Naive Bayes classifier-based dermatosis image color feature extraction method

A Bayesian classifier and color feature technology, applied in the field of skin disease image processing, can solve problems such as reducing the dimension of data processing, and achieve the effect of high classification accuracy, fast speed and high accuracy

Inactive Publication Date: 2017-04-05
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF1 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0026] In view of the above prior art, the purpose of the present invention is to provide and solve the technical pr

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
  • Naive Bayes classifier-based dermatosis image color feature extraction method
  • Naive Bayes classifier-based dermatosis image color feature extraction method
  • Naive Bayes classifier-based dermatosis image color feature extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Computer-aided diagnosis of skin diseases needs to extract the color features of skin disease images, that is, to classify and count the colors of the pixels of skin disease images. This solution builds a color histogram based on a naive Bayesian classifier.

[0056] Bayesian classifiers are based on statistical methods. Suppose, X is an eigenvector, ω iis a category set (i is the index number of the category), then in ω i The probability of X appearing in the set is: Among them, p(ω i |X) is the posterior probability, p(ω i ) is the prior probability of sample data, probability p(X)=∑ i p(X|ω i )p(ω i ), p(X|ω i ) is the conditional probability of the feature attribute.

[0057] If X is classified, it is first necessary to calculate p(ω i |X), and then find all p(ω i |X), X can be classified into ω i kind. Assuming that the same amount of training data is provided for each class, there is a property of the prior probability: for all i and j, there is p(ω ...

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 present invention discloses a naive Bayes classifier-based dermatosis image color feature extraction method which relates to the dermatosis image processing technology field and solves the technical problems in the prior art that the data processing dimension can not be reduced on the condition of guaranteeing the classification precision, etc. The method of the present invention mainly comprises the steps of converting an RGB color model of a dermatosis image into an HSI color model; in the HSI model, scanning each pixel point of the dermatosis image to obtain an HSI color model value (h, s, i) and an HSI color feature vector of each pixel point; according to skin colors of different kinds of diseases in the dermatosis clinical diagnosis, adopting a naive Bayes classifier to respectively classify the HSI color feature vectors corresponding to the pixel points into the skin colors of different kinds of diseases; gathering the number of the pixel points of the skin color of each kind of disease to obtain the features of the dermatosis image.

Description

technical field [0001] The invention relates to the technical field of skin disease image processing, in particular to a method for extracting color features of skin disease images based on a naive Bayesian classifier. Background technique [0002] Due to the deteriorating environment, the incidence and types of skin diseases are increasing, and the challenges are becoming increasingly severe. At present, the diagnosis of skin diseases mostly adopts the traditional clinical diagnosis method, which greatly depends on the clinical experience of doctors. If supplemented with advanced information processing methods such as computer vision and digital image processing, the construction of a skin disease image content understanding and computer-aided diagnosis system will have far-reaching theoretical research and application value for the early prediction and scientific treatment of skin diseases. [0003] Doctors' clinical diagnosis of skin diseases is mainly based on morpholog...

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
CPCG06V10/56G06V2201/03G06F18/24155
Inventor 蒲晓蓉王之骢宋帅领
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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