 is used to select a cassette stage to be copied.

Reference numeral 5018 denotes a copy density adjustment key which is used to reduce the copy density. An AE key 5019 is used to automatically adjust the copy density with respect to the original density. A copy density adjustment key 5020 increases the copy density. 5021 is a key for specifying the operation of the sorter. Reference numeral 5022 denotes a preheating key, which is used to turn on / off a preheating mode. Reference numeral 5023 denotes an interrupt key, which is used when an interrupt is required to be performed during copying. Reference numeral 5024 denotes a numeric keypad, which is used to input numerical values.

Reference numeral 5025 denotes a marker processing key for setting trimming, masking, and partial processing (contour processing, halftone processing, shadowing processing, negative / positive processing). Reference numeral 5026 denotes a pattern processable key which is used to express a color in a pattern or to express a color by a density difference. 50
A color erasing key 27 is used to erase a specific color. An image quality key 5028 is used to set the image quality. 5029 is a negative / positive key,
Used when performing negative / positive processing. Reference numeral 5030 denotes an image create key which is used when performing contour processing, shadowing processing, halftone processing, italic, mirror processing, and repeat processing.

Reference numeral 5031 denotes a trimming key used to designate an area and perform trimming. 5032
A masking key is used to designate an area and perform masking. Reference numeral 5033 denotes a partial processing key, which is used to designate an area and then perform partial processing (contour processing, halftone processing, shadowing processing, negative / positive processing). Reference numeral 5034 denotes a frame erasing key, which is used when erasing a frame in accordance with a mode. The modes include sheet frame erasing (creating a frame for the sheet size), document frame erasing (creating a frame in accordance with the document size. Document size is specified), and book frame erasing (according to the spread size of the book). Create a blank in the frame and center. Book spread size specified). A binding margin key 5035 is used to create a binding margin at one end of a sheet.

Reference numeral 5036 denotes a move key for moving an image in a desired area, which is used when moving is desired.
The movement includes parallel movement (up, down, left and right), center movement, corner movement, and designated movement (point designation). 5037
Is a zoom key, which can set a copy magnification from 25% to 400% in increments of 1%. Further, the main scanning and the sub-scanning can be set independently. The magnification of the image is controlled by controlling the moving speed of the scanner 4 in the sub-scanning direction of the document, and by thinning out or interpolating the image data read from the scanner 4 in the main scanning direction of the document. Do.

Reference numeral 5038 denotes an automatic scaling key, which automatically enlarges or reduces the size according to the size of the copy sheet. In addition, the main scanning and the sub-scanning can be automatically scaled independently. Reference numeral 5039 denotes an enlargement continuous shooting key, which is used when one original is enlarged to a plurality of copies and copied. Reference numeral 5040 denotes a reduced layout key, which is used when copying a plurality of originals by enlarging / reducing them. Reference numeral 5043 denotes a continuous shooting key which is used to divide a copy area on the glass surface of the original platen into two right and left sides and perform continuous copying (page continuous shooting, double-side continuous shooting) for automatically making two copies. Reference numeral 5044 denotes a double-sided key which is used to output both sides (single-sided double-sided, page continuous double-sided, double-sided double-sided).

Reference numeral 5045 denotes a multiplex key.
Use when you want to perform (page continuous multiplexing). 5046
Is a memory key, which is used to perform a mode using a memory (memory synthesis, area synthesis, watermark synthesis). A projector key 5047 is used when using the projector. Reference numeral 5048 denotes a printer key, which is used when setting for a printer. 50
Reference numeral 50 denotes a mixed original key, which is used when originals are mixed when taking a copy using a feeder. Reference numeral 5051 denotes a mode memory key, which is used for registering the copy mode set for copy, when calling the registered copy mode.

Reference numeral 5052 denotes a liquid crystal display with a touch panel, which displays the status of the apparatus, the number of copies, the copy magnification, and the copy paper size, and sets the character recognition copy mode or the normal copy mode and the contents of the set copy mode. Is displayed. Further, during the operation of correcting the uncertain character when the character recognition copy mode is set, the correction target character and a plurality of surrounding characters are displayed. Reference numeral 5053 denotes a key for switching between a copy mode and an image processing setting mode.

