# US 2008/0304746 A1 · Method and apparatus for character string recognition

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2008/0304746 A1
- Document ID: US20080304746A1
- Status: Published application
- Kind: A1
- Application number: 12/110,524
- Filed: 2008-04-28
- Published: 2008-12-11
- Earliest claimed: 2007-04-27
- Assignees: Nidec Sankyo Corporation
- Inventors: Hiroshi Nakamura
- Web page: https://patentgrep.com/patent/US20080304746A1

## CPC

- G06V 30/158: {using character size, text spacings or pitch estimation}
- G06V 30/10: Character recognition
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

To provide a method and apparatus for character string recognition that enables improvement in accuracy of character recognition while maintaining high-speed operation performance in character recognition.

## Claims

### Claim 1

A method for character string recognition by processing image data obtained through picking up a character string placed on a medium comprising:
a first step of processing the image data into black-and-white binary image data by using a prescribed reference threshold value for binary conversion;
a second step of calculating vertical projection data of the binary image data in a vertical direction perpendicular to a direction of the character string while shifting the binary image data in the direction of the character string;
a third step of detecting positions exceeding a prescribed border judgment threshold value in the vertical projection data obtained through the second step described above as segmentation positions of characters included in the character string; and
a fourth step of segmenting the characters out of the character string according to the segmentation positions of the characters detected through the third step, and examining characteristics of each character segmented; and
further comprising:
a fifth step of judging validity of the border judgment threshold value before the fourth step according to the number of characters included in the character string.

### Claim 2 (depends on 1)

The method for character string recognition according to claim 1:
wherein the reference threshold value for binary conversion is changed when the border judgment threshold value is judged to be invalid by the fifth step, and the image data is processed again into binary image data, and then the first step through the fifth step are carried out again.

### Claim 3 (depends on 2)

The method for character string recognition according to claim 2:
wherein the reference threshold value for binary conversion is changed to be smaller than the initial one when the border judgment threshold value is judged to be invalid by the fifth step.

### Claim 4 (depends on 1)

The method for character string recognition according to claim 1:
wherein the prescribed border judgment threshold value corresponds to the “n+1”-th value of the peak values where the positive peak values included in the vertical projection data are disposed in due order starting from the largest one and the “n” represents the number of characters included in the character string.

### Claim 5 (depends on 1)

An apparatus for character string recognition comprising:
means for recognizing a character string placed on a medium by using the method for character string recognition in accordance with claim 1.

### Claim 6 (depends on 2)

The method for character string recognition according to claim 2:
wherein the prescribed border judgment threshold value corresponds to the “n+1”-th value of the peak values where the positive peak values included in the vertical projection data are disposed in due order starting from the largest one and the “n” represents the number of characters included in the character string.

### Claim 7 (depends on 3)

The method for character string recognition according to claim 3:
wherein the prescribed border judgment threshold value corresponds to the “n+1”-th value of the peak values where the positive peak values included in the vertical projection data are disposed in due order starting from the largest one and the “n” represents the number of characters included in the character string.

### Claim 8 (depends on 2)

An apparatus for character string recognition comprising:
means for recognizing a character string placed on a medium by using the method for character string recognition in accordance with claim 2.

### Claim 9 (depends on 3)

An apparatus for character string recognition comprising:
means for recognizing a character string placed on a medium by using the method for character string recognition in accordance with claim 3.

### Claim 10 (depends on 4)

An apparatus for character string recognition comprising:
means for recognizing a character string placed on a medium by using the method for character string recognition in accordance with claim 4.
