Optical character reader with tangent detection for detecting tilt of image data

• US 6,175,664 B1
• Filed: 12/11/1998
• Issued: 01/16/2001
• Est. Priority Date: 09/28/1995
• Status: Expired due to Fees

• Current Assignee: NEC Electronics Corporation (Renesas Electronics Corporation)
• Original Assignee: NEC Corporation
• Inventors: Nakashima, Yutaka
• Primary Examiner(s): Bella, Matthew C.
• Assistant Examiner(s): CHAWAN, SHEELA C
• Application Number:
  US09/210,278
• Time in Patent Office: 767 Days
• Field of Search: 382/173, 382/174, 382/177, 382/178, 382/181, 382/183, 382/194, 382/199, 382/229, 382/276, 382/289, 382/292, 382/295, 382/296, 382/279, 358/261.1, 358/280, 358/285, 358/282
• US Class Current: 382/289
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1478 of characters or characters lines

Abstract

A character reader for optically reading and entering characters. The character reader including: an input apparatus for photoelectrically reading characters as an image, creating image data formed by black pixels lying on a white surface, and entering the image data; a tangent detector for generating at least two line segments, each line segment connecting two black pixels within a character string of the image data; and a tilt decider for choosing a representative line segment from the at least two line segments which is representative of the tilt of the character string, on the basis that the distance between two black pixels specifying the representative line segment is longer than the distance between two black pixels specifying another line segment.

Claims

1. A character reader for optically reading and entering characters, comprising:

an input means for photoelectrically reading characters as an image, creating image data formed by black pixels lying on a white surface, and entering the image data;

a tangent detecting means for generating at least two line segments, each line segment connecting two black pixels within a character string of the image data; and

a tilt deciding means for choosing a representative line segment from the at least two line segments which is representative of the tilt of the character string, on the basis that the distance between two black pixels specifying the representative line segment is longer than the distance between two black pixels specifying another line segment.

2. The character reader according to claim 1, wherein:

said tangent detecting means defines a black pixel first detected by scanning the image data from the top portion by one line in a constant direction as a first black pixel, so as to generate a first line segment extending from the first black pixel on the opposite side to the scanning direction, and defines a black pixel at the distal end on the opposite side to a group of black pixels sequentially lying from the first black pixel in the scanning direction as a second black pixel so as to generate a second line segment extending from the second black pixel on the same side as the scanning direction; and

said tilt deciding means chooses the longer one of the first and second line segments as the representative line segment.

3. The character reader according to claim 1, wherein:

said tangent detecting means includes;

a reference point detecting means for detecting a first black pixel that is a black pixel first detected by scanning the image data from the top portion by one line in a constant direction and a second black pixel that is a black pixel located at the distal end on the opposite side to a group of black pixels sequentially lying from the first black pixel in the scanning direction;

a first quasi-reference detecting means for detecting a third black pixel that is a black pixel first detected by scanning a first region obtained by a predetermined condition on the basis of the coordinates of the first black pixel, from the top portion by one line in the same direction as the scanning direction; and

a second quasi-reference detecting means for detecting a fourth black pixel that is a black pixel first detected by scanning a second region obtained by a predetermined condition on the basis of the coordinates of the second black pixel, from the top portion by one line in the same direction as the scanning direction; and

wherein said tilt deciding means, by comparison between a first line segment connecting the first black pixel and the third black pixel and a second line segment connecting the second black pixel and the fourth black pixel, chooses the longer segment of the first and second line segments as the representative tangent.

4. The character reader according to claim 1, wherein:

said tangent detecting means defines a black pixel first detected by scanning the image data from the top portion by one line in the direction from left to right as a first black pixel, so as to generate a first line segment extending leftward from the first black pixel, and defines a black pixel at the distal end of a group of black pixels sequentially lying in the scanning direction from the first black pixel as a second black pixel, so as to generate a second line segment extending rightward from the second black pixel; and

said tilt deciding means chooses the longer one of the first and second line segments as the representative line segment.

5. The character reader according to claim 1, wherein:

said tangent detecting means includes;

a reference point detecting means for detecting a first black pixel that is a black pixel first detected by scanning the image data from the top portion by one line in the direction from left to right and a second black pixel that is a black pixel located at the distal end on the right side of a group of black pixels sequentially lying from the first black pixel in the right direction;

a first quasi-reference detecting means for detecting a third black pixel that is a black pixel first detected by scanning a first region extending leftward and downward from the coordinates of the first black pixel, which region is obtained by a predetermined condition, from the top portion by one line in the same direction as the scanning direction; and

a second quasi-reference detecting means for detecting a fourth black pixel that is a black pixel first detected by scanning a second region extending rightward and downward from the coordinates of the second black pixel, which region is obtained by a predetermined condition, from the top portion by one line in the same direction as the scanning direction; and

wherein said tilt deciding means, by comparison between a first line segment connecting the first black pixel and the third black pixel and a second line segment connecting the second black pixel and the fourth black pixel, chooses the longer line segment of the first and second line segments as the representative line segment.

6. The character reader according to claim 1, wherein:

said tangent detecting means;

requires a first region including one distal end of the character string and extending at a right angle to the direction of row of the character string with a constant width, and a second region including another distal end of the character string and extending at a right angle to the direction of row of the character string with a constant width;

defines a black pixel first detected by scanning the first region from the top portion of the image data by one line in a constant direction as a first black pixel; and

defines a black pixel first detected by scanning the second region from the top portion of the image data by one line in a constant direction as a second black pixel; and

said tilt deciding means chooses a line segment connecting the first black pixel and the second black pixel as the representative line segment.

7. The character reader according to claim 1, wherein:

said tangent detecting means;

requires a first region including the left end of the character string and extending vertically with a constant width, and a second region including the right end of the character string and extending vertically with a constant width;

defines a black pixel first detected by scanning the first region from the top portion of the image data by one line in the direction from left to right as a first black pixel; and

defines a black pixel first detected by scanning the second region from the top portion of the image data by one line in the direction from left to right as a second black pixel; and

said tilt deciding means chooses a line segment connecting the first black pixel and the second black pixel as the representative line segment.

8. A character reader for optically reading and entering characters, comprising:

an input means for photoelectrically reading characters as an image, creating image data formed by black pixels lying on a white surface, and entering the image data;

a tangent detecting means for generating at least two line segments, each line segment connecting two black pixels within a character string of the image data;

a tilt deciding means for choosing a representative line segment from the at least two line segments which is representative of the tilt of the character string, on the basis that the distance between two black pixels specifying the representative line segment is longer than the distance between two black pixels specifying another line segment;

a correcting means for correcting the imaged data on the basis of the tilt of the character string obtained by said tilt deciding means; and

a recognition means for performing character recognition by pattern matching the image data corrected by said correcting means.

9. The character reader according to claim 8, wherein:

said tangent detecting means defines a black pixel first detected by scanning the image data from the top portion by one line in a constant direction as a first black pixel, so as to generate a first line segment extending from the first black pixel on the opposite side to the scanning direction, and defines a black pixel at the distal end on the opposite side to a group of black pixels sequentially lying from the first black pixel in the scanning direction as a second black pixel, so as to generate a second line segment extending from the second black pixel on the same side as the scanning direction; and

said tilt deciding means chooses the longer one of the first and second line segments as the representative line segment.

10. The character reader according to claim 8, wherein:

said tangent detecting means includes;

a reference point detecting means for detecting a first black pixel that is a black pixel first detected by scanning the image data from the top portion by one line in a constant direction and a second black pixel that is a black pixel located at the distal end on the opposite side to a group of black pixels sequentially lying from the first black pixel in the scanning direction;

a first quasi-reference detecting means for detecting a third black pixel that is a black pixel first detected by scanning a first region obtained by a predetermined condition on the basis of the coordinates of the first black pixel, from the top portion by one line in the same direction as the scanning direction; and

a second quasi-reference detecting means for detecting a fourth black pixel that is a black pixel first detected by scanning a second region obtained by a predetermined condition on the basis of the coordinates of the second black pixel, from the top portion by one line in the same direction as the scanning direction; and

wherein said tilt deciding means, by comparison between a first line segment connecting the first black pixel and the third black pixel and a second line segment connecting the second black pixel and the fourth black pixel, chooses the longer line segment of the first and second line segments as the representative line segment.

11. The character reader according to claim 8, wherein:

said tangent detecting means;

requires a first region including one distal end of the character string and extending at a right angle to the direction of row of the character string with a constant width, and a second region including another distal end of the character string and extending at a right angle to the direction of row of the character string with a constant width;

defines a black pixel first detected by scanning the first region from the top portion of the image data by one line in a constant direction as a first black pixel; and

defines a black pixel first detected by scanning the second region from the top portion of the image data by one line in a constant direction as a second black pixel; and

said tilt deciding means chooses a line segment connecting the first black pixel and the second black pixel as the representative line segment.