Next, a processing flow of the image recognizing unit 4000 when character recognition of a document image is performed will be described with reference to FIG.

FIG. 4 is a flowchart showing the processing flow of the image recognition unit of the first embodiment.

First, character recognition is performed in the character recognition circuit 109 (step S5001). Note that the character recognition circuit 1
The details of the process 09 are described later. Next, it is determined whether or not the character is determined (step S5002). If determined (YES in step S5002), the character code of the character is stored in the character code information storage area (provided in the image buffer memory 118) (step S5003). Next, the image data conversion unit 110 generates image data corresponding to the character code (step S5004). Next, it is stored in the image information storage area (provided in the image buffer memory 118) (step S5005).

On the other hand, if the character is not fixed (step S
(NO in 5002), the process proceeds to step S5006. When a plurality of candidate characters exist (YE in step S5006)
S), the character codes of the plurality of candidate characters are stored in the character code information storage area (provided in the image buffer memory 118) (step S5007). Next, the image data conversion unit 110 generates image data corresponding to the character code of the first candidate character of the plurality of candidate characters. The pointer image generation unit 111 generates a pointer image indicating that the character is a correction target character (undefined character) (step S5008). Next, the image data and the pointer image are stored in the image information storage area (provided in the image buffer memory 118) (step S5009).

On the other hand, when there is no candidate character (step S5)
006), the character code of a character (for example,?
18 is provided in the character code information storage area (step S5010). Next, the read image data in the range corresponding to the unknown character is stored in the image information storage area (provided in the image buffer memory 118) (step S5011).

The above process is repeated for the number of characters to generate one page of character code data and output image data, and then the process proceeds to the process of correcting an uncertain character.

Next, a detailed processing flow of the character recognition circuit 109 will be described with reference to FIG.

FIG. 5 is a flowchart showing a detailed processing flow of the character recognition circuit according to the first embodiment. In the first embodiment, it is assumed that the image input as a recognition target is a vertically written document image. When the text to be recognized is written horizontally, the “character width” described below is changed to “character height”.
What is necessary is just to read and process.

First, the character direction of the input image is determined based on the presence or absence of an image in the vertical direction (for example, a histogram) from the input image, and the line width h thereof is obtained (step S40).
02). Next, character patterns are cut out according to the presence / absence of a horizontal image (histogram) for each of the obtained lines, and the character width W (i) and position coordinates X of each character pattern are extracted.
(I) is stored (step S4003). Here, the character width W (i) of the cut-out character pattern is h-Δa ≦ W (i) ≦ h + Δa (1) (where, Δa: allowable range value from line width h, i: character pattern number) Are extracted, and the standard character width W is obtained by averaging them (step S).
4004).

Next, the obtained standard character width W is compared with the character width W (i) of each cut character pattern. If the character width W (i) is significantly larger than the standard character width W,
That is, a character pattern that satisfies W + Δb <W (i) (2) (where Δb is an allowable range from the standard character width) is searched for (step S4005).

When the character width W (i) of the target character pattern does not satisfy the above expression (2) (N in step S4005)
O), and proceed to step S4009. On the other hand, when the character width W (i) of the target character pattern satisfies the above expression (2) (YES in step S4005), up to the character pattern having the standard character width W before and after the target character pattern, A character pattern that includes the character pattern to be satisfied and that is located between the character patterns having the standard character width W closest thereto is projected in the horizontal direction to create a histogram (step S4006).

The position of the horizontal axis is x, the number of dots on the vertical axis is y, a predetermined threshold value z is provided for the value y, and (x =
0), a value x near the standard character width W and smaller than the threshold value z is obtained (step S4007).

If the length of the projection is L, x
In the process of obtaining is approximately the standard character width W, and the last width is almost the standard character width W (step S4).
(YES in 007), a new character segmentation process is performed at the obtained x (step S4008). On the other hand, when a break is not found in the vicinity of the standard character width W in the middle of obtaining x, or when the character width of the last character pattern is significantly less than the standard character width W even if it is cut to the end (step S4007) NO), and proceed to step S4009.

