JPH07325843A - Electronic filing device - Google Patents

Abstract

PURPOSE:To provide an electronic filing device for easily inputting a document name at the time of reading an original. CONSTITUTION:This device is provided with a picture read part 11 for reading the pictures of the original, a picture storage part 12 for storing the read pictures, a recognition object area storage part 13 for storing a recognition object area instructed so as to recograize characters in the read pictures, a character recognition part 14 for recognizing the characters in the pictures inside the recognition object area and generating a recognized result, a recognized result storage part 16 for storing the recognized result, a display part 23 for displaying the pictures inside the recognition object area and the recognized result in contrast, a recognized result correction part 17 for receiving the manual correction of the recognized result, an input part 24 for inputting the correction information of the recognized result and a control part 25 for controlling the whole.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an electronic filing device.

[0002]

2. Description of the Related Art An electronic filing device is widely used as a device for reading an image from a document and filing information in an external storage device such as a magneto-optical disk device. This electronic filing device is convenient because a large amount of documents can be filed in a small space.

[0003]

However, in the conventional electronic filing apparatus, the user manually inputs the attributes such as the document name and the document code from the keyboard after reading the image of the document in which the document is shown on the paper. It was supposed to do. Therefore, there is a problem that the operation becomes extremely complicated when the number of documents is large.

SUMMARY OF THE INVENTION Therefore, an object of the present invention is to provide an electronic filing device which can set the attributes of a document simply and accurately.

[0005]

SUMMARY OF THE INVENTION An electronic filing apparatus of the present invention is to perform an image reading unit for reading an image of a document, an image storage unit for storing the read image, and a character recognition of the read image. A recognition target area storage unit that stores a designated recognition target area, a character recognition unit that performs character recognition on an image in the recognition target area to generate a recognition result, and a recognition result storage unit that stores the recognition result, A display unit that displays images in the recognition target area in contrast with the recognition result, a recognition result correction unit that accepts manual correction of the recognition result, an input unit for inputting correction information of the recognition result, and overall control And a control unit for controlling.

[0006]

With the above structure, the character recognition section performs character recognition on the image in the area set as the recognition target area in the image of the original, and the attribute of the document is set. Here, the user only needs to set the recognition target area of the document, and can easily set the attribute without manually inputting the document name and the like. Further, the recognition result and the image in the recognition target area are displayed in contrast to each other, and the user corrects only the point having an error in the recognition result from the input unit, whereby the correct attribute can be set.

[0007]

Embodiments of the present invention will now be described with reference to the drawings. 1 is a block diagram of an electronic filing apparatus according to an embodiment of the present invention, and FIG. 2 is a functional block diagram of an electronic filing apparatus according to an embodiment of the present invention. In FIG. 1, 1 is a ROM (read only memory) that stores a control program according to the flowcharts of FIGS. 4, 11 and 12, and 2 is a CPU that executes the control program in the ROM 1 and controls other elements ( Central processing unit), 3 is a RAM (random access memory) provided with an area for storing information necessary for executing the control program,
Reference numeral 4 is a CRT (cathode ray tube) for displaying 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 magneto-optical disk device or a large-capacity hard disk device, The external storage device 6 stores a document file as shown in FIG. 3 (configuration diagram of the document file in the embodiment of the present invention).
Reference numeral 7 is a keyboard for inputting correction information and the like, 8 is a scanner for reading an original 9 and generating 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 images of a plurality of originals 9 continuously, 12
Is an image storage unit provided in the external storage device 6 for storing the read image, and 13 is provided in the RAM 3, and is a recognition target region for storing a recognition target region instructed to perform character recognition in the read image. The storage unit 14 performs line segmentation processing on the image in the recognition target area, performs character segmentation processing on the segmented line, recognizes each segmented character, and the image spans multiple lines. Sometimes, it is a character recognition unit that adds a line feed code to the end of a line. Since the character recognition unit 14 itself is the same as the known means, detailed description will be omitted.

Reference numeral 15 is a storage condition storage unit referred to by the character recognition unit 14, and the storage condition storage unit 15 stores
A user interface as shown in FIG. 6 (illustration diagram of a save condition setting window in one embodiment of the present invention) saves the recognition result in the recognition target area as which attribute of the document (either the document name or the document code). Information is stored whether to do it. 16 is provided in RAM3,
The recognition result storage unit for temporarily storing the recognition result output by the character recognition unit 14, and 17 for the recognition result of the recognition result storage unit 16 relating to the maximum number of characters and the process shown in FIG. 7 (automatic correction in one embodiment of the present invention. The user interface (example of condition window)
The recognition result correction unit includes an automatic correction function including a process performed by referring to information stored in the correction condition storage unit 18 provided in the RAM 3, and a manual correction function according to a user's correction instruction. Reference numeral 19 denotes a replacement character storage unit that stores replacement characters that correspond one-to-one to a processing target to be described later, and is referred to by the recognition result correction unit 17 during automatic correction. Reference numeral 20 denotes a boundary condition between documents set according to FIG. 5 (an exemplary view of the boundary condition window in the embodiment of the present invention).
A document boundary recognition unit that determines the boundary of a document by referring to the information stored in the boundary condition storage unit 21 provided in AM3, 2
Reference numeral 2 denotes a page number storage unit provided in the RAM 3 for storing the page number of a document, 23 a display unit such as a CRT 4, 24 an input unit including a keyboard 7, a mouse 5 and the like, and 25 a control unit for controlling the whole. . The control unit 25 and the character recognition unit 1
4, the recognition result correction unit 17 and the document boundary recognition unit 20 are C
It is realized by the PU 2 executing the control program in the ROM 1, and necessary information temporarily stored in the RAM 3 is written in the external storage device 6 as needed. Further, as shown in FIG. 3, the document file is composed of an attribute part including a document name, a document code, etc., and an image data part consisting of the substance of the image data. Is being instructed.

