Multi-color grade image connected domain-based segmentation and mark method and device

A marking method and a technology of connected domains, applied in the field of image processing, can solve the problems of running time loss, connected domains that cannot meet the needs of multi-color image connected domain analysis, and color-level image feature description omissions, etc.

Active Publication Date: 2018-01-09
佛山市国方软件科技有限公司 +1
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1. Most of the image connected domain marking methods in the prior art require multiple scans, which consume a lot of running time;
[0006] 2. The connected domains generated by the prior art image connected domain marking method are difficult to meet the needs of multi-color image connected domain analysis, resulting in the omission of some color-level image feature descriptions

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
  • Multi-color grade image connected domain-based segmentation and mark method and device
  • Multi-color grade image connected domain-based segmentation and mark method and device
  • Multi-color grade image connected domain-based segmentation and mark method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] This embodiment discloses a segmentation and labeling method based on multi-color image connected domains, such as figure 1 shown, including the following steps:

[0092] S100. Perform preprocessing on the image, so that the image is divided into two or more color-level image color blocks.

[0093] Images acquired through computer equipment, mobile phones with camera functions, cameras, video cameras or other devices that integrate cameras or store images can be used as input images in the present invention.

[0094] Image preprocessing specifically includes extracting the gray value of the pixel points of the input image, calculating the multi-color level binarization adaptive threshold, and segmenting the image into two or more color-level image blocks. Among them, the calculation method of the binarization adaptive threshold can adopt the technical method of "a method and system for dynamically calculating multi-color binarization adaptive threshold" with the patent...

Embodiment 2

[0125] The segmentation and labeling method based on multi-color level image connected domains disclosed in this embodiment, such as Figure 10 shown, including the following steps:

[0126] S100. Perform preprocessing on the image, so that the image is divided into two or more color-level image color blocks.

[0127] S200. Acquire pixel point data of image blocks of each color level, where the pixel point data includes a color level number or a gray value of a color level, a pixel row number, and a pixel column number.

[0128] S300. According to the pixel point data, respectively find out the connection lines formed by the continuous connected pixel points in the preset direction, obtain sub-line segments, and label the sub-line segments.

[0129] S400. Record line segment numbers of one or more sub-line segments where the pixel point is located in the pixel point data. By corresponding the line segment number with the relevant pixel points, it is realized that the pixel p...

Embodiment 3

[0145] The segmentation and labeling method based on multi-color level image connected domains disclosed in this embodiment, such as Figure 11 shown, including the following steps:

[0146] S100. Perform preprocessing on the image, so that the image is divided into two or more color-level image color blocks.

[0147] S200. Acquire pixel point data of image blocks of each color level, where the pixel point data includes a color level number or a gray value of a color level, a pixel row number, and a pixel column number.

[0148] S300. According to the pixel point data, respectively find out the connection lines formed by the continuous connected pixel points in the preset direction, obtain sub-line segments, and label the sub-line segments.

[0149] S400. Record line segment numbers of one or more sub-line segments where the pixel point is located in the pixel point data. By corresponding the line segment number with the relevant pixel points, it is realized that the pixel p...

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 discloses a multi-color grade image connected domain-based segmentation and mark method and device. The method comprises the following steps of: preprocessing an image to ensure that image color lumps of two or more color grades are divided from the image; obtaining pixel point data of the image color block of each color grade; respectively finding out a connection line formed by pixel points which are continuously connected in at least two preset directions according to the pixel point data so as to obtain a sub-segments, and marking numbers for the sub-segments; recording segment numbers of one or more sub-segments where the pixel points are located in the pixel point data; combining the segment numbers according to a preset connected domain combination rule, considering pixel point sets to which the combined segment numbers belong as a same connected domain, and carrying out color grade classification and numbering on the connected domain; and recording connected domain numbers where the pixel point is located in the pixel point data. According to the method and device, images can be segmented according to color blocks and color block connected domains, so that requirements of image analysis can be satisfied more widely.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a segmentation and labeling method and device based on connected domains of multi-color images. Background technique [0002] Image connected domain marking is a common link in digital image analysis and processing. The marking methods of image connected domain mainly include pixel scanning, that is, point marking method and line segment scanning, that is, line marking method. The pixel point scanning methods include: sequential scanning method, recursive marking method, District City Growth Act, etc. Line segment scanning algorithms mainly include marking algorithms based on run length codes and run length based marking algorithms. These algorithms can accurately mark the target connected domain based on a certain technical purpose. The main difference is that the equivalent labels are handled differently, but the final labeling number is to mark the equivalent...

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
IPC IPC(8): G06T7/11G06T7/187
Inventor 徐庆
Owner 佛山市国方软件科技有限公司
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