JPH07225810A - Picture processor - Google Patents

Abstract

PURPOSE:To handle a correct area in succeeding processings by storing position information and attributes of respective areas, into which a document picture is divided, as area information in relation to each other and correcting this area information in accordance with user's indication. CONSTITUTION:The picture of a document read by an image read part 10 like a scanner is stored in a picture storage part 11 and is divided into plural areas by an area dividing part 12, and an attribute discriminating part 13 gives an attribute to each area. Position information and attributes of respective areas are stored as area information in an area information storage part 14 while being related to each other. After areas and their attributes are set once, the user confirms the results on a display part 18 to indicate the error correction from an input part 20, and then, an area information correcting part 15 corrects area information in the area information storage part 14 in accordance with the user's indication. Thus, the user can correct positions and attributes of areas to correctly perform the succeeding processing.

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 for reading an image from a document in which components having different attributes such as characters and figures are mixed and processing the image.

[0002]

2. Description of the Related Art In recent years, as an auxiliary function of a desktop publishing system, an image processing apparatus capable of reading an image of a document in which characters, figures or tables are mixed, dividing this image into each area, and performing various editing work is provided. It is being implemented. Further, in many of these areas, the character area is subjected to character recognition to obtain text data.

[0003]

However, in the conventional image processing apparatus, once the area or the attribute of the area is set, it cannot be corrected thereafter. Here, especially for the character area, the attributes of vertical character (vertical writing) and horizontal character (horizontal writing) can be taken, but if these attributes are incorrect, the text data as the character recognition result is completely meaningless. There was a problem that it would not exist. Also, a plurality of areas that should originally be different areas may be treated as one area, or conversely, one area may be mistakenly divided into a plurality of areas, which may interfere with subsequent editing work. There was also a problem that there was.

Therefore, it is an object of the present invention to provide an image processing apparatus capable of handling a correct area.

[0005]

According to the present invention, there is provided an image reading section for taking in an image of an original, an image storing section for storing the taken image, and an area dividing section for dividing the image into a plurality of areas. An attribute determination unit that assigns an attribute to each area, an area information storage unit that stores area information that associates the position information of each area with the attribute, and a display unit that displays the position and attribute of each area,
It has an area information correction unit that corrects the area information stored in the area information storage unit in response to a user's instruction.

[0006]

With the above structure, once the area and the area attributes are set, the user confirms the result on the display unit,
The area information correction unit can correct the error. As a result, the subsequent processing can be performed meaningfully.

[0007]

Embodiments of the present invention will now be described with reference to the drawings. 1 is a block diagram of an image processing apparatus according to an embodiment of the present invention, and FIG. 2 is a functional block diagram of an image processing apparatus according to an embodiment of the present invention. In FIG. 1, reference numeral 1 denotes an R which stores a control program according to the flowchart of FIG.
OM (Read Only Memory), 2 is a CPU (Central Processing Unit) that executes the control program of the ROM 1 and controls each element, and 3 is a RAM (Random Access Memory) that stores various data necessary for executing the control program Four
Is a CR that displays the operating status, area, area attributes, images, etc.
T (cathode ray tube), 5 is an auxiliary storage device such as a magneto-optical disk device for storing image data, 6 is an image scanner for reading an image from an original, 7 is a keyboard for a user to input necessary information, 8 Is CR by user
It is a mouse for designating an arbitrary point on the display screen of T4.

