# US 2014/0193075 A1 · Local Scale, Rotation and Position Invariant Word Detection for Optical Character Recognition

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

- Number: US 2014/0193075 A1
- Document ID: US20140193075A1
- Status: Published application
- Kind: A1
- Application number: 13/734,760
- Filed: 2013-01-04
- Published: 2014-07-10
- Earliest claimed: 2013-01-04
- Assignees: Ricoh Company, Ltd.
- Inventors: Sri-Kaushik Pavani; Ekta Prashnani
- Web page: https://patentgrep.com/patent/US20140193075A1

## CPC

- G06V 20/62: Text, e.g. of license plates, overlay texts or captions on TV images
- G06V 30/1478: {of characters or characters lines}
- G06V 30/224: of printed characters having additional code marks or containing code marks
- G06V 30/10: Character recognition
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A system and method using a text extraction application for identifying words with multiple orientations from an image are described. The text extraction application receives an input image, generates progressively blurred images, detects blobs in the blurred images, outputs ellipses over the blobs, detects a word in the input image, orients and normalizes a first version of the word, generates an inverted version of the word, performs OCR on the first version and the inverted version of the word, generates confidence scores for the first version and the inverted version of the word and outputs text associated with the word.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving an input image;
generating progressively blurred images from the input image;
detecting blobs in the blurred images;
outputting ellipses over the blobs;
detecting, using one or more computing devices, a word in the input image based on the ellipses;
orienting and normalizing, using the one or more computing devices, the word;
performing optical character recognition on the word; and
outputting, using the one or more computing devices, text associated with the word.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
generating an inverted version of the word;
generating a confidence score for a first version of the word and the inverted version of the word; and
wherein the text associated with the word is associated with the word having a higher confidence score.

### Claim 3 (depends on 1)

The method of claim 1, further comprising generating a representative ellipse for the word.

### Claim 4 (depends on 3)

The method of claim 3, wherein determining the representative ellipse for the word comprises:
removing ellipses that are non-words using word filters;
retaining at least one ellipse for the word in the input image; and
determining the representative ellipse for the word based on an aspect ratio of the at least one ellipse.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
comparing the text associated with the word to a dictionary definition; and
adjusting the text based on the comparison.

### Claim 6 (depends on 1)

The method of claim 1, wherein orienting and normalizing the first version of the word comprises:
determining an orientation of the first version of the word; and
normalizing the orientation of the first version of the word to an upright orientation.

### Claim 7 (depends on 1)

The method of claim 1, further comprising outputting the text associated with the word for performing an image match and retrieving a document that includes the text.

### Claim 8 (depends on 1)

The method of claim 1, further comprising outputting the text associated with the word for performing translation on the text.

### Claim 9

A system comprising:
one or more processors;
a controller stored on a memory and executable by the one or more processors, the controller configured to receive an input image;
a word detection engine configured to generate progressively blurred images from the input image, to detect blobs in the blurred images, to output ellipses over the blobs and to detect a word in the input image based on the ellipses;
a word orientation engine configured to orient and normalize the word; and
an optical character recognition (OCR) engine configured to perform optical character recognition on the word and output text associated with the word.

### Claim 10 (depends on 9)

The system of claim 9, wherein the word orientation engine is further configured to:
generate an inverted version of the word;
generate a confidence score for a first version of the word and the inverted version of the word; and
wherein the text associated with the word is associated with the word having a higher confidence score.

### Claim 11 (depends on 9)

The system of claim 9, wherein the word detection engine is further configured to generate a representative ellipse for the word.

### Claim 12 (depends on 11)

The system of claim 11, wherein determining the representative ellipse for the word comprises:
removing ellipses that are non-words using word filters;
retaining at least one ellipse for the word in the input image; and
determining the representative ellipse for the word based on an aspect ratio of the at least one ellipse.

### Claim 13 (depends on 9)

The system of claim 9, wherein the OCR engine is further configured to:
compare the text associated with the word to a dictionary definition; and
adjust the text based on the comparison.

### Claim 14 (depends on 9)

The system of claim 9, wherein orienting and normalizing the first version of the word comprises:
determining an orientation of the first version of the word; and
normalizing the orientation of the first version of the word to an upright orientation.

### Claim 15

A computer program product comprising a computer useable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:
receive an input image;
generate progressively blurred images from the input image;
detect blobs in the blurred images;
output ellipses over the blobs;
detect a word in the input image based on the ellipses;
orient and normalize the word;
perform optical character recognition on the word; and
output text associated with the word.

### Claim 16 (depends on 15)

The computer program product of claim 15, further comprising:
generating an inverted version of the word;
generating a confidence score for a first version of the word and the inverted version of the word; and
wherein the text associated with the word is associated with the word having a higher confidence score.

### Claim 17 (depends on 16)

The computer program product of claim 16, further comprising generating a representative ellipse for the word.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein determining, the representative ellipse for the word comprises:
removing ellipses that are non-words using word filters;
retaining at least one ellipse for the word in the input image; and
determining the representative ellipse for the word based on an aspect ratio of the at least one ellipse.

### Claim 19 (depends on 15)

The computer program product of claim 15, wherein the computer readable program when executed on the computer further causes the computer to:
compare the text associated with the word to a dictionary definition; and
adjust the text based on the comparison.

### Claim 20 (depends on 15)

The computer program product of claim 15, wherein orientating and normalizing the first version of the word comprises:
determining an orientation of the word; and
normalizing the orientation of the first version of the word to an upright orientation.