Method and apparatus for processing a document by utilizing an image

• US 5,101,448 A
• Filed: 08/21/1989
• Issued: 03/31/1992
• Est. Priority Date: 08/24/1988
• Status: Expired due to Term

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Kawachiya, Sachiko, Takeda, Haruo
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): Klocinski, Steven P.
• Application Number:
  US07/397,117
• Time in Patent Office: 953 Days
• Field of Search: 382/61, 382/54, 382/46, 358/464, 340/747
• US Class Current: 382/287
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G06F 40/177 of tables; using ruled lines
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables

Abstract

A document processor for processing a document image which includes both a table formed by a plurality of ruled lines, and characters to generate vector data defining the ruled lines comprises an image input device for reading an image of the document, a display for displaying the document image and a processor for processing the document image. The processor corrects a skew of the input document image, detects a successive black pixel area included in the skew-corrected image, detects a character area based on a size of a rectangle which circumscribes the successive black pixel area, and converts the image to a second document image having characters deleted and including only the ruled lines. Those line segments detected by horizontally scanning the second document image which are longer than a predetermined threshold are determined as horizontal temporary lines, and those segments detected by vertically scanning the second document image which are longer than a predetermined threshold are determined as vertical temporary lines, and data defining positons and sizes of those lines are stored. A plurality of horizontal temporary lines which are adjacent to each other are consolidated into one solid line and defining data for the horizontal ruled lines are determined. Similarly, a plurality of vertical temporary lines are consolidated and defining data for the vertical ruled lines are determined.

Claims

1. A method for processing a document in a document processor having image input means and display means, comprising:

a first step of converting a document including a plurality of characters and a table having a plurality of vertical and horizontal ruled lines into a document image by said image input means;

a second step of converting the document image into a second document image including only the ruled lines;

a third step of scanning said second document image to detect and store vector data of a plurality of line segments each comprising said ruled lines and including one or more of successive black pixels arranged on a scan line in a direction;

a fourth step of determining a threshold value of successive black pixels for distinguishing horizontal ruled lines form vertical ruled lines in said second document image, based on frequencies of line segment length in the second document image calculated from said stored vector data of the line segments;

a fifth step of extracting horizontal ruled lines and vertical ruled lines from said second document image on the basis of said threshold value of successive black pixels and said stored vector data of the line segments to obtain vector data defining respective ruled lines; and

,

a sixth step of drawing on a screen of said display means a table form comprising a plurality of ruled lines drawn on the basis of said vector data of the ruled lines.

2. The method for processing a document according to claim 1 wherein said second step includes a step of determining circumscribed rectangles of respective successive black pixel areas included in the document image, and a step of substituting black pixels located in each circumscribed rectangle having smaller size than a predetermined size on the document image, with white pixels.

3. The method for processing a document according to claim 1 wherein said fifth step includes a step of extracting a plurality of horizontal ruled lines from the second document image to generate vector data representing start points, end points and line widths of respective horizontal ruled lines, and a step of extracting a plurality of vertical ruled lines from the second document image to generate vector data representing start points, end points and line width of respective vertical ruled lines.

4. The method for processing a document according to claim 3 wherein said horizontal ruled lines are extracted by excluding form a plurality of line segments each having one or more black pixels detected by sequentially scanning the second document image in a horizontal direction, those line segments each comprising less number of black pixels than said threshold value, and wherein the vertical ruled lines are extracted by excluding from a plurality of line segments each having one or more black pixels, detected by sequentially scanning the second document image in a vertical direction, those line segments each comprising less number of black pixels than said threshold value.

5. The method for processing a document according to claim 4 wherein the vector data of the horizontal ruled lines are generated by consolidating those line segments extracted by the horizontal scan, which are in adjacent positional relationship into one line segment having an increased line width and/or length and by detecting a start point, an end point and a line width of the consolidated line segment, and the vector data of the vertical ruled lines are generated by consolidating those line segments extracted by the vertical scan, which are in adjacent positional relationship, into one line segment having an increased line width and/or line length and detecting a one of the start points, a one of the end points and line width of the consolidated line segment.

6. The method for processing a document according to claim 3 further comprising a step of comparing the vector data representing the vertical ruled lines, with the vector data representing the horizontal ruled lines of the vector data generated in said third step to selectively correct the start points and the end points.

7. The method for processing a document according to claim 1 further comprising a step of detecting a skew of the document image generated in said first step to correct the skew, wherein said second step is carried out for the skew-corrected document image.

8. The method for processing a document according to claim 1 further comprising a step of detecting a plurality of sections constituting the table and having upper, lower, left and right side segments therefor sectioned by ruled lines based on the vector data of said ruled lines generated in said fifth step.