In FIG. 2, 10 is an image reading unit such as a scanner 6 that reads an image of an original, 11 is an image storage unit that stores the read image, 12 is an area dividing unit that divides the image into a plurality of areas, and 13 is an area dividing unit. Is an attribute determination unit that assigns an attribute to each area, 1
Reference numeral 4 denotes an area information storage unit that stores area information including the position and attribute of each area as shown in FIG. 10, and 15 an area information correction unit that corrects the area information of the area information storage unit 14 in response to a user's instruction. Reference numeral 16 denotes a character recognition unit that performs character rectangle extraction, character rectangle integration, character region extraction, and character recognition within each character rectangle for an image, 17 is a data storage unit that stores edited data, and 18 is a position of each region and A display unit that displays attributes, 19 is a control unit that controls each element, and 20 is an input unit for the user to input information. Here, the image storage unit 11 and the area information storage unit 14 are provided in the RAM 3,
The data storage unit 17 is provided in the auxiliary storage device 5, and the CPU 2 is the ROM of the control unit 19, the area dividing unit 12, the attribute determining unit 13, the area information correcting unit 15, and the character recognizing unit 16.
It is realized by executing the control program No. 1.

Next, the operation of the image processing apparatus of this embodiment will be described with reference to FIG. First, in step 1, the image reading unit 10 reads image data from a document and stores it in the image storage unit 11. The image data may be compressed when it is stored in the image storage unit 11, or may be stored as it is if there is enough capacity. FIG. 4 exemplifies a document P. The document P has character regions 22 to 28, a table region 29, and a graphic region 30 which are vertically or horizontally arranged in columns.
It is included. Of course, other ruled lines, images such as binary or multi-valued photographs may be recognized, but in this embodiment, in order to simplify the explanation, a character area (attribute vertical or horizontal) and a table area (A figure component consisting of line segments of a table frame and a character component are mixed in the same area) and a figure (area containing only a figure component which is not recognized as a character) are handled.

Next, in steps 2 to 5, the area dividing unit 12 divides the image data into areas. At this time, the coordinates of the upper left point and the lower right point are obtained as the position information of each area. That is, as shown in FIG. 6, a graphic rectangle surrounding an area that cannot be recognized as a character is generated (step 2), and the character recognition unit 16
Generates a character rectangle enclosing image data that can be recognized as a character as shown in FIG. 5 (step 3), and integrates the character rectangles as shown in FIG. 7 (step 4), as shown in FIG. A character area surrounding the character rectangle integrated with is extracted (step 5). At this time, the attribute determination unit 13 determines whether the character feeding direction of each character region is horizontal or vertical based on the division result of the region dividing unit 12 and the connecting direction of the character rectangle at the time of character integration. The positions of the upper left point and lower right point and the attributes of each area are determined and written in the area information storage unit 14 as area information (step 6). That is, as shown in FIG. 10, the area information is unique to each area. And the position information consisting of the coordinates of the upper left point and the coordinates of the lower right point of the rectangle surrounding each area, and the attribute of that area. Here, regarding the attribute, from the division result and the determination result, only a character exists in a certain area, and if the character feeding direction is vertical, the character vertical and the horizontal character attributes are given. Further, if the graphic component and the character component are mixed in a certain area, the attribute of the table is given, and if the certain area contains only the graphic component, the attribute of the graphic is given. The area dividing section 12, the attribute determining section 13, and the character recognizing section 16 are publicly known.

By the above processing, the layout recognition result as shown in FIG. 9 is automatically obtained. In FIG. Taking A1 as an example, a1 is an upper left point, a2 is a lower right point, and a character “horizontal character” indicates that a character horizontal attribute is given. Then, the display unit 18 displays the position and attribute of each area by superimposing the area information of the area information storage unit 14 and the image data of the image storage unit 11 (step 7).

However, the above division result or discrimination result may be incorrect. In such a case, the problem that the subsequent editing work is hindered is as described in the section of the problem to be solved by the invention. For this reason, this means is provided with the area information correction unit 15 which corrects the area information of the area information storage unit 14 in response to the user's instruction.

