Method for removing shadow of single image by edge attention based on semi-supervised learning

A semi-supervised learning and supervised learning technology, applied in the field of image lighting editing, can solve the problems of color distortion, obvious shadow boundary, and poor shadow removal effect in complex scenes, so as to enhance the detection ability, reduce the intra-class variance, enhance the The effect of performance

Pending Publication Date: 2021-11-09
WUHAN UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a shadow detection and elimination network based on semi-supervised learning, aiming to solve the problem that the existing shadow elimination method has poor shadow

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 removing shadow of single image by edge attention based on semi-supervised learning
  • Method for removing shadow of single image by edge attention based on semi-supervised learning
  • Method for removing shadow of single image by edge attention based on semi-supervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] An embodiment of an image shadow detection and elimination method based on semi-supervised learning provided by the present invention can better realize shadow removal for shadow areas in complex scene images.

[0025] Such as figure 1 As shown in , it is a schematic diagram of the overall network of image shadow detection and elimination in this embodiment. It randomly inputs an image with a shadow, and obtains the input features of the attention network through down-sampling to the encoder, and then uses the features at different scales to generate a shadow detection map of the input image through the attention module and decoder; The shared encoder is directly decoded by the decoder in the shadow elimination network, and then performs a dot product operation with the shadow mask image output by the shadow detection network, and the final shadow elimination feature is obtained through a deep feature fusion elimination network, and finally compared with the original i...

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 shadow elimination in image processing, and provides a method for removing a shadow of a single image based on semi-supervised edge attention. The method comprises a generator and a discriminator, wherein the generator is divided into a shadow detection network, an edge attention module and a shadow elimination network. Through the training of the semi-supervised learning network, the shadow region of the shadow image of the complex scene can be detected, the shadow image is guided to perform shadow elimination, and a better shadow-eliminated image is obtained.

Description

technical field [0001] The invention relates to a single image shadow removal method based on semi-supervised learning edge attention, especially capable of removing complex shadows in real scenes. The invention belongs to the field of image illumination editing, in particular to a shadow removal method based on semi-supervised learning. 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 sha...

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
IPC IPC(8): G06T5/00G06T5/50G06N3/04G06N3/08
CPCG06T5/005G06T5/50G06N3/08G06T2207/20221G06N3/047G06N3/048G06N3/045
Inventor 肖春霞朱云罗飞
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