Skin scar diagnosis method based on secondary harmonic image texture analysis

An image texture and second harmonic technology, which is applied in the intersecting fields of image processing, pattern recognition and biomedicine, can solve the problems of non-existent texture extraction method and texture complexity, and achieve high recognition rate and diagnostic ability

Active Publication Date: 2014-03-12
FUJIAN NORMAL UNIV
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Texture feature extraction has a good application prospect in medical image research, but due to the...

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
  • Skin scar diagnosis method based on secondary harmonic image texture analysis
  • Skin scar diagnosis method based on secondary harmonic image texture analysis
  • Skin scar diagnosis method based on secondary harmonic image texture analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] Texture Feature Extraction and Classification Recognition of Scar Collagen Second Harmonic Image

[0070] The specific process is as follows:

[0071] Step 1. Take the collagen second harmonic images of 20 normal and 10 abnormal scars to be processed as samples, among which 8 normal and 5 abnormal scar images are randomly selected as training set samples, and the others are used as test set samples

[0072] Step 2. Convert the second harmonic images to be processed in the training set and test set into grayscale images

[0073] Such as Figure 4 (a) shows the original second harmonic image of scar collagen, and the converted grayscale image is as follows Figure 4 (b) shown.

[0074] Step 3. Use the LD-LBP method to encode the grayscale image for uniformity feature extraction. Generate LD-LBP code map and calculate LD-LBP variance V 1

[0075] The traditional LBP operator ignores the interrelationships between local textures, and cannot reflect the gray level cha...

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 skin scar diagnosis method based on secondary harmonic image texture analysis. The method comprises the following steps: classifying to-be-treated images into a training set and a test set and transforming the images into gray images; encoding the gray images in an LD-LBP (Local Difference-Local Binary Pattern) way to obtain an LD-LBP code image and a variance V1; performing Haar wavelet transformation on the LD-LBP code image, calculating a low-frequency sub-band coefficient average value ULL, a variance Var, an energy ratio Er and a level sub-band coefficient average value VLH; forming a characteristic vector by use of V1, ULL, Var, Er and ULH and performing gaussian normalization on the characteristic vector; performing a fuzzy K-Nearest neighbor algorithm on the normalized characteristic vector; outputting the category of the test set. The method can be used for achieving non-destructive diagnosis on skin scars and is excellent in identification effect and diagnosis capability, and can be used for solving the destructive problem of scar diagnosis in the prior art and assisting doctors in judging the category of scars and selecting a reasonable therapy method.

Description

technical field [0001] The invention belongs to the intersection field of image processing, pattern recognition and biomedicine, and relates to a skin scar diagnosis method based on second harmonic image texture analysis. Background technique [0002] Scar is a general term for the appearance and histopathological changes of normal skin tissue caused by various traumas. Broadly speaking, scars are divided into two categories: physiological (normal) and pathological (abnormal) scars. Normal scars are asymptomatic and dysfunctional, but they still require treatment due to their instability, discoloration, and tendency to enlarge. Abnormal scars are mainly divided into hypertrophic scars and keloids, which not only affect the appearance, but also affect the repair of normal tissues, and even become cancerous. Different scars need to be treated in different ways. Effectively distinguishing normal and abnormal scars can help patients to carry out reasonable treatment. Scars ar...

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): G06K9/46G06K9/62
Inventor 陈冠楠刘垚朱小钦陈荣黄祖芳胡恒阳蔡坚勇吴怡林居强冯尚源
Owner FUJIAN NORMAL 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