Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A feature selection method for breast x-ray images based on bfba and elm

An image feature and X-ray technology, applied in the field of image processing, can solve the problems of the analytical method or the bat algorithm easily falling into the local optimal solution, "exponential explosion", etc., and achieve the effect of improving the classification performance, accuracy and classification accuracy.

Active Publication Date: 2020-09-04
TAIYUAN UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention overcomes the deficiencies in the prior art, and the technical problem to be solved is to provide a feature selection method for mammary gland X-ray images, which avoids the "exponential explosion" problem encountered by the dynamic programming method, and the analytical method or bat algorithm is easy to fall into local optimal solution problem

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
  • A feature selection method for breast x-ray images based on bfba and elm
  • A feature selection method for breast x-ray images based on bfba and elm
  • A feature selection method for breast x-ray images based on bfba and elm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Such as figure 1 , figure 2 Shown, a kind of breast X-ray image feature selection method based on BFBA and ELM of the present invention, concrete steps are as follows: the first step, collect used data set MIAS, i.e. the Mammographic Image Analysis Society, extract the mammographic image feature, and The data set is divided into a training set and a test set. The training set is used to train the extreme learning machine ELM, namely Extreme Learning Machine, to design the ELM classifier, and the test set is used to test the effectiveness of the ELM classifier;

[0051] The method adopted for extracting mammogram image features is a gray-scale co-occurrence matrix, extracting four kinds of statistical parameters: angular second-order moment, entropy, moment of inertia, correlation coefficient, and the direction of the gray-scale co-occurrence matrix is ​​0°, 45°, 90° °, 135° in four directions; first calculate the gray level co-occurrence matrix in the four directions,...

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 is a mammary X-ray image feature selection method based on BFBA and ELM, which relates to the technical field of image processing. The problem of falling into a local optimal solution; the technical solution adopted is as follows: the first step is to collect the data set MIAS used; the second step is to set the BFBA parameters; the third step is to initialize the bat population; the fourth step is to The position encoding of bats generates corresponding feature subsets; the fifth step is to update the search pulse frequency, speed and position of each bat; the sixth and seventh steps are to generate uniformly distributed random numbers rand; the eighth step is to adapt to all bats Degree values ​​are sorted to find the current optimal solution and the optimal value; Step 9, determine whether the optimal solution has changed; Step 10, determine whether stagnant_count is equal to stagnant_max; Step 11, repeat Step 4 to The tenth step; the twelfth step, output the global optimal value and optimal solution.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a mammogram X-ray image feature selection method based on Bird Flock Bat Algorithm (BFBA) and Extreme Learning Machine (Extreme Learning Machine, ELM). Background technique [0002] Breast disease is one of the common diseases in women. At the same time, the multiple and harmful effects of breast cancer seriously affect women's health and even life. Therefore, early diagnosis of breast disease is directly related to women's personal health. Especially for breast cancer, people still can't fully determine its pathogenesis. The current clinical diagnosis methods of breast cancer mainly include touch diagnosis, histological diagnosis, cytological diagnosis and imaging diagnosis. Imaging is widely used for its convenience, scientificity and relatively high operability in diagnosis. Mammography is the most common technique for early diagnosis of breast cancer. For t...

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 Patents(China)
IPC IPC(8): G06K9/62G06K9/46G06N3/00G06N20/00
CPCG06N3/006G06N20/00G06V10/462G06F18/24G06F18/214
Inventor 韩晓红相洁
Owner TAIYUAN UNIV OF TECH
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
Eureka Blog
Learn More
PatSnap group products