Multi-resolution deep network image highlight removing method based on divide-and-conquer

A divide-and-conquer, deep network technology, applied in the field of multi-resolution deep network image de-highlighting, which can solve the problems of weak real-time performance, complex processing flow, and cumbersome de-highlighting steps.

Active Publication Date: 2020-05-19
HANGZHOU DIANZI UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In terms of highlight removal, existing methods have certain problems: (1) multiple multi-angle images are required, which limits its application; (2) the processing flow is complicated, the steps of highlight removal are cumbersome, and the real-time performance is weak

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] specific implementation plan

[0026] The present invention will be described in detail below in conjunction with examples, so that those skilled in the art can better understand the present invention. It should be noted that in the following description, when detailed descriptions of known functions and designs may dilute the main content of the present invention, these descriptions will be omitted here.

[0027] A divide-and-conquer based multi-resolution deep network image de-highlight method, including a training method and a testing method.

[0028] The training method is specifically:

[0029] Step (1). Construct the de-highlight network model. The de-highlight network model includes pyramid structure, nested residual network, and fusion structure;

[0030] The pyramid structure grades and resizes the image blocks through the Laplacian pyramid, and sends them to the nested residual network; the residual sub-network in the nested residual network extracts the fe...

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 multi-resolution deep network image highlight removing method based on divide-and-conquer. The method comprises a training method and a testing method. Firstly, a highlight network removing model is constructed, and the model is composed of a pyramid structure, a nested residual network and a fusion structure. A pyramid structure uses a Laplace pyramid to grade image blocks, highlight is processed on different levels, a convolutional network and a residual network are adopted in a nested residual network to extract features of the image blocks of different levels, anda fusion structure is combined with output of the nested residual network to predict a non-highlight image. And after model training is completed, directly partitioning the test image, predicting a non-highlight image by the model, and finally splicing prediction results to obtain a non-highlight whole image. According to the model structure, the highlight phenomenon in the image can be efficiently removed in real time, and the model structure has high adaptability and high robustness to images with complex colors and textures.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and in particular relates to a divide-and-conquer-based multi-resolution deep network image highlight removal method. Background technique [0002] In image processing, the image quality will directly affect the effect of image processing. However, in practical engineering applications, due to the influence and limitation of imaging conditions by various physical and environmental factors, the image quality is often greatly affected. Among them, the specular phenomenon is one of the main reasons for the sharp decline in image quality. Unlike diffuse reflection, the highlight component represents not the chromaticity information of the object surface, but the chromaticity information of the light source, so the light intensity is much larger than the diffuse reflection component. When highlights appear on the surface of an object, human vision will have a dazzling feeling. At th...

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): G06T5/00G06N3/04G06N3/08
CPCG06T5/005G06N3/084G06T2207/20081G06T2207/20084G06T2207/20016G06N3/045
Inventor 陈华华罗凌杰郭春生应娜叶学义
Owner HANGZHOU DIANZI 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