# US 2023/0274565 A1 · Image, pattern and character recognition

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

- Number: US 2023/0274565 A1
- Document ID: US20230274565A1
- Status: Published application
- Kind: A1
- Application number: 18/143,501
- Filed: 2023-05-04
- Published: 2023-08-31
- Earliest claimed: 2020-12-04
- Assignees: Beijing Sogou Technology Development Co., Ltd.
- Applicants: Beijing Sogou Technology Development Co., Ltd.
- Inventors: Congtao WANG; Jiajun YANG; Yuanming WEI; Wei CHEN; Tao WEI; Jun WU; Li GONG; Weiji ZHU
- Web page: https://patentgrep.com/patent/US20230274565A1

## CPC

- G06V 30/15: {Cutting or merging image elements, e.g. region growing, watershed or clustering-based techniques}
- G06V 30/153: {using recognition of characters or words}
- G06F 40/58: Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
- G06V 10/96: Management of image or video recognition tasks
- G06V 30/10: Character recognition
- G06V 30/20: Combination of acquisition, preprocessing or recognition functions
- G06V 30/413: Classification of content, e.g. text, photographs or tables
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Some aspects of the disclosure provide a method for image processing. The method includes receiving one or more first images corresponding to first portions in a section of characters for recognition, splicing the one or more first images into a first intermediate spliced image and performing a first intermediate character recognition on the first intermediate spliced image based on a first optical character recognition model. The first intermediate character recognition generates a first intermediate recognition result for display. The method further includes performing a final character recognition on a final spliced image corresponding to the section of characters for recognition based on a second optical character recognition model that is different from the first optical character recognition model. The final character recognition generates a final recognition result of the section of characters. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.

## Claims

### Claim 1

A method for image processing, comprising:
receiving one or more first images corresponding to first portions in a section of characters for recognition;
splicing the one or more first images into a first intermediate spliced image;
performing a first intermediate character recognition on the first intermediate spliced image based on a first optical character recognition model, the first intermediate character recognition generating a first intermediate recognition result for display; and
performing a final character recognition on a final spliced image corresponding to the section of characters for recognition based on a second optical character recognition model that is different from the first optical character recognition model, the final character recognition generating a final recognition result of the section of characters.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
the receiving the one or more first images comprises:
receiving the one or more first images via a first thread of execution, the first thread of execution providing the one or more first images captured in real time; and
the splicing the one or more first images comprises:
splicing the one or more first images via a second thread of execution, the second thread of execution splicing the one or more first images into the first intermediate spliced image in real time.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first optical character recognition model requires less computation than the second optical character recognition model.

### Claim 4 (depends on 1)

The method of claim 1, wherein the performing the first intermediate character recognition comprises:
in response to a number of frames of the one or more first images being equal to or greater than a threshold, performing the first intermediate character recognition.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
receiving one or more second images corresponding to second portions in the section of characters for recognition;
splicing the one or more second images with the first intermediate spliced image into a second intermediate spliced image; and
performing a second intermediate character recognition on the second intermediate spliced image based on the first optical character recognition model, the second intermediate character recognition generating a second intermediate recognition result for display.

### Claim 6 (depends on 5)

The method of claim 5, wherein the performing the second intermediate character recognition further comprises:
after a predetermined time from the first intermediate character recognition, performing the second intermediate character recognition.

### Claim 7 (depends on 1)

The method of claim 1, wherein the performing the final character recognition further comprises:
in response to a status change for acquiring images, detecting an end of the section of characters; and
performing the final character recognition in response to the detection of the end of the section.

### Claim 8

An apparatus for image processing, comprising processing circuitry configured to:
receive one or more first images corresponding to first portions in a section of characters for recognition;
splice the one or more first images into a first intermediate spliced image;
perform a first intermediate character recognition on the first intermediate spliced image based on a first optical character recognition model, the first intermediate character recognition generating a first intermediate recognition result for display; and
perform a final character recognition on a final spliced image corresponding to the section of characters for recognition based on a second optical character recognition model that is different from the first optical character recognition model, the final character recognition generating a final recognition result of the section of characters.

### Claim 9 (depends on 8)

The apparatus of claim 8, wherein the processing circuitry is configured to:
receive the one or more first images via a first thread of execution, the first thread of execution providing the one or more first images captured in real time; and
splice the one or more first images via a second thread of execution, the second thread of execution splicing the one or more first images into the first intermediate spliced image in real time.

### Claim 10 (depends on 8)

The apparatus of claim 8, wherein the first optical character recognition model requires less computation than the second optical character recognition model.

### Claim 11 (depends on 8)

The apparatus of claim 8, wherein the processing circuitry is configured to:
in response to a number of frames of the one or more first images being equal to or greater than a threshold, perform the first intermediate character recognition.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the processing circuitry is configured to:
receive one or more second images corresponding to second portions in the section of characters for recognition;
splice the one or more second images with the first intermediate spliced image into a second intermediate spliced image; and
perform a second intermediate character recognition on the second intermediate spliced image based on the first optical character recognition model, the second intermediate character recognition generating a second intermediate recognition result for display.

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein the processing circuitry is configured to:
after a predetermined time from the first intermediate character recognition, perform the second intermediate character recognition.

### Claim 14 (depends on 8)

The apparatus of claim 8, wherein the processing circuitry is configured to:
in response to a status change for acquiring images, detect an end of the section of characters; and
perform the final character recognition in response to the detection of the end of the section.

### Claim 15

A non-transitory computer-readable storage medium storing instructions which when executed by at least one processor cause the at least one processor to perform:
receiving one or more first images corresponding to first portions in a section of characters for recognition;
splicing the one or more first images into a first intermediate spliced image;
performing a first intermediate character recognition on the first intermediate spliced image based on a first optical character recognition model, the first intermediate character recognition generating a first intermediate recognition result for display; and
performing a final character recognition on a final spliced image corresponding to the section of characters for recognition based on a second optical character recognition model that is different from the first optical character recognition model, the final character recognition generating a final recognition result of the section of characters.

### Claim 16 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the instructions cause the at least one processor to perform:
receiving the one or more first images via a first thread of execution, the first thread of execution providing the one or more first images captured in real time; and
splicing the one or more first images via a second thread of execution, the second thread of execution splicing the one or more first images into the first intermediate spliced image in real time.

### Claim 17 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the first optical character recognition model requires less computation than the second optical character recognition model.

### Claim 18 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the instructions cause the at least one processor to perform:
in response to a number of frames of the one or more first images being equal to or greater than a threshold, performing the first intermediate character recognition.

### Claim 19 (depends on 18)

The non-transitory computer-readable storage medium of claim 18, wherein the instructions cause the at least one processor to perform:
receiving one or more second images corresponding to second portions in the section of characters for recognition;
splicing the one or more second images with the first intermediate spliced image into a second intermediate spliced image; and
performing a second intermediate character recognition on the second intermediate spliced image based on the first optical character recognition model, the second intermediate character recognition generating a second intermediate recognition result for display.

### Claim 20 (depends on 19)

The non-transitory computer-readable storage medium of claim 19, wherein the instructions cause the at least one processor to perform:
after a predetermined time from the first intermediate character recognition, performing the second intermediate character recognition.