Next, the operation of the electronic filing apparatus according to the present embodiment will be described with reference to FIG. 4 (flow chart of the electronic filing apparatus according to the embodiment of the present invention). First, in step 1, a window as shown in FIG. 5 is displayed on the display unit, and boundary conditions between documents are set. In this embodiment, three types of boundary conditions are prepared. The first boundary condition is
Each document consists of a certain number of pages (for example, 5 pages each)
The condition is that when the number of pages exceeds a certain number from the first page of a certain document, it is determined that the document is moved to the next document. As the second boundary condition, as shown in FIGS. 8 and 9 (illustration of the original in the embodiment of the present invention), the originals P1, P2, P3 ... Of the same size (the length L1 in the feeding direction) are If the originals P1 and P2 are the first part of the document and the originals P3 to P3 are the second set of documents, the size between the first and second sets of documents is half or less of the above size. When the partition sheet D having a length (L2 <L1 / 2 in the feeding direction) is sandwiched and the partition sheet D is detected, it is a condition that it is determined that the next document is moved to the next document. The third boundary condition is to specify the number of documents for each copy, such as how many copies are for the first copy, and so on for the second copy, when the documents for each copy are composed of a variable number of originals. Every other time, when the number of specified sheets is exceeded, it is a condition for determining that the next document has been moved. Since this is done, the user does not need to intentionally interrupt the reading at the boundary of the document, can read a plurality of documents continuously, and can automatically give a document name etc. to each document.
The user can perform filing more easily.

Next, in step 2 of FIG. 4, the window of FIG. 6 is displayed as described above, and the attribute to save the recognition result is set. Then, in step 3, the window of FIG. 7 is displayed and the automatic correction conditions are set.

Here, in the conventional electronic filing apparatus,
Used as a line feed code or wildcard * or? There is no special consideration for the case where a document name or a document code that is not suitable, such as a symbol such as, is included, and an error is likely to occur when the user searches for a file later. There was a problem. However, in the present embodiment, as will be described later, these unsuitable symbols are removed without manual input by the user, so that not only the user can save time but also unnecessary errors can be avoided. Now, in this embodiment, a line feed code ,? , * Are ignored (deleted), or replacement characters corresponding to these symbols stored in advance in the replacement character storage unit 19 in a one-to-one correspondence (all are blank in this embodiment, but may be variously changed). ) You can choose to replace.

Next, the recognition page can be set in step 4 of FIG. In consideration of the fact that some documents do not include the recognition target, meaningless recognition processing can be omitted. By default, only the first page is recognized.

Then, in step 5, the leading original is read and the image of the leading original is displayed on the display unit 23. Then, the recognition target area is set (step 6), the next document is read in step 7, and if the specified boundary condition is not satisfied (step 8), the remaining document is read (step 10) until it is read. Is repeated. If the boundary condition is satisfied, the page number is stored (step 9) and the reading is repeated. In the example of FIG. 8, it is assumed that the area within the broken line surrounding “Tokyo” of the original P1 is set as the recognition target area, and the first sheet of each part is set as the recognition page. As a result, the characters of the original P2 are not recognized, and the characters of the image of "Saitama prefecture" in the broken line of the first page (original P3) of the second copy are recognized.

Then, the character recognition of FIG. 11 is performed on the original of the page indicated by the page number and stored in step 11, and the character recognition of FIG.
After the automatic correction of step 2 (step 12), as shown in FIG. 10 (a display example diagram of the recognition result of the electronic filing apparatus in the embodiment of the present invention), the image in the storage target area and the recognition result are It is displayed in contrast.

As shown in FIG. 11, the following processing is performed during the character recognition processing. First, the character of interest is aligned with the first character (step 20), and this character is recognized (step 21). If there is no character of interest (step 22), the process returns to the original process. On the other hand, if the noted character exists, it is saved character by character in the recognition result storage unit 16 and it is checked whether the saved character number exceeds the maximum character number as the document name or the document code (step 24). If it is less than the maximum number of characters, the target character is updated (step 25) and the process returns to step 21. If the maximum number of characters is exceeded, a warning is displayed on the display unit 23 (step 26) and the original processing is returned to.