Finally, a character recognition process is performed on the extracted character pattern to generate a character code corresponding to the character pattern (step S4009).

Next, a processing flow and a specific example of the correction processing of the uncertain character will be described with reference to FIGS. 6, 7 to 9.

FIG. 6 is a flowchart showing the processing flow of the correction processing of the uncertain character according to the first embodiment.
FIG. 8 is a diagram showing transition of the display unit at the time of correcting the character code data, the output image data, and the uncertain character according to the first embodiment.

FIG. 7 shows the character code data and output image data generated after reading and character recognition are completed. The character code data is stored in the character code information storage area of the image buffer memory 118. 801 of FIG. 8 is a diagram showing the character codes of a plurality of candidate characters for the uncertain character, and the character codes are stored in the character code information storage area of the image buffer memory 118. Further, in the image information storage area of the image buffer memory 118, each character code is developed into image data and stored, and a plurality of character codes corresponding to an undefined character are stored together with a pointer image indicating that the character code is undefined. The character code of one candidate character is developed into image data and stored.

When the uncertain character correction operation is started, first, n × m (for example, 3 × 3) is displayed on the display unit 5052 in FIG.
Characters are displayed (step S6001). At this time, a pointer image indicating an undefined character is also displayed in a superimposed manner (step S6002). Here, the pointer image may be a gray background for the text, a black and white display of the text,
A halftone dot image or underline is added, or the display thereof is blinked, or the user is notified that the character is an uncertain character (802 in FIG. 9).

The operator checks the display contents of the display section 5052 and performs a key operation according to the display contents (step S).
6003). Here, it is determined that the first candidate “pain” is incorrect, and the ↓ key (5009) is pressed (step S6003). In response, the current correction target character “pain” is changed to the next candidate character “disease” (80 in FIG. 9).
3). That is, the pointer image for the plurality of candidate characters in the character code information storage area is moved by one (step S6011), and the character code is developed into image data and the display is switched (step S6009). At this time, the pointer image indicating the uncertain character is also displayed in a superimposed manner (step S6010).

Next, the operator checks the display content of the display section 5052, judges that the character of the second candidate "disease" is incorrect, and presses the ↓ key (5010) (step S600).
3). In response, the current correction target character "disease" is changed to the next candidate character "saku" (804 in FIG. 9). That is, the pointer image for the plurality of candidate characters in the character code information storage area is moved by one (step S6).
011), the character code is developed into image data and the display is switched (step S6009). At this time, the pointer image indicating the uncertain character is also displayed in a superimposed manner (step S6010).

Next, the operator checks the display content of the display unit 5052, and judges that the character of the third candidate “Mr.” is correct.
Press the key (5011). In response thereto, the current correction target character “Sai” is provisionally determined (step S6004).
The correction target character “Sai” is converted into image data and stored in the image information storage area (step S6005). Next, in the order along the coordinates, the first candidate character of the next uncertain character, “Shi”, is converted into image data, and n × m (here, 3 × 3) characters are converted to the image data. It is displayed (step S6006, 805 in FIG. 9). At this time, a pointer image indicating an undefined character is also displayed in a superimposed manner (step S6).
007).

Hereinafter, similarly, the correction and provisional determination are repeated one character at a time (806 to 810 in FIG. 9), and when the operator presses the OK key (5012), the final determination is made over the entire page (step). S6014). Note that the OK key (5
Until (012) is pressed, the correction target character can be returned to the previous position and the provisionally determined candidate character can be changed again (steps S6008 to S6012).

After all characters are determined over the entire page, the image is printed out by the image recording unit 117.

As described above, the process of correcting an uncertain character when there are a plurality of candidate characters for an uncertain character after character recognition has been described. This will be described below with reference to FIG.

If there is no candidate character, the character code of a character (for example,? Mark) indicating that the character is unknown is stored in the character code information storage area (provided in the image buffer memory 118) ( Step S501
0). Next, the read image data in the range corresponding to the unknown character is stored in the image information storage area (provided in the image buffer memory 118) (step S50).
11).

Then, the context and the word are further estimated from the characters before and after the unknown character, and a plurality of characters considered to have a high probability are set as candidate characters, and the character codes are stored in the character code information storage area. The process of correcting an unknown character is the same as that described with reference to FIG. However, in this case, a character indicating that there is an unknown character is displayed instead of the pointer image. At the end of the candidate character, an option is provided for directly selecting the read image data in the range corresponding to the unknown character (the last character of each candidate character string 801 in FIG. 8), and all the estimated candidate characters did not correspond. If
The read image data is determined as output image data as it is.

As described above, according to the first embodiment, a regular character pattern is generated for characters that can be recognized in an input document image, and characters that cannot be narrowed down for recognition candidates. It occurs in a format in which a plurality of candidate character patterns can be selected and selected in descending order of recognition probability. Then, the generated candidate character pattern and the dot information of the document image corresponding to the unrecognizable character are stored. Also, a part of the stored page information is displayed, and for characters for which recognition candidates could not be narrowed down, first, candidate characters having the highest recognition probability are displayed together with the pointer image, so that the operator can easily display the candidate characters. The operability related to character recognition can be improved by successively changing the display of the candidate characters by key operation and selecting and confirming them. <Second Embodiment> A second embodiment which has the same configuration as the first embodiment and outputs read image data at high speed will be described below. In the first embodiment, when there are dozens of uncertain characters in one page of the read image data, it takes a lot of trouble and time to correct and fix the work. Therefore, in the second embodiment, when priority is given to outputting read image data faster than accuracy of recognition, this is realized by providing the following means.

First, at step S5002 in FIG. 4, even if a character is not fixed and a plurality of undefined characters are raised,
Means for limiting the number of uncertain characters (three in FIG. 7) to an arbitrary number x or less set by the operator is provided. For example, if the number is two, two from the lower recognition probability are used. Is selected, and the other unknown characters are determined in advance as the first candidate characters. (In FIG. 8, for example, the character of "failure" is subjected to correction work, and is determined in advance by the first candidate character "failure"). FIG. 10 is a diagram showing a setting screen displayed on the display unit when setting the number of characters of uncertain characters. The document reading process and the character recognition process shown in FIGS.
A display unit 505 is provided between the processing for correcting the uncertain character shown in FIG.
2 is displayed.

Here, the setting screen shown in FIG. 10 will be described.

FIG. 10 is a diagram showing a setting screen displayed on the display unit 5052 when the number of unknown characters is set.
It is displayed on the display unit 5052 between the document reading process and the character recognition operation shown in FIGS. 4 and 5 and the uncertain character correction / fixing operation shown in FIG.

After finishing the character recognition processing shown in FIG. 5, if the operator considers that the maximum number of uncertain characters shown in the display section of FIG. Set the desired number. Then, the “yes” button is used to confirm the settings, and “n” is used to cancel the settings.
Press the "o" button. Depending on this setting, the number of characters that are determined as wrong characters or that are determined as unrecognized image information increases, but the number of unknown characters to be corrected decreases, so the time until image data is output is reduced. Is shortened.

Further, when the operator temporarily determines one undetermined character, among the other undetermined characters on the page, the first candidate is an undetermined character similar to the character determined by the operator. The order of the candidate characters with respect to is replaced, and the character temporarily determined by the operator is set as the first candidate character of other similar uncertain characters thereafter. For example, in FIG. 7 and FIG. 8, if the operator determines that the uncertain character “pain” on the first line is “medical”, the first candidate is “pain” or “disease” with other uncertain characters on the page. The character "" changes the order of the candidate characters and makes "Sai" the first candidate. By doing so, if all similar uncertain characters thereafter are correct for “medical”, it can be temporarily determined by pressing the ← key once.

