JP2851089B2 - Table processing method - Google Patents

Description

Description: TECHNICAL FIELD The present invention relates to a method of processing a table in an image such as a document or a form in a character recognition device or the like.

[Conventional technology]

When a document image is processed by a character recognition device, the image is often divided into a character area, an image area such as a photograph or a drawing, a table area, and the like, and each processing is performed separately.

With respect to the table area, a method is used in which each frame in the table is recognized using the position coordinates of the ruled line, and characters are cut out from the image in each frame.

In the processing of such a table, conventionally, a rectangle of a ruled line in the main scanning direction and the sub-scanning direction which constitutes a frame is extracted, and a frame is defined using coordinates inside the rectangle (as viewed from the inside of the frame). ing.

[Problems to be solved by the invention]

However, there has been a problem that when a document image is input with an inclination, characters in the frame cannot be cut out correctly.

For example, in the case of an image as shown in FIG. 4, a solid line is a ruled line (line segment), which is extracted as a rectangle like a broken line. FIG. 5 is an explanatory diagram of a rectangle of a ruled line in the main scanning direction (X direction), where 51 is an actual ruled line input, and 52 is the rectangle. Then, a frame surrounded by the ruled line is recognized. At that time, the coordinates inside the rectangle of the ruled line are conventionally used. For example, in the case of a rectangle in the main scanning direction constituting the upper side of the frame, the Y coordinate of the upper side of the frame is defined by the coordinates Ye shown in FIG. Therefore, in the case of the inclined image shown in FIG. 4, the hatched area is extracted as a frame area, and the frame becomes narrower than it actually is. As a result, characters approaching the ruled line in the frame may protrude from the frame and may not be cut out normally.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a table processing method capable of correctly cutting out and recognizing characters in a table even when a document image is input at an angle.

[Means for solving the problem]

According to the table processing method of the present invention, a rectangle including ruled lines in the main scanning direction and the layer scanning direction is extracted in a table area, and a frame surrounded by the ruled line is used by using coordinates outside the rectangle of the ruled line (as viewed from within the frame). And find the circumscribed rectangle of the black connection in the frame,
The present invention is characterized in that a circumscribed rectangle in contact with a frame is removed, and characters in the frame are cut out using the remaining circumscribed rectangle.

(Operation)

To recognize the frame using the coordinates outside the rectangle of the ruled line,
Even when the document is inclined, the width of the recognized frame does not become extremely narrower than it actually is, so that character missing can be prevented.

For example, in the case of the image of the same inclined table as the image shown in FIG. 4, according to the present invention, the recognized frame is widened as shown in FIG.

On the other hand, since the coordinates outside the rectangle of the ruled line are used, a part of the ruled line constituting the frame is included in the recognized frame.
However, by excluding the circumscribed rectangle of the black connection in the frame that touches the frame, the line segment portion of such a ruled line can be removed.

Therefore, even in the case of a tilted document image, characters in the table can be correctly cut out and recognized.

〔Example〕

FIG. 1 is a block diagram showing an embodiment of the present invention, and FIG. 2 is a flowchart of a process.

The document is read by the binary image input unit 11 such as a scanner, and the binary image is stored in the binary image memory 12 (processing step 31). For this document image, the table area recognition unit 13 recognizes the table area and stores the image in the table area image memory 14 (processing step 32). The table area recognition includes a method of automatically recognizing the area using a run-length distribution or the like, and a method of recognizing the area by designating the area from outside using a mouse or the like.

The main scanning direction line segment extraction unit 15 traces black pixels connected in the main scanning direction with respect to the table area image, extracts a rectangle surrounding the ruled line in the main scanning direction, and sets its starting point coordinates (Xs, Y
s) and end point coordinates (Xe, Ye) in the main scanning direction line segment memory
16 (see FIG. 5, processing step 33).

The sub-scanning direction line segment extraction unit 17 similarly extracts a ruled line rectangle in the sub-scanning direction from the table area image, and stores the start and end point coordinates in the sub-scanning direction line segment coordinate memory 18 (processing step 34). .

Next, the frame recognizing unit 19 recognizes the frame based on a combination of the ruled line in the main scanning direction and the ruled line in the sub-scanning direction, and stores, for example, the coordinates of a diagonal vertex of the frame in the frame coordinate memory 20 (step
35). At this time, as described above, the coordinates outside the rectangle of the ruled line forming the frame (upper ruled line, lower side ruled line lower, left side ruled line outer, right side ruled line lower coordinate)
Is used to find the coordinates of the diagonal vertices of the frame. In this way, a frame region as shown as a hatched region in FIG. 3 is recognized.

Next, in the frame area extracting unit 21, an image in the frame is cut out from the table area image in accordance with the frame coordinates and stored in the in-frame image memory 22 (processing step 36).

The black-connected circumscribed rectangle extracting unit 23 extracts a black-connected circumscribed rectangle from the image inside the frame, and stores the coordinates of the circumscribed rectangle memory
Stored in 24 (processing step 37).

The line cutout unit 25 checks the contact between the circumscribed rectangle and the frame by comparing the coordinates of the extracted black-connected circumscribed rectangle with the coordinates of the frame, and determines the black-connected circumscribed rectangle that is in contact with the frame with the ruled line forming the frame. It is regarded as a part and removed (processing step 38).
Then, for the remaining black connected circumscribed rectangle in the frame, the character size is estimated and integrated to generate a character line (integrated rectangle of the circumscribed rectangle forming the character element) in the frame, and the necessary correction or After deletion, the final character line image is cut out from the in-frame image memory 22 and the line image memory 26 is deleted.
(Processing steps 39, 40, 41, 42).

Next, the character extraction / recognition unit 27 extracts and recognizes characters from the character line image (processing step 44).

〔The invention's effect〕

As is apparent from the above description, according to the present invention, even when a document image is input with an inclination, the frame to be recognized does not become inappropriately narrower than the actual frame, thereby preventing the character image from being lost. In order to remove the ruled lines constituting the frame prior to character extraction by removing the rectangles that touch the frame by black connection in the recognized frame, character extraction and recognition are performed. Can be done accurately.

[Brief description of the drawings]

FIG. 1 is a block diagram showing an embodiment of the present invention, FIG. 2 is a flowchart of a process, FIG. 3 is an explanatory diagram of frame recognition, FIG.
FIG. 5 is an explanatory diagram of a problem of frame recognition by a conventional method, and FIG. 5 is an explanatory diagram of a ruled line rectangle. 11: Binary image input unit, 13: Table area recognition unit, 15: Main scanning direction line segment extraction unit, 17: Sub-scanning direction line segment extraction unit, 19: Frame recognition unit, 21: Frame Area extraction unit, 23: Black connected circumscribed rectangle extraction unit, 25: Line extraction unit, 27: Character extraction / recognition unit

Claims (1)

(57) [Claims] In a table area, rectangles of ruled lines in a main scanning direction and a sub-scanning direction are extracted, and a frame surrounded by the ruled lines is recognized using coordinates outside the rectangle of the ruled lines. A table processing method comprising: obtaining a rectangle; removing a circumscribed rectangle in contact with the frame; and cutting out characters in the frame using the remaining circumscribed rectangle.