Robust texture feature extraction method based on grouping-order mode

A technology of texture features and extraction methods, which is applied in character and pattern recognition, image analysis, image data processing, etc., can solve the problems of noise sensitivity, poor texture characteristic effect, neglect of neighbor pixel relationship, etc., and achieve high feature discrimination, good Robustness, the effect of improving classification accuracy

Active Publication Date: 2018-11-23
CHONGQING UNIV OF POSTS & TELECOMM
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, LBP has a big defect that limits its application, that is, it is sensitive to noise, and the extracted texture features are less effective in classifying noisy images, and ignore the relationship between adjacent pixels.

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
  • Robust texture feature extraction method based on grouping-order mode
  • Robust texture feature extraction method based on grouping-order mode
  • Robust texture feature extraction method based on grouping-order mode

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the accompanying drawings and implementation methods.

[0020] refer to figure 1 , the robust texture feature extraction method based on the grouping-sequential mode of the present invention includes the following steps: obtaining the central pixel x c and the neighbor pixel x p , Neighboring pixel interval grouping, Neighboring pixels after encoding grouping, Histogram statistics, Histogram concatenation.

[0021] Step 1, refer to figure 2 , first obtain each central pixel x of the image to be processed by bilinear interpolation c and its P(P=8+4(r-1)) neighboring pixels x p (p=0,1,...P-1). if x c The coordinates are (0,0), then x p The coordinates of are given by: (-rsin(2πp / P), rcos(2πp / P)). Neighboring pixels that do not fall exactly in the center of the pixel are estimated by interpolation. Then use the mean filter to the 3×3 area X centered on the interpolated pixel p (and X c ) ...

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 robust texture feature extraction method based on a grouping-order mode, and belongs to the fields of image processing and pattern recognition. The main thinking includes: firstly, using bilinear interpolation to obtain each central pixel of a to-be-processed image and neighboring pixels thereof, and carrying out mean filtering on the pixels obtained by interpolation; then carrying out grouping on the neighboring pixels to reduce feature dimensions, and carrying out encoding on a size order among neighboring pixel values in each group after grouping; and finally, carrying out histogram counting on encoding values which are of all the pixels in the image and are obtained in the different groups, and cascading histograms of all the groups to form a final texture feature histogram.

Description

technical field [0001] The invention relates to image feature extraction in the field of image processing and computer vision, in particular to a method for extracting robust texture features based on grouping-sequence mode. Background technique [0002] With the rapid development of network technology and multimedia technology, a large number of different types of image data are emerging on the Internet. And image data has some characteristics that conventional data do not have, such as: non-uniform format, rich and diverse information content, and two-dimensionality of time and space. [0003] Texture is a basic attribute of the appearance of objects in nature. The perception of texture is an important way for human beings to distinguish different objects and understand the external world. The purpose of feature extraction is to reduce the dimensionality of data and obtain features that can reflect the attributes of objects, thereby facilitating classification. A good fe...

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): G06T7/44G06T3/40G06T5/00G06K9/62
CPCG06T3/4007G06T5/00G06T7/44G06F18/24147
Inventor 罗林宋铁成张刚张天骐
Owner CHONGQING UNIV OF POSTS & TELECOMM
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