US 5,966,473 A · Method and apparatus for recognizing a quadrilateral object contained in an input bitmap image

Abstract

Described is an image processing system which is operative to automatically determine a quadrilateral object such as a character frame, page mark, or position correction mark only with a mouse click. A field is automatically specified by displaying a scanned image of a form including a black frame on a display, clicking within a character frame at the left end for each recognition field, and clicking within a character frame at the right end of the same field. In this case, a field position/size determination program scans the image in the vertical and horizontal directions from the two clicked points to detect the inner wall of the black frame, and produces a histogram by establishing rectangles between two character frames to automatically detect the number of character frames in the field and the thickness of the black line between the character frames. In addition, for a form with a page mark or position correction mark, what is the mark can be automatically detected from the surrounding is black, and the height of the mark only by clicking the inside of the mark with a mouse.

Drawings

Drawings are temporarily unavailable. Open the PDF at USPTO

Drawings

Claims6

Dependent claims

A method for recognizing position information of a quadrilateral object contained in an input bitmap image comprising the steps of:

(a) identifying a first input point in the bitmap image;
(b) deriving position information of a first point and a second point by searching along a first rectilinear line passing through near said first input point the first and second points corresponding to a first pixel and a second pixel, respectively, said first and second pixels being pixels existing on said first rectilinear line, and having specific values, and existing in directions symmetric to said first input point, respectively;
(c) deriving position information of a third point and a fourth point by searching along a second rectilinear line which passes through near said first input point and is substantially perpendicular to said first rectilinear line, said third and fourth points corresponding to a third pixel and a fourth pixel, respectively, said third and fourth pixels being pixels existing on said second rectilinear line, and having specific values, and existing in directions symmetric to said first input point, respectively;
and
(d) deriving position information of said quadrilateral object from the position information of said first, second, third and fourth points.

2 more elements

A method for recognizing position information of a plurality of quadrilateral objects contained in an input bitmap image based on information on a first input point and a second input point input by an operator comprising the steps of:

(a) identifying a first input point in said bitmap image;
(b) deriving position information of a first point and a second point by searching along a first rectilinear line passing through near said first input point, said first and second points corresponding to a first pixel and a second pixel, respectively, said first and second pixels being pixels existing on said first rectilinear line, and having specific values, and existing in directions symmetric to said first input point, respectively;
(c) deriving position information of a third point by searching along a second rectilinear line which passes through near said first input point and is substantially perpendicular to said first rectilinear line, said third point corresponding to a third pixel, said third pixel being a pixel existing on said second rectilinear line, and having a specific value, and existing in a direction symmetric to said second input point with respect to said first input point;
(d) deriving position information of a fourth point and a fifth point by searching said fourth and fifth points corresponding to a fourth pixel and a fifth pixel, respectively, said fourth pixel being a pixel existing on a rectilinear line passing through near said second input point and parallel to said second direction, and having a specific value, and existing between said first and second input points, said fifth pixel being a pixel existing on a rectilinear line substantially parallel to said second direction, and having a specific value, and existing in a direction symmetric to said first input point with respect to said second input point;
and
(e) deriving position information of said plurality of quadrilateral objects from the position information of said first, second, third, fourth and fifth points.

3 more elements

Dependencies are inferred from the claim text.

Description7,416 words

Summary1,743 words

#The present invention relates to an image processing method and apparatus, and, more particularly, to a method and apparatus for detecting position information of frames contained in an Optical Character Reader (OCR) form of an input bitmap image based on position information input by an operator.

#In defining an OCR form for having a character recognition program recognize a new formatted OCR form, it should be conventionally required to measure the size of the form, the relative positions and sizes of page marks, position correction marks (also called a timing or reference mark), character fields, characters with a scale and to input their values. However, the definition of OCR forms is troublesome for programmers. For example, it takes an enormous amount of time to design new dropout OCR forms (a form specially prepared for OCR, and printed with characters and character frames in colors that are not sensed by scanners).

#To solve such problems, several conventional techniques have been proposed. As an example, "WinReader Hand, v. 1.5, Users' Manual, Setting of Fields," pp. 19 and 20, Media Drive Co. ("WinReader Hand" is a trademark of Media Drive Co.) describes an approach in which the image of an unfilled form with black frames is captured by a scanner and displayed on a display. All black vertical and horizontal lines are automatically detected and character recognition fields are set after the operator confirms that all rectilinear lines are properly detected.

Brief description of the drawings10 figures

#FIG. 1 is a block diagram of an image processing system in accordance with the present invention.

#FIG. 2 is a block diagram of a system configuration of the image processing system of FIG. 1.

#FIG. 3 is an image of a form input by the scanner in the system of FIG. 1.

Detailed description5,478 words

#Referring to FIG. 1, there is shown a schematic diagram of a hardware configuration for implementing an image processing system in accordance with the present invention. The image processing system 100 includes a central processing unit (CPU) 1 and a memory 4. The CPU 1 and the memory 4 are connected to a hard disk drive 13 as an auxiliary device through a bus 2. A floppy disk drive (or, a drive for a medium such as an MO or a CD-ROM) 20 is connected to the bus 2 through a floppy disk controller 19.

#A floppy disk 24 (or, a medium such as an MO or CD-ROM) is inserted into the floppy disk drive (or, a drive for a medium such as an MO or a CD-ROM) 20. It is possible to record in the floppy disk, the hard disk drive 13 or a ROM 14 codes of a program for providing instructions to a CPU or the like in cooperation with an operating system and for implementing the present invention. These codes are loaded in the memory 4 for execution. The computer program codes may be compressed or divided into a plurality of segments for storage in a plurality of media.

#The image processing system 100 may be a system with user interface hardware. The user interface hardware may include, for example, a pointing device such as a mouse, joystick or track ball 7 for inputting screen position information, a keyboard 6 and a display 12 for presenting image data to a user. In addition, a speaker 23 receives audio signals from an audio controller 21 through an amplifier 22 and outputs it as sound.

Facts

Application

08/949,464Filed 14 Oct 1997

Priority

JP 8-31724228 Nov 1996

Granted

12 Oct 1999

Term ended

14 Oct 2017

Estimated · how

20 years from earliest known nonprovisional domestic filing. Maintenance-fee lapses, terminal disclaimers and statutory extensions have not been checked. The continuity chain may be incomplete; this is not an enforceability determination. Patent term adjustment is unavailable; no adjustment was added.

Classification5 codes

G06T 7/73
Determining position or orientation of objects or cameras: using feature-based methods
G06V 30/1444
Image acquisition: selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
G06V 30/10
Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition: character recognition
G06T
Image data processing or generation, in general

Method and apparatus for recognizing a quadrilateral object contained in an input bitmap image

Life of this patent

Method and apparatus for recognizing a quadrilateral object contained in an input bitmap image

Life of this patent

Life of this patent

Abstract

Drawings

Drawings

Claims6

Description7,416 words

Drawings

Classification5 codes

Life of this patent

Description7,416 words