Lung cancer image fine classification method based on fusion of LBP and wavelet moment features

A technology of fine classification and fusion of features, which is applied in character and pattern recognition, instruments, computing, etc., can solve the problems of lack of research on image fine classification in the medical field, and achieve the effects of improving classification accuracy, comprehensively representing images, and good recognition effects

Inactive Publication Date: 2016-06-29
JILIN UNIV
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that the existing image fine classification is scarce in the medical field, and the traditional image classification method cannot be effectively applied to the image fine classification

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
  • Lung cancer image fine classification method based on fusion of LBP and wavelet moment features
  • Lung cancer image fine classification method based on fusion of LBP and wavelet moment features
  • Lung cancer image fine classification method based on fusion of LBP and wavelet moment features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Step 1: Use the lesion area detection method based on the gray level change to locate the lesion on the original input image.

[0032] In the template matching framework proposed before, the first step adopts the method of randomly generating a large number of templates. Before generating the templates, no preprocessing is performed, resulting in a large number of redundant template blocks containing useless information. In the subsequent scaling and matching process, the extracted features If the dimension is too large, the classification accuracy will decrease. Based on this, before generating the template block, we use the lesion area detection method based on the gray level change to locate the lesion first. figure 2 Because the image texture reflects a local structural feature of the image, which is specifically manifested as a certain change in the gray level or color of pixels in a certain neighborhood of the image, it can be used to quantitatively describe the ...

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 lung cancer image fine classification method based on fusion of LBP and wavelet moment features. The lung cancer image fine classification method is characterized in that S1, nidus positioning of an input image can be carried out; S2, a plurality of templates of the nidus part can be generated randomly; S3, the scaling of the input image in different dimensions can be carried out, and the extraction of the textural feature MB-LBP and shape feature wavelet moment of the image block and the template block can be respectively carried out, and then the two features can be integrated by adjusting the weighting parameters by the experiment; S4, the feature response image can be acquired by matching the different positions of the image; S5, the response image can be converted into the feature vector by adopting the improved mean space pyramid model; S6, the fine classification can be realized by adopting the vector machine. The algorithm provided by the invention is the attempt of the fine classification idea in the medical science field, and the generating of the redundant templates can be reduced. The lung cancer image information can be represented by the well fusion of the LBP textural features and the wavelet moment features. By adopting the pyramid model extraction model, the strong features can be maintained, and the identification precision can be improved.

Description

technical field [0001] The invention relates to image feature extraction and image classification Background technique [0002] In recent years, lung cancer has become a major disease that endangers human life and health. In the diagnosis and treatment of lung cancer, medical image analysis is one of the main means of auxiliary diagnosis of lung cancer. At present, image classification for lung cancer has achieved certain results. However, clinical practice has shown that if lung cancer can be further divided into different types such as small cell lung cancer, squamous lung cancer, adenocarcinoma, and bronchioloalveolar carcinoma based on medical imaging data, it will have more practical significance for subsequent treatment. However, the existing common image classification technology cannot automatically realize this fine classification. Research on fine image classification of medical images for lung cancer has not been reported yet. Therefore, the present invention ...

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): G06K9/62
CPCG06V2201/031G06V2201/032G06F18/241G06F18/253
Inventor 王生生王琪
Owner JILIN 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