Retina image parallel processing method and device

A processing method and retinal technology, applied in the field of image processing, can solve the problems of unguaranteed model generalization performance and poor retinal image processing effect, etc.

Pending Publication Date: 2020-11-13
HENAN UNIVERSITY OF TECHNOLOGY +1
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problem that the existing intelligent retinal image processing effect is not good and the generalization performance of the model cannot be guaranteed, the present invention proposes a retinal image parallel processing method and device

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
  • Retina image parallel processing method and device
  • Retina image parallel processing method and device
  • Retina image parallel processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] The present invention will be further explained below in conjunction with accompanying drawing and specific embodiment:

[0076] The present invention first adopts the chaotic supply and demand algorithm to optimize the objective function (determined according to the specific requirements of image enhancement) to determine the undetermined parameters of the transformation function so as to enhance the collected retinal images; then perform traditional transformation on the enhanced retinal images according to an appropriate order (rotate, flip, increase contrast, translate, etc.), and then use the generated confrontation network and its variants to synthesize the image through confrontation training with the previous retinal image as the real image, and then use the above image as the real image input to generate the multi-layered model and virtual-real interaction Decompose the joint training model composed of interval-type two intuitionistic fuzzy convolutional neural ...

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 technical field of image processing, and particularly relates to a retina image parallel processing method, which comprises the steps of 1, optimizing a target function byadopting a chaotic supply and demand algorithm, and enhancing a real retina image; 2, synthesizing a virtual retina image based on a mixed image generation method; 3, constructing a parallel multilayer decomposition interval type-2 intuitionistic fuzzy convolutional neural network model based on the virtual retina image and the enhanced real retina image; 4, integrating the outputs of the multiple parallel multilayer decomposition interval type-2 intuitionistic fuzzy convolutional neural network models to serve as a final classification result. The invention further discloses a retina image parallel processing device which comprises an image enhancement module, a virtual retina image generation module, a model construction module and an integration module. According to the method, the problem that the number and quality of retinal image training data samples cannot be guaranteed is solved, and the accuracy of retinal image feature extraction and classification recognition is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a retinal image parallel processing method and device. Background technique [0002] At present, most of the processing of relevant objects in retinal images is manually designed. This method has great limitations both in accuracy and in objectivity. Thanks to the rapid development of computer software and hardware technology and the maturity of computer vision technology, researchers are trying to find an efficient and intelligent way that can automatically process the relevant features of retinal images without subjective interference, so as to provide a basis for the corresponding application fields. , such as biometric identification technology to provide more reliable and effective technical protection. Lin Jipeng (Lin Jipeng, Research on Key Technologies of Fundus Retina Image Processing and Analysis [D], Huaqiao University, 2019.) uses the wavelet do...

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): G06K9/62G06N3/00G06N3/04G06N3/08
CPCG06N3/08G06N3/006G06N3/043G06N3/045G06F18/24G06F18/214G06T11/00G06V20/20G06V40/18G06V10/82G06N3/047G06N3/088G06T3/60G06T5/50G06T2207/20084G06T2207/30041
Inventor 赵亮周川冯晓霞李晶晶刘园园司冉冉谢志峰付园坤金军委张坤鹏张磊石世猛王天赐刘东江李萌石志远
Owner HENAN UNIVERSITY OF TECHNOLOGY
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