A character denoising method and terminal based on binarization

A binarization and character technology, applied in the field of data processing, can solve problems such as the inability to identify connected domains of area noise points, poor denoising effect, etc.

Active Publication Date: 2021-08-20
厦门商集网络科技有限责任公司
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above method can only identify the connected domain of noise points with a smaller area, but cannot identify the connected domain of noise points with a larger area, and the denoising effect is poor.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A character denoising method and terminal based on binarization
  • A character denoising method and terminal based on binarization
  • A character denoising method and terminal based on binarization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0160] Such as figure 1 As shown, the present embodiment provides a binarization-based character denoising method, including:

[0161] S1. Binarize a character image of a single character to obtain a single character image.

[0162] Among them, image binarization is to set the gray value of the pixel on the image to 0 or 255, that is, the process of presenting an obvious black and white effect to the entire image. For example, in this embodiment, a single character in a character image is set to black, and the background of the character image is set to white. Binarizing the character image first can effectively distinguish the character from the background, and improve the efficiency of subsequent noise removal.

[0163] S2. Detect connected domains of the single-character image to obtain a first set of connected domains.

[0164] Among them, the connected domain refers to a collection of all connected points, and the connected points form a region, while the disconnected ...

Embodiment 2

[0285] Such as Figure 12 As shown, this embodiment provides a terminal, including one or more processors 1 and a memory 2, the memory 2 stores a program, and is configured to perform the following steps by the one or more processors 1:

[0286] S1. Binarize a character image of a single character to obtain a single character image.

[0287] Among them, image binarization is the process of setting the gray value of the pixels on the image to 0 or 255, that is, the process of presenting an obvious black and white effect to the entire image. For example, in this embodiment, a single character in a character image is set to black, and the background of the character image is set to white. Binarizing the character image first can effectively distinguish the character from the background, and improve the efficiency of subsequent noise removal.

[0288] S2. Detect connected domains of the single-character image to obtain a first set of connected domains.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a binarization-based character denoising method and a terminal, belonging to the field of data processing. The present invention uses the phenomenon that the maximum number of vertical crossings of all numbers and letters is 3, firstly recognizes the main connected domain of numbers or alphabetic characters from the single-character image, and then connects other connected domains in the single-character image with the main connected domain in turn. Domain as a whole, if the main connected domain and a connected domain other than the main connected domain in the single-character image are taken as a whole, the maximum vertical crossing number is greater than 3, which means that the connected domain cannot be combined with the main connected domain Form a number or letter, the connected domain is a noisy connected domain, which should be removed. Improved the accuracy of denoising connected domains for English and numeric character images.

Description

technical field [0001] The invention relates to a binarization-based character denoising method and a terminal, belonging to the field of data processing. Background technique [0002] In order to improve the accuracy of character recognition, it is necessary to denoise the character image before recognizing characters to reduce interference. A commonly used method for denoising a character image is specifically to search for small invalid connected regions in the binarized character image and delete them. For example, a connected region with an area smaller than 5 pixels is automatically regarded as an isolated noisy connected domain, and the isolated noisy connected domain is deleted to reduce interference information. However, the above method can only identify the connected domain of noise points with a smaller area, but cannot identify the connected domain of noise points with a larger area, and the denoising effect is poor. Contents of the invention [0003] The te...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/34G06K9/40
CPCG06V30/153G06V10/30G06V10/267
Inventor 庄国金郝占龙杜保发陈文传吴建杭林玉玲方恒凯
Owner 厦门商集网络科技有限责任公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap