Image segmentation method and apparatus

An image segmentation and image technology, applied in image analysis, image enhancement, image data processing and other directions, can solve the problems of poor image segmentation, over-segmentation, and the pixel points are not smooth enough with color changes.

Active Publication Date: 2016-11-09
甘肃阡陌文化旅游产业有限公司 +1
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] A kind of image segmentation method based on the Graph-based (graph theory) algorithm proposed by Felzenswalb and Huttenlocher is disclosed in the prior art. Although the method is simple in algorithm and easy to implement, when the image is segmented, due to the insufficient color variation of pixels Smooth, there will be over-segmentation phenomenon, that is, there will be small messy areas in the entire area of ​​​​the segmented image, or the entire area will be divided into multiple areas, so that the image segmentation effect is not good

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
  • Image segmentation method and apparatus
  • Image segmentation method and apparatus
  • Image segmentation method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 As shown, it is a flow chart of the image segmentation method provided by the embodiment of the present invention. The principle of the method is: by using the idea of ​​superpixels, when the image is segmented, the different pixels in the adjacent area in the image are averaged to obtain The change of pixel points tends to be smooth, thereby reducing the phenomenon of over-segmentation and improving the image segmentation effect. The methods include:

[0057] S110, map all the pixels of the image into the CIELAB color space, each pixel corresponds to a unique pixel feature; the pixel feature includes the two-dimensional coordinates of the corresponding pixel on the image and the three-dimensional map to the CIELAB color space coordinate.

[0058] Specifically, the image to be segmented is placed in two-dimensional space coordinates, and the pixels in the image are arranged in an orderly manner one by one, and each pixel point uniquely corresponds to ...

Embodiment 2

[0120] As a preferred solution of the first embodiment above, the difference from the first embodiment is that after step A4 and before step A5, the method also includes:

[0121] If the difference between the two-dimensional coordinates of the center of the kth pre-segmented superpixel in the image and the two-dimensional coordinates of the center of the corresponding first region in the image is greater than the third threshold, then move the center of the kth pre-segmented superpixel to the position corresponding to the minimum color gradient in the RGB color space in the image; the position corresponding to the minimum color gradient in the RGB color space in the image is located in the third region centered on the kth pre-segmented superpixel.

[0122] In this embodiment, when calculating the first superpixel, the center positions of some pre-segmented superpixels obtained may be at the edge positions or noise points of the image. The pixels in the area are severely uneve...

Embodiment 3

[0126] Such as figure 2 As shown, it is a schematic structural diagram of an image segmentation device provided by an embodiment of the present invention, which is used to perform the above-mentioned figure 1 The method shown, the device comprises:

[0127] CIELAB color space mapping module 210, for mapping all pixels of the image into CIELAB color space, each pixel corresponds to a unique pixel feature; the pixel feature includes the two-dimensional coordinates and mapping of the corresponding pixel on the image to three-dimensional coordinates in the CIELAB color space;

[0128] The first superpixel acquisition module 220 is used to evenly divide all the pixels of the image into the preset number of first superpixels first regions, and perform similar pixel processing on each first region and the pixels in its vicinity. dividing the points to obtain the first superpixel corresponding to the first region;

[0129] The second superpixel acquisition module 230 is configured...

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

Embodiments of the invention provide an image segmentation method and apparatus. The method comprises the steps of mapping all pixel points of an image into a CIELAB color space; uniformly segmenting the image into first regions with the same number as first super-pixels, and performing partition on pixel points in each first region and regions near the first region to obtain the first super-pixels corresponding to the first regions; mapping all the first super-pixels into an RGB color space, averaging pixel points in the first super-pixels to obtain corresponding second super-pixels, and constructing an undirected graph by taking all the second super-pixels as vertexes and taking a similar distance between every two adjacent second super-pixels as an edge; and forming a segmented region by the two adjacent second super-pixels with the similar distance meeting a preset condition in the undirected graph, and judging whether the adjacent segmented regions are combined or not according to a weight value of the edge in the adjacent segmented regions. According to the embodiments of the image segmentation method and apparatus, the pixel points in the image can be changed smoothly, the over-segmentation phenomena are reduced, and the image segmentation effect is improved.

Description

technical field [0001] The invention relates to the technical field of computer image processing, in particular to an image segmentation method and device. Background technique [0002] With the continuous development of the computer field, users have higher and higher requirements for image processing technology. Image segmentation, as a basic work of computer image processing technology, has become a research hotspot. [0003] Image segmentation refers to the segmentation of areas with special meaning in a digital image, and these areas do not overlap with each other. The properties of images between any adjacent areas are obviously different. Under the criterion, it can be considered to have the same property, that is, the images in each region satisfy a specific region consistency condition. For example, in a painting, a criterion can be defined that colors similar to red can be classified into a region. Based on this criterion, it can be considered that the difference...

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 Applications(China)
IPC IPC(8): G06T7/00
CPCG06T2207/10004G06T2207/10024
Inventor 卢明赵海英贾耕云
Owner 甘肃阡陌文化旅游产业有限公司
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