Further, when one uncertain character is temporarily determined by the operator, the characters before and after the other undetermined characters in the page are equal to the characters before and after the character temporarily determined by the operator. Then, the order of the candidate characters for the character is changed, and the character temporarily determined by the operator is set as the first candidate character of the uncertain character in which other characters before and after the character are equal. For example, in FIGS. 7 and 8, if the operator determines that the uncertain character “pain” on the first line is “medical”, among the other uncertain characters on the page, the previous character is “medical”, For the uncertain character in which the subsequent character is “,”, the order of the candidate characters is switched, and “Sai” is made the first candidate. In this way, if all of the uncertain characters that become “medicine?” Are correct for “medical”, it can be provisionally determined only with the ← key.

In the case of an unknown character having no candidate character at all, the read image data in the range corresponding to the unknown character is stored as it is in the image information storage area (step S5011 in FIG. 4), and the unknown character is corrected. If the read image data is determined as output image data as it is, the erroneous recognition rate increases, but the output of the image data becomes faster.

As described above, according to the second embodiment, by allowing the operator to set the number of indeterminate characters, even if there are more indeterminate characters than the set number, the first candidate character can be used. Determine in advance. In addition, when the operator temporarily determines one uncertain character, the first candidate is a candidate character for an undetermined character similar to the character determined by the operator among other undetermined characters on the page. Swap the rankings. Further, when one uncertain character is temporarily determined by the operator, when the characters before and after the other undetermined characters in the page are equal to the characters before and after the character temporarily determined by the operator, the character is determined. Swap the order of candidate characters for. In the case of an unknown character having no candidate character at all, read image data in a range corresponding to the unknown character is determined as output image data in the image information storage area. This allows
Although the accuracy of recognition is reduced, the output of image data can be made faster.

In the first and second embodiments, the result of adaptation to the copying machine and the finally recognized result are printed out. However, for example, the result is stored in a memory and used for document editing. Depending on the case, it may be stored in a storage medium such as a floppy (registered trademark) disk device.

In the above description, an example in which the present invention is applied to a single copying machine has been described. For example, a system having an image reader, a host computer for performing character recognition processing, and a printer having a printer for printing out can also obtain the same operation and effect. be able to. In this case, the host computer may be loaded with a program code for implementing the above processing. As described above, the present invention can be realized by a single device, a combination of a plurality of devices, and a case where the present invention is realized by supplying a program code.

Even if the present invention is applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), a device including one device (for example, a copying machine, a facsimile machine) Etc.).

An object of the present invention is to provide a storage medium storing a program code of software for realizing the functions of the above-described embodiments to a system or an apparatus, and to provide a computer (or CPU) of the system or apparatus.
And MPU) read and execute the program code stored in the storage medium.

In this case, the program code itself read from the storage medium implements the functions of the above-described embodiment, and the storage medium storing the program code constitutes the present invention.

Examples of a storage medium for supplying the program code include a floppy disk, hard disk, optical disk, magneto-optical disk, CD-ROM, and CD.
-R, a magnetic tape, a nonvolatile memory card, a ROM, or the like can be used.

When the computer executes the readout program code, not only the functions of the above-described embodiment are realized, but also the OS (Operating System) running on the computer based on the instruction of the program code. ) May perform some or all of the actual processing, and the processing may realize the functions of the above-described embodiments.

Further, after the program code read from the storage medium is written into a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, based on the instruction of the program code, It goes without saying that the CPU included in the function expansion board or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above-described embodiments.

When the present invention is applied to the storage medium, the storage medium stores program codes corresponding to the flowcharts shown in FIGS. 4, 5 and 6 described above.

[0089]

As described above, according to the present invention,
An image processing apparatus and method capable of efficiently executing post-processing on a character recognition result, and a computer-readable memory can be provided.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating a functional configuration of an image processing apparatus according to a first embodiment.

FIG. 2 is a cross-sectional view illustrating a hardware configuration of the image processing apparatus according to the first embodiment.

FIG. 3 is a diagram illustrating an appearance of an operation unit according to the first embodiment.

FIG. 4 is a flowchart illustrating a processing flow of an image recognition unit according to the first embodiment.

FIG. 5 is a flowchart illustrating a detailed processing flow of the character recognition circuit according to the first embodiment.

FIG. 6 is a flowchart illustrating a processing flow of an indeterminate character correcting process according to the first embodiment.

