Image segmentation method based on super pixel clustering

A technology of superpixel clustering and image segmentation, applied in image analysis, image data processing, instruments, etc., can solve the problems of difficult identification, inability to achieve real-time, etc., and achieve good fit, good evaluation results, and remarkable effects. Effect

Inactive Publication Date: 2015-12-02
SOUTHEAST UNIV
View PDF6 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the existing segmentation methods with good effects cannot achieve real-time, so it is more difficult to achieve real-time recognition

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 based on super pixel clustering
  • Image segmentation method based on super pixel clustering
  • Image segmentation method based on super pixel clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0033] figure 1 It is a flowchart of the present invention. Depend on figure 1 It can be seen that the method is built on the basis of SLIC and AP, so the SLIC and AP will be introduced first, and then the SLICAP method of the present invention will be introduced.

[0034] (1) SLIC super pixel algorithm

[0035] First convert the color picture to a 5-dimensional feature vector under the CIELAB color space and space coordinates [Labxy] T , and then set the 5-dimensional feature vector metric, and finally the image pixels are locally clustered to complete the superpixel process.

[0036] (1) Initialize the seed point. For example, an image has N pixels, and it is planned to be divided into K superpixels of similar size, then a single superpixel contains about N / K pixels, and the distance between each seed is about The selection of seed points see...

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 an image segmentation method based on super pixel clustering. More specifically the image segmentation method includes the steps of: 1, segmenting images by using a Simple Linear Iterative Clustering (SLIC) algorithm, and generating super pixels; 2, improving a construction mode of a similarity matrix about the super pixels, and fusing a color characteristic and a texture characteristic through non-symmetry of the similarity matrix; 3, clustering the super pixels through an Affinity Propagation (AP) clustering algorithm based on the similarity matrix; and 4, reaching the purpose of image segmentation by adding spatial information of the super pixels and dividing a disconnected region into different types of super pixel groups by means of breadth-first traversal. The image segmentation method based on the super pixel clustering has good segmentation effect and a fast convergence speed. Target objects can be effectively segmented without arrangement of target quantity.

Description

technical field [0001] The invention relates to target detection and contour detection technology, in particular, it provides an image segmentation method based on superpixel clustering. Background technique [0002] Superpixels are generally a collection of pixels with similar characteristics (such as color and spatial location). Superpixels are widely used in the field of image segmentation and object recognition. Compared with the traditional pixel level, superpixel can simplify the original picture and improve the efficiency of image representation. When performing target recognition tasks, it is more convenient and efficient to use superpixels to process images, which can greatly simplify the task and form a more concise representation of the image. [0003] The quality of the target image segmentation has a significant impact on the computer vision recognition rate. At present, there are many algorithms for image segmentation, but most of the proposed segmentation m...

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
Inventor 王海贤周宝
Owner SOUTHEAST UNIV
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