# US 2022/0036062 A1 · Text block recognition based on discrete character recognition and text information connectivity

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

- Number: US 2022/0036062 A1
- Document ID: US20220036062A1
- Status: Published application
- Kind: A1
- Application number: 16/942,852
- Filed: 2020-07-30
- Published: 2022-02-03
- Earliest claimed: 2020-07-30
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Zhong Fang Yuan; Zhuo Cai; Tong Liu; Yu Pan; Li Ni Zhang; Jian Long Li
- Web page: https://patentgrep.com/patent/US20220036062A1

## CPC

- G06V 30/274: {Syntactic or semantic context, e.g. balancing}
- G06V 10/40: Extraction of image or video features
- G06V 30/412: Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
- G06V 30/413: Classification of content, e.g. text, photographs or tables
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

In an approach for a text block recognition in a document, a processor detects characters in the document using an object detection technique. A processor identifies positions of the detected characters in the document. A processor analyzes semantic connectivity among the detected characters based on the positions and semantic connectivity of the characters. A processor recognizes text blocks of related characters based on the semantic connectivity analysis. A processor outputs the text blocks associated with the related characters.

## Claims

### Claim 1

A computer-implemented method comprising:
detecting, by one or more processors, characters in a document using an object detection technique;
identifying, by one or more processors, positions of the detected characters in the document;
analyzing, by one or more processors, semantic connectivity among the detected characters based on the positions and semantic connectivity of the characters;
recognizing, by one or more processors, text blocks of related characters based on the semantic connectivity analysis; and
outputting, by one or more processors, the text blocks associated with the related characters.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
receiving, by one or more processors, the document, including tabular data, for processing, the document being a scanned document.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein detecting the characters includes recognizing content of the detected characters.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein analyzing the semantic connectivity includes taking a detected character as a starting point and performing connectivity detection in multiple directions, the connectivity detection being based on a base corpus calculating information entropy gain rate of the connecting characters.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, further comprising:
calculating probability of character units to be connected; and
determining the semantic connectivity based on the calculated probability.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein recognizing the text blocks includes performing text content connection based on probability of the content connection of the related characters.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein outputting the text blocks includes reconstructing a table document based on the text blocks with the corresponding coordinates of the text blocks.

### Claim 8

A computer program product comprising:
one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to detect characters in a document using an object detection technique;
program instructions to identify positions of the detected characters in the document;
program instructions to analyze semantic connectivity among the detected characters based on the positions and semantic connectivity of the characters;
program instructions to recognize text blocks of related characters based on the semantic connectivity analysis; and
program instructions to output the text blocks associated with the related characters.

### Claim 9 (depends on 8)

The computer program product of claim 8, further comprising:
program instructions, stored on the one or more computer-readable storage media, to receive the document, including tabular data, for processing, the document being a scanned document.

### Claim 10 (depends on 8)

The computer program product of claim 8, wherein program instructions to detect the characters include program instructions to recognize content of the detected characters.

### Claim 11 (depends on 8)

The computer program product of claim 8, wherein program instructions to analyze the semantic connectivity includes program instructions to take a detected character as a starting point and program instructions to perform connectivity detection in multiple directions, the connectivity detection being based on a base corpus calculating information entropy gain rate of the connecting characters.

### Claim 12 (depends on 11)

The computer program product of claim 11, further comprising:
program instructions, stored on the one or more computer-readable storage media, to calculate probability of character units to be connected; and
program instructions, stored on the one or more computer-readable storage media, to determine the semantic connectivity based on the calculated probability.

### Claim 13 (depends on 8)

The computer program product of claim 8, wherein program instructions to recognize the text blocks include program instructions to perform text content connection based on probability of the content connection of the related characters.

### Claim 14 (depends on 8)

The computer program product of claim 8, wherein program instructions to output the text blocks include program instructions to reconstruct a table document based on the text blocks with the corresponding coordinates of the text blocks.

### Claim 15

A computer system comprising:
one or more computer processors, one or more computer readable storage media, and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:
program instructions to detect characters in a document using an object detection technique;
program instructions to identify positions of the detected characters in the document;
program instructions to analyze semantic connectivity among the detected characters based on the positions and semantic connectivity of the characters;
program instructions to recognize text blocks of related characters based on the semantic connectivity analysis; and
program instructions to output the text blocks associated with the related characters.

### Claim 16 (depends on 15)

The computer system of claim 15, further comprising:
program instructions, stored on the one or more computer-readable storage media, to receive the document, including tabular data, for processing, the document being a scanned document.

### Claim 17 (depends on 15)

The computer system of claim 15, wherein program instructions to detect the characters include program instructions to recognize content of the detected characters.

### Claim 18 (depends on 15)

The computer system of claim 15, wherein program instructions to analyze the semantic connectivity includes program instructions to take a detected character as a starting point and program instructions to perform connectivity detection in multiple directions, the connectivity detection being based on a base corpus calculating information entropy gain rate of the connecting characters.

### Claim 19 (depends on 18)

The computer system of claim 18, further comprising:
program instructions, stored on the one or more computer-readable storage media, to calculate probability of character units to be connected; and
program instructions, stored on the one or more computer-readable storage media, to determine the semantic connectivity based on the calculated probability.

### Claim 20 (depends on 15)

The computer system of claim 15, wherein program instructions to output the text blocks include program instructions to reconstruct a table document based on the text blocks with the corresponding coordinates of the text blocks.
