Method for segmenting high-resolution combined view dermoscopy images on basis of global cavity convolution

A high-resolution, high-resolution technology, applied in the field of image processing, can solve the problem of reducing image resolution and achieve the effect of improving segmentation results and data enhancement

Inactive Publication Date: 2018-03-06
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF8 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the downsampling layer retained in DeepLab, the convolutional layer with a stride of 2, eventually leads to eight times downsampling, reducing the resolution of the image

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
  • Method for segmenting high-resolution combined view dermoscopy images on basis of global cavity convolution
  • Method for segmenting high-resolution combined view dermoscopy images on basis of global cavity convolution
  • Method for segmenting high-resolution combined view dermoscopy images on basis of global cavity convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0038] The invention discloses a high-resolution compound field of view dermoscopic image segmentation method based on global atrous convolution. The specific implementation steps include:

[0039] (1) Construct a high-resolution composite field of view feature extraction network based on ResNet50 and dilated convolution.

[0040] (2) Construct a compound view semantic segmentation network based on dilated convolution.

[0041] (3) Use the deep neural network constructed in (1)(2) for compound loss function training.

[0042] (4) Use the deep neural network trained in (3) to make predictions, and perform prediction enhancement and post-processing.

[0043] The high-resolution compound field of view feature extraction network in the step (1) specifically includes:

[0044] (11) The first convolutional layer of ResNet50, the step size is adjusted from 2 to 1 to ensu...

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 belongs to the field of image processing, computer vision, deep learning and semantic image segmentation, and particularly discloses a method for segmenting high-resolution combined viewdermoscopy images on the basis of global cavity convolution. The method includes constructing high-resolution combined view feature extraction networks and semantic segmentation networks on the basisof cavity convolution; carrying out training by the aid of cross entropy and jaccard approximation coefficient combined loss functions; carrying out data enhancement and post-processing during prediction. The method has the advantages that sufficiently comprehensive context information can be sieved by combined view by the aid of the global cavity convolution, high-resolution images can be retained, accordingly, sufficiently detailed information can be captured, and the dermoscopy images can be accurately segmented.

Description

technical field [0001] The invention belongs to the fields of image processing, computer vision, deep learning, and image semantic segmentation, and specifically relates to a high-resolution compound field of view dermoscopic image segmentation method based on global atrous convolution. Background technique [0002] In recent years, deep learning has played an increasingly important role in the field of image processing. In the field of image semantic segmentation, in 2014, Jonathan Long proposed a classic framework for image semantic segmentation based on FCN (Fully Convolutional Network), based on the VGG network, using deconvolution and skip layer connections to achieve pixel-by-pixel classification Image Semantic Segmentation Method. In 2016, the DeepLab network proposed by Liang-Chieh Chen used hole convolution for image semantic segmentation, and avoided a sharp drop in resolution on the basis of ensuring the field of view of the convolution kernel. [0003] With the...

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): G06T7/10
CPCG06T7/10G06T2207/20081G06T2207/20084G06T2207/30088
Inventor 漆进张通胡顺达
Owner UNIV OF ELECTRONICS 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