JPH08185483A - Character recognition device - Google Patents

Abstract

PURPOSE: To provide a character recognition device capable of easily reading recognized results upto the halfway and a picture file when the character recognition device is activated next after it is ended in the middle of operations. CONSTITUTION: This device is provided with an end state storage part 19 for storing a state at the point of time of ending this character recognition device in a previous time, a picture page number storage part 20 for tentatively storing the page number of read pictures, an area set page number storage part 21 for tentatively storing the page number for which the specification of a recognition object area is ended among the pictures and a recognized page number storage part 22 for tentatively storing the page number for which the character recognition is ended among the pictures for which area setting is ended.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a character recognition device.

[0002]

2. Description of the Related Art Character recognition devices that read an image from a document and convert it into a character code are becoming popular. This character recognition device saves labor in character input and is convenient.

[0003]

However, in the conventional character recognition device, the character recognition device is always in the initial state when it is activated, and the image data is read by the user from the image scanner or the already registered image file. After reading, it started to recognize characters.
Therefore, if the character recognition process was performed halfway at the end of the previous time, the original must be read again or the image file must be saved at the end, which is a problem that the operation is complicated in any case. there were.

Therefore, it is an object of the present invention to provide a character recognition device which can easily read out an image file and the recognition results up to the middle when the character recognition device is terminated in the middle of work. .

[0005]

A character recognition apparatus according to the present invention includes an end state storage section for storing the state at the time when the character recognition apparatus was last terminated, and an image page for temporarily storing the number of pages of a read image. Number storage unit, a region number set page storage unit for temporarily storing the number of pages for which the recognition target region has been designated in the image, and the number of pages for which character recognition has been completed for the region set image And a recognized page number storage unit.

[0006]

With the above configuration, the number of pages of the image, the number of pages in which the area setting process is completed, and the number of pages in which the character recognition process is completed can be stored when the character recognition device is terminated. Even when the work is completed halfway, the next time the character recognition device is started up, by referring to these pieces of information, it is possible to continue the work from the time when the work is completed halfway.

[0007]

Embodiments of the present invention will now be described with reference to the drawings. FIG. 1 is a block diagram of a character recognition device in one embodiment of the present invention, and FIG. 2 is a functional block diagram of a character recognition device in one embodiment of the present invention. In FIG. 1, reference numeral 1 is a ROM (read only memory) that records a control program according to the flowchart of FIG. 3, and 2 is a CPU that executes the control program in the ROM 1 and controls each of the other elements.
(Central processing unit) 3 is a RAM provided with an area for storing information necessary for executing the control program
(Random access memory), 4 is a CRT (cathode ray tube) that displays the operation status and recognition result, 5 is a mouse for operating the recognition target area, 6 is an external storage device such as a hard disk device, 7 is characters, etc. Is a keyboard for inputting, and 8 is a scanner for reading an original 9 to generate an image, and 10 is a printer.

In FIG. 2, numeral 11 comprises a scanner 8 and the like,
An image reading unit for reading an image of the original document 9, 12 is an image storage unit provided in the external storage device 6 for storing the read image, and 13 is a recognition target region instructed to perform character recognition of the read image. A recognition target area designating unit for designating the recognition target area, a recognition target area storage unit 14 provided in the RAM 3 for storing the recognition target area, and a recognition target area modifying unit 15 for modifying the recognition target area by the user as necessary. Is a character recognition unit that performs line segmentation on the image in the recognition target area, performs character segmentation processing on the segmented line, and recognizes each segmented character. The character recognition unit 16 is the same as a known unit, and thus detailed description thereof is omitted.

A character recognition unit 1 is provided in the RAM 3
A recognition result storage unit for temporarily storing the recognition result output by 6;
Reference numeral 18 is a recognition result correction unit that corrects the recognition result in the recognition result storage unit 17 according to a correction instruction from the user, and 19 is a RAM.
An end state storage unit 20 provided in the RAM 3 for storing the state when the entire process is finished, and an image page number storage unit 20 provided in the RAM 3 for temporarily storing the page number of the read image.
Numeral 22 is provided in the RAM 3, and an area-set page number storage unit for temporarily storing the number of pages of the read image for which the recognition target area has been designated; 22 is provided in the RAM 3; The page number storage unit for temporarily storing the number of finished pages, 23 is a page counter storage unit provided in the RAM 3 for storing the number of pages being processed, 24 is a display unit such as a CRT 4, and 25 is a keyboard 7 , Mouse 5
The input unit 26 and the like are control units for controlling the whole.

