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

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...

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