Next, in step 12 of FIG. 4, automatic correction is performed according to the set correction conditions. As shown in FIG. 12, the line feed code (step 30) ,? As (step 31) and * (step 32), the processes from step 33 onward are performed. First, in step 33, a processing target is searched in the recognition result of the recognition result storage unit 16 (step 33), and if there is no processing target, the process returns to the original processing (step 34). If there is even one processing target, it is checked in the correction condition storage unit 18 whether the correction condition of the processing target is replacement (step 35). If it is replacement, the processing target is stored in the replacement character storage unit 19. The replacement character (blank in this embodiment) is replaced (step 36). If the condition is not a replacement, all the corresponding processing targets are deleted (step 37). When the above is completed, the original processing is returned to.

Next, in step 13 of FIG. 4, the image in the recognition target area and the recognition result are displayed in contrast with each other, and the manual correction by the user is accepted (step 14). Figure 1
In the display example of 0, the first part of the document and the third part of the document have the correct recognition result, but the second part of the document should be recognized as “Saitama prefecture” and is incorrectly recognized as “Saio prefecture”. I have recognized it. Therefore, the user clicks "Saio Prefecture" with the mouse 5 to make it a correction target, and corrects "King" to "Ball" from the keyboard for accuracy.

When the above processing is completed, the recognition result is stored in the external storage device 6 according to the storage condition.

[0020]

According to the present invention, an image reading section for reading an image of a document, an image storage section for storing the read image, and a recognition target area instructed to perform character recognition in the read image are stored. A recognition target area storage unit, a character recognition unit that performs character recognition on an image in the recognition target area to generate a recognition result, a recognition result storage unit that stores the recognition result, an image in the recognition target area, and a recognition result Since a display unit for displaying and contrasting with each other, a recognition result correction unit for receiving a manual correction of the recognition result, an input unit for inputting correction information of the recognition result, and a control unit for controlling the whole are provided. It is possible to perform filing of a document accurately and easily by omitting troublesome manual input such as a document name.

[Brief description of drawings]

FIG. 1 is a block diagram of an electric filing apparatus according to an embodiment of the present invention.

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

FIG. 3 is a configuration diagram of a document file according to an embodiment of the present invention.

FIG. 4 is a flowchart of an electronic filing device according to an embodiment of the present invention.

FIG. 5 is an exemplary view of a boundary condition window according to an embodiment of the present invention.

FIG. 6 is a view showing an example of a storage condition setting window according to an embodiment of the present invention.

FIG. 7 is a view showing an example of an automatic correction condition window in an embodiment of the present invention.

FIG. 8 is an exemplary view of an original according to an embodiment of the present invention.

FIG. 9 is a view showing an example of an original according to an embodiment of the present invention.

FIG. 10 is a display example diagram of a recognition result of the electronic filing device according to the embodiment of the present invention.

FIG. 11 is a flowchart of an electronic filing device according to an embodiment of the present invention.

FIG. 12 is a flowchart of an electronic filing device according to an embodiment of the present invention.

[Explanation of symbols]

 11 image reading unit 12 image storage unit 13 recognition target area storage unit 14 character recognition unit 16 recognition result storage unit 17 recognition result correction unit 23 display unit 24 input unit 25 control unit

Claims (9)

[Claims] 1. A recognition target area for storing an image reading section for reading an image of a document, an image storage section for storing the read image, and a recognition target area instructed to perform character recognition in the read image. A storage unit, a character recognition unit that performs character recognition on an image in the recognition target area to generate a recognition result, a recognition result storage unit that stores the recognition result, an image in the recognition target area, and the recognition result. And a display unit for displaying the recognition result, a recognition result correction unit for accepting the manual correction of the recognition result, an input unit for inputting correction information of the recognition result, and a control unit for controlling the whole. A characteristic electronic filing device. 2. The electronic filing apparatus according to claim 1, further comprising a document boundary recognition unit that determines boundary conditions of a plurality of documents and recognizes document boundaries. 3. The electronic filing apparatus according to claim 2, wherein the boundary condition is that when the number of sheets exceeds a certain number, it is determined that the document has moved to the next document. 4. The boundary condition is that the size is smaller than that of a document, and when a partition sheet inserted at the boundary of a document is detected, it is determined that the document has moved to the next document. The electronic filing device according to claim 2. 5. The electronic filing apparatus according to claim 2, wherein when the boundary condition exceeds the number specified for the number of documents, it is determined that the document has moved to the next document. 6. The recognition result correction unit also has a function of searching for a specific processing target in the recognition result and replacing the processing target with a specific replacement character.
Electronic filing device as described. 7. The electronic filing apparatus according to claim 1, wherein the recognition result correction section also has a function of searching for a specific processing target in the recognition result and deleting the processing target. 8. The electronic filing apparatus according to claim 6, wherein the processing target includes a line feed code. 9. The electronic filing apparatus according to claim 6 or 7, wherein the processing target includes a signal used as a wild card.