FIG. 11 shows an example in which the character "lesson 5" which should be originally integrated is divided into an area A1 containing the word "lesson" and an area A2 consisting of the characters "5". In such a case, the software that controls the subsequent editing work can specify the single area and change the font size and font.
When the user wants to perform such editing work, the user has to specify both the area A1 and the area A2, which is complicated. Therefore, when the user can use the input unit 20 to indicate the point a1 or the upper left point n1 and the point a4 or the lower right point n2 using the input unit 20 when the area can be corrected in step 8, the instructed point Is set as the upper left point and the lower right point, and the area information correction unit 15 deletes the area information of the areas A1 and A2 from the area information storage unit 14 in accordance with the new area N and the area N Information will be written (step 9). At this time, since the attribute remains horizontal, the attribute of the area N is also horizontal.

Further, FIG. 12 shows an example in which the attribute of the area A5 is erroneously recognized as a horizontal character. At this time, if the area A5 is indicated by text data, it is correct that "ABCDEFGHIJ
Although it is "KLMNOP", "M
IEANJFBOKGCPLHD ". And when the user wants to change the number of lines or the number of characters in the subsequent editing work, if the processing is performed while making a mistake,
The processing result is completely different from the editing result desired by the user. Therefore, in step 8, when the user uses the input unit 20 to specify the area A5 and changes the attribute correctly, the area information correction unit 15 writes the attribute of the area A5 in the area information storage unit 14 from the horizontal character to the vertical character. Replace (step 9).

Then, in step 10, the character recognition unit 16 performs character recognition for each character rectangle,
Text data is generated while connecting each character in the direction corresponding to the attribute of the area, and each data obtained by the above processing is held in the data storage unit 11 (step 11). The area information correction unit 15 corrects areas and attributes prior to character recognition and editing work, so that the subsequent processing can be performed smoothly and accurately.

[0016]

According to the present invention, an image reading section for taking in an image of a document, an image storing section for storing the taken image, an area dividing section for dividing the image into a plurality of areas, and an attribute for each area. A region determination unit that assigns the region information, a region information storage unit that stores region information in which the position information of each region is associated with the attribute, and a display unit that displays the position and attribute of each region, and responds to user instructions. Since an area information correction unit that corrects the area information stored in the area information storage unit is included, the user can
The attribute can be corrected and the subsequent processing can be performed correctly.

[Brief description of drawings]

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

FIG. 2 is a functional block diagram of an image processing apparatus according to an embodiment of the present invention.

FIG. 3 is a flowchart of an image processing apparatus according to an embodiment of the present invention.

FIG. 4 is an exemplary view of a document handled by an image processing apparatus according to an embodiment of the present invention.

FIG. 5 is an operation explanatory diagram of the image processing apparatus according to the embodiment of the present invention.

FIG. 6 is an operation explanatory diagram of the image processing apparatus according to the embodiment of the present invention.

FIG. 7 is an operation explanatory diagram of the image processing apparatus according to the embodiment of the present invention.

FIG. 8 is an operation explanatory diagram of the image processing apparatus according to the embodiment of the present invention.

FIG. 9 is an operation explanatory diagram of the image processing apparatus according to the embodiment of the present invention.

FIG. 10 is a data configuration diagram of area information of the image processing apparatus according to the embodiment of the present invention.

FIG. 11 is an operation explanatory diagram of the image processing apparatus according to the embodiment of the present invention.

FIG. 12 is an operation explanatory diagram of the image processing apparatus according to the embodiment of the present invention.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 10 image reading section 11 image storage section 12 area division section 13 attribute determination section 14 area information storage section 15 area information correction section 18 display section P document

Claims (2)

[Claims] 1. An image reading unit that captures an image of an original, an image storage unit that stores the captured image, a region dividing unit that divides the image into a plurality of regions, and an attribute that assigns an attribute to each region. A region information storage unit that stores region information in which the position information of each region and the attribute are associated with each other, and a display unit that displays the position and attribute of each region, and the region information in response to a user's instruction. An image processing apparatus comprising an area information correction unit that corrects area information stored in a storage unit. 2. The image processing apparatus according to claim 1, further comprising a character recognition unit for performing character recognition on each character in the area to which the character attribute is added.