An Essential Image Analysis Method Based on Multi-Scale Attention and Label Loss

Abstract

The present invention