FIG. 7 is a diagram illustrating transitions of the display unit when correcting the character code data, output image data, and uncertain characters according to the first embodiment.

FIG. 8 is a diagram illustrating transition of the display unit when correcting the character code data, output image data, and uncertain characters according to the first embodiment.

FIG. 9 is a diagram illustrating transition of a display unit when correcting character code data, output image data, and uncertain characters according to the first embodiment.

FIG. 10 is a diagram illustrating a setting screen displayed on a display unit when setting the number of undefined characters according to the second embodiment.

[Explanation of symbols]

 Reference Signs List 101 lens 102 image sensor 103 AD converter 104 shading correction circuit 105 mode switching circuit 106 light density conversion circuit 107 image editing unit 108 pattern recognition unit 109 character recognition circuit 110 image data conversion unit 111 pointer image generation unit 113 CPU 114 ROM 115 RAM 116 Operation unit 117 Recording unit 118 Image buffer memory 1001 Document 1002 Image reading unit 1003 Image processing unit 1004 Image recording unit 4000 Image recognition unit

 ────────────────────────────────────────────────── ─── Continuing on the front page (72) Inventor Eiwa, Honda 3- 30-2 Shimomaruko, Ota-ku, Tokyo Inside Canon Inc. (72) Inventor Makoto Kobayashi 3- 30-2, Shimomaruko, Ota-ku, Tokyo Canon Incorporated (72) Inventor Hiroshi Tanioka 3-30-2 Shimomaruko, Ota-ku, Tokyo F-term in Canon Inc. (reference) 5B064 AA01 AA07 BA01 EA12 EA14 FA04 FA09 FA11

Claims (25)

[Claims] 1. An image processing apparatus for recognizing a character in an input document image, comprising: a recognizing means for recognizing a character in the input document image; First memory means for storing a plurality of candidate character codes corresponding to uncertain characters having a plurality of recognition candidates, a character pattern corresponding to the character code, and a plurality of characters corresponding to the plurality of candidate character codes. Generating means for generating a candidate character pattern, a second memory means for storing the character pattern and the plurality of candidate character patterns, a display means for displaying contents stored in the second memory means, and the display means. A designating means for designating a desired candidate character pattern from a plurality of candidate character patterns displayed by the user; a candidate character pattern designated by the designating means; The image processing apparatus according to an outputting means for outputting the over down. 2. The apparatus according to claim 1, wherein the display unit displays the candidate character patterns of the plurality of candidate character patterns in descending order of their recognition probabilities in accordance with the designation by the designation unit. Image processing device. 3. The image processing apparatus according to claim 1, wherein the display unit displays the candidate character pattern by synthesizing a predetermined image indicating the candidate character pattern. 4. The image processing apparatus according to claim 3, wherein the predetermined image is an inverted image of the candidate character pattern. 5. The image processing apparatus according to claim 3, wherein the predetermined image is a halftone image. 6. The image processing apparatus according to claim 3, wherein the predetermined image is an underline. 7. The first memory unit further stores a predetermined character code indicating an unknown character that cannot be recognized by the recognition unit, and the generation unit further stores a predetermined character pattern corresponding to the predetermined character code. 2. The image processing apparatus according to claim 1, wherein the second memory unit stores a partial image in the original image corresponding to the predetermined character pattern and the unknown character. 8. The display device according to claim 7, wherein the display unit displays the predetermined character pattern at a display position of the unknown character, and displays the partial image in accordance with the designation of the designation unit. Image processing device. 9. The image processing apparatus according to claim 1, wherein the output unit further outputs the partial image in accordance with the designation of the designation unit. 10. The display means displays a character pattern and a candidate character pattern included in a predetermined area of the second memory means determined based on a position of a noticeable candidate character pattern among the plurality of candidate character patterns. The image processing apparatus according to claim 1, wherein: 11. The designating means has at least a first key, a second key, a third key, a fourth key, and an enter key, and when the first key is pressed, the display means displays a message. Displaying the candidate character pattern located after the candidate character pattern being displayed, and when the second key is pressed, the display means displays the candidate character pattern located before the displayed candidate character pattern. When the third key is pressed, the display means displays a candidate character pattern next to the displayed candidate character pattern, and when the fourth key is pressed, the display means displays Displaying the candidate character pattern preceding the candidate character pattern that is displayed, and when the determination key is pressed, the display unit determines each candidate character pattern to be displayed as an output target of the output unit. The image processing apparatus according to claim 1. 12. The image processing apparatus according to claim 1, wherein the specifying unit can further specify the number of candidate character patterns to be displayed on the display unit. 13. An image processing method for recognizing characters in an input document image, comprising: a recognition step of recognizing characters in the input document image; A first character code, a plurality of candidate character codes corresponding to an uncertain character having a plurality of recognition candidates in a first memory, a character pattern corresponding to the character code, and the plurality of candidate character codes Generating a plurality of candidate character patterns corresponding to the character pattern;
A second storage step of storing in a memory; a display step of displaying contents stored in the second memory; and a designation step of designating a desired candidate character pattern from a plurality of candidate character patterns displayed in the display step. An image processing method, comprising: a candidate character pattern designated in the designation step; and an output step of outputting the character pattern. 14. The display step according to claim 13, wherein the displaying step displays the candidate character patterns of the plurality of candidate character patterns in descending order of their recognition probabilities in accordance with the designation in the designation step. Image processing method. 15. The image processing method according to claim 13, wherein in the displaying step, the candidate character pattern is displayed by synthesizing a predetermined image indicating the candidate character pattern. 16. The image processing method according to claim 15, wherein the predetermined image is an inverted image of the candidate character pattern. 17. The image processing method according to claim 15, wherein the predetermined image is a halftone image. 18. The method according to claim 15, wherein the predetermined image is an underline. 19. The first storage step further stores a predetermined character code indicating an unknown character that cannot be recognized in the recognition step in the first memory, and the generating step further corresponds to the predetermined character code. The method according to claim 13, wherein a predetermined character pattern is generated, and wherein the second storage step stores the partial image in the original image corresponding to the predetermined character pattern and the unknown character in the second memory. Image processing method. 20. The display device according to claim 19, wherein the display step displays the predetermined character pattern at a display position of the unknown character, and displays the partial image in accordance with the designation in the designation step. Image processing method. 21. The image processing method according to claim 13, wherein the output step further outputs the partial image in accordance with the designation in the designation step. 22. The display step displays a character pattern and a candidate character pattern included in a predetermined area of the second memory, which are determined based on a position of a target candidate character pattern among the plurality of candidate character patterns. 14. The image processing method according to claim 13, wherein: 23. The designating step includes at least a first key, a second key, a third key, a fourth key, and an enter key. When the first key is pressed, the display step displays Displaying the candidate character pattern located after the candidate character pattern being displayed, and when the second key is pressed, the display step displays the candidate character pattern located before the displayed candidate character pattern. If the third key is pressed, the display step displays a candidate character pattern next to the displayed candidate character pattern. If the fourth key is pressed, the display step displays Displaying the candidate character pattern before the candidate character pattern that is present, and when the confirmation key is pressed, the display step decides each candidate character pattern to be displayed as an output target of the output step. The image processing method according to claim 13. 24. The image processing method according to claim 13, wherein in the specifying step, the number of candidate character patterns to be displayed in the display step can be specified. 25. A computer readable memory storing an image processing program code for recognizing a character in an input document image, comprising: a program code for a recognition step for recognizing a character in the input document image; A program code of a first storage step of storing, in a first memory, a character code corresponding to the recognized character recognized in the recognition step and a plurality of candidate character codes corresponding to an uncertain character having a plurality of recognition candidates; A character pattern corresponding to the character code, a program code of a generating step for generating a plurality of candidate character patterns corresponding to the plurality of candidate character codes,
A program code of a second storage step to be stored in a memory; a program code of a display step to display contents stored in the second memory; and a candidate character pattern desired from a plurality of candidate character patterns displayed in the display step. A computer readable memory comprising: a program code of a designation step for designating a character pattern; a candidate character pattern designated in the designation step; and a program code of an output step of outputting the character pattern.