The control unit 26, the character recognition unit 16, the recognition target area designation unit 13, the recognition target area correction unit 15, and the recognition result correction unit 18 are realized by the CPU 2 executing the control program in the ROM 1. Of the information stored in the RAM 3, necessary information is stored in the external storage device 6 as needed.
Is written to.

Next, the operation of the character recognition apparatus according to the embodiment of the present invention will be described with reference to the flowcharts shown in FIGS. First, in step 1, a status file is read from the external storage device 6. This file stores the image page number storage unit 20, the area-set page number storage unit 21, and the recognized page number storage unit 22 at the time when the user last completed the processing.
This is a file in which the contents stored in (1) are stored in the external storage device 6, and as shown in FIG. 5, the number of image pages, the number of area-set pages, and the number of recognized pages are stored. When the number of image pages is 0, the image file is not stored, and when it is 1 or more, the image file is stored.

Next, in step 2, it is checked whether the image file is stored in the external storage device 6. This is judged by checking whether the number of image pages in the above-mentioned status file is 1 or more. In the present embodiment, the image file has a specific name (eg, “001.img”) or “002.img” in a specific location (directory) of the external storage device 6.
Since a name such as "img" that can be uniquely specified by the number of pages is given, the user does not have to specify the file name.

Step 2 if the image file exists
8. If not, go to step 3. In step 3, 0 is substituted into the values of the image page number storage unit 20, the area-set page number storage unit 21, and the recognized page number storage unit 22. Next, in step 4, the image is read from the image reading unit 11 and stored in the external storage device 6 as an image file.
Increase the value of 0 by 1. In step 5, the user is inquired whether to continue the processing. When the user gives an instruction to end the process, the process proceeds to step 25. In step 6, a screen as shown in FIG. 6 is displayed, and the user is inquired whether or not to read the original of the next page. If the next page is read, the process returns to step 4, otherwise the process proceeds to step 7.

In step 7, the image file of the first page is called from the external storage device 6 to the image storage unit 12. The recognition target area setting unit 13 sets a recognition target area for this image, stores it in the recognition target area storage unit 14, and then stores it as an area file in the external storage device 6 (step 8). This file is composed of the number of areas and the coordinates of each area as shown in FIG. 7, and is given a name that can be uniquely specified by the number of pages as in the image file. Note that the processing in the recognition target area designating unit 13 can be realized by a known method, so a detailed description thereof will not be given here.

In step 9, it is checked whether the user has input an instruction to end the process.
If not, go to step 10. In step 10, inquire of the user whether to set the recognition target area for the next page. When setting, set the image file of the next page to the image storage unit 12 (step 13), and then return to step 8 or not. Proceeds to step 11. Step 11
Then, the image of the original on the first page and the recognition target area are displayed on the display unit 24 on the screen as shown in FIG.
At 2, the user determines whether the area needs to be modified and can do so if necessary.

When the area is corrected for the next page (step 14), the image file and the area file of the next page are read in step 31, and the process returns to step 12. Next, in step 15, after reading the image file and area file for the first page, the coordinates of the first area in this page are specified (step 16), and character recognition is executed for the image in this area. Then, the recognition result is stored in the recognition result file (step 17).

There is one recognition result file for each page, and character codes are stored for each area as shown in FIG.
Further, like the image file and the area file, a name that can be uniquely specified by the number of pages is given. When the character recognition processing for one area is completed, it is checked in step 18 whether the user has given an instruction to end the processing.

If no instruction is given, it is checked in step 19 whether or not there is an area in the page for which character recognition processing has not been completed. If there is any, the process returns to step 17. In step 20, the user is inquired whether character recognition is to be executed for the next page. If the character recognition is to be executed, the image file and area file of the next page are read, and then the process returns to step 16.

Next, in step 21, the image file for the first page, the area file, and the recognition result file are read from the external storage device 6, and the image data and the recognition result thereof are displayed on the display unit 24. If correction is necessary, the recognition result can be corrected in step 22, and the recognition result file is updated after changing the contents of the recognition result storage unit 17. In step 23, it is checked whether the user has input an instruction to end the process halfway. If not finished, if there is a next page (step 24), read the file and step 2
Return to 2. If the next page does not exist in step 24, the user is asked whether or not to delete the image file, the area file, and the recognition result file (step 25), and if approved, the files in the external storage device 6 are deleted in step 26. To do. Step 27 outputs the status file.

Step 28 asks if the user has an intention to add an image file if the image file exists in the external storage device 6. If yes, go to step 4,
If not, go to step 29. Next, it is checked whether the recognition target area is set for all the image files (step 29), and if it is set, it is checked whether the character recognition is completed for all the image files (step 30).
If the character recognition is not completed, the process proceeds to step 16, and if it is completed, the process proceeds to step 21.

The state file may store, for example, the number of pages of the image file displayed at the end time, in addition to the case described in this embodiment. In this case, the page is displayed at the next start-up. The advantage is that you can specify

Further, the contents of the state file may be displayed on the screen when the character recognition device is activated, in which case the user can more clearly know the state at the end of the previous time and the work can be performed more smoothly. It helps.

[0023]

According to the present invention, an image reading section for reading an image of an original, an image storage section for storing the read image, and a recognition target area instructed to perform character recognition in the read image are designated. Recognition target area designation unit, a recognition target area storage unit that stores the designated recognition target area, a recognition target correction unit that the user corrects as necessary, and character recognition is performed on an image in the recognition target area. A character recognition unit for generating a recognition result, a recognition result storage unit for storing the recognition result, an input unit for inputting information for correcting the recognition result, and a time point when the character recognition device was last terminated. The end state storage unit that stores the state of the image, the image page number storage unit that temporarily stores the number of pages of the read image, and the area setting that temporarily stores the number of pages of the read image for which the recognition target region has been designated Number of completed pages Storage unit, a recognized page number storage unit for temporarily storing the number of pages for which character recognition has been completed in the image for which region setting has been completed, and a display unit for displaying the image in the recognition target region for which character recognition has ended and the recognition result And a control unit for controlling the whole, the number of pages of the image, the number of pages in which the area setting process is completed, and the number of pages in which the character recognition process is completed are stored at the end of the character recognition device. Therefore, even if the work is terminated halfway, the next time the character recognition device is started, by referring to these pieces of information, the work can be continued from the point when the work is finished, The user can be freed from complicated operations.

[Brief description of drawings]

FIG. 1 is a block diagram of a character recognition device according to an embodiment of the present invention.

FIG. 2 is a functional block diagram of a character recognition device according to an embodiment of the present invention.

FIG. 3 is a flowchart of a character recognition device according to an embodiment of the present invention.

FIG. 4 is a flowchart of a character recognition device according to an embodiment of the present invention.

FIG. 5 is an explanatory diagram of contents of a status file of the character recognition device in the embodiment of the present invention.

FIG. 6 is a view showing an example of image display when an image is read by the character recognition device in the embodiment of the present invention.

FIG. 7 is an explanatory diagram of contents of an area file of the character recognition device in the embodiment of the present invention.

FIG. 8 is a view showing an example of image display when a recognition target area is corrected by the character recognition device in the embodiment of the present invention.

FIG. 9 is an explanatory diagram of contents of a recognition result file of the character recognition device in the embodiment of the present invention.

[Explanation of symbols]

 19 end state storage unit 20 image page number storage unit 21 area set page number storage unit 22 recognized page number storage unit

Claims (1)

[Claims] 1. Image data is obtained by irradiating a character on a document and photoelectrically converting it into an electric signal based on the amount of light reflected from the document, and the character is cut out from the image data one by one, Character recognition is performed by extracting a feature amount from a character and matching the feature amount with a feature amount corresponding to a character belonging to a character group specified in advance among the feature amounts of characters registered in the dictionary storage unit in advance. In the character recognition device to perform, the end state storage unit that stores the state at the time when the character recognition device was last terminated, the image page number storage unit that temporarily stores the number of pages of the read image, and the recognition target of the image An area-set page number storage unit that temporarily stores the number of pages for which area designation has been completed, and a recognized page number storage unit that temporarily stores the number of pages for which character recognition has been completed in the image for which area setting has been completed Special Character recognition device to.