Two-stage image context recognition network and single image shadow removal method

A technology for shadow removal and network recognition, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of color distortion of processing results, difficulty in meeting practical application requirements, and weak generalization ability.

Active Publication Date: 2021-09-10
WUHAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the deficiencies of the prior art, the present invention provides a single-image shadow removal method based on a two-stage image context recognition network, which aims to solve the problem of poor generalization ability of existing shadow removal methods, color distortion in processing results, and difficult Problems that meet the needs of practical applications

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
  • Two-stage image context recognition network and single image shadow removal method
  • Two-stage image context recognition network and single image shadow removal method
  • Two-stage image context recognition network and single image shadow removal method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to further understand the content of the present invention and make the purpose, technical solution and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the present invention is only explained here rather than limited.

[0054] The Context-Aware Network (CANet) based on the two-stage image context recognition network designed by the present invention includes two stages: a shadow removal network based on context feature transfer and a result refinement network, wherein the shadow removal network includes a feature extractor, a "double-head "Context information matching module, context feature migration module and upsampling shadow removal result generation module; the result refinement network is used to further refine the results output by the shadow removal network.

[0055] Among them, the feature extractor is use...

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 relates to the field of image illumination editing, and provides a two-stage image context recognition network and a single image shadow removal method. The method explicitly captures an implicitly existing shadow and non-shadow image pair relationship in a shadow image, and performs context information feature migration of the image according to the matching pair relationship so as to migrate useful information of a non-shadow area to the non-shadow area, thereby effectively eliminating the shadow in the image. According to the invention, the problems of inaccurate shadow removal results, color distortion of processing results and poor generalization ability in the prior art are solved, and high-quality shadow removal of a single image is realized at the same time.

Description

technical field [0001] The invention belongs to the field of image lighting editing, and specifically relates to a two-stage image context recognition network and a single image shadow removal method, which can capture and effectively eliminate shadows in an image by using paired context matching information in the image. Background technique [0002] At present, the commonly used shadow removal methods can be mainly divided into the following two categories: 1. Methods based on traditional physics, such as the shadow removal method proposed in the paper "Single-image shadow detection and removal using paired regions", through physical models. Analyzes the light intensity of an image group by pixel. This method can achieve a good shadow removal effect under certain assumptions, but because it is very dependent on the acquisition of prior knowledge and a series of related assumptions, the generalization ability of this method is poor, and it cannot handle shadows beyond the a...

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): G06T5/00G06K9/62G06N3/04G06N3/08
CPCG06T5/006G06N3/08G06T2207/20081G06T2207/20084G06N3/045G06F18/22G06F18/2415
Inventor 肖春霞陈子沛罗飞
Owner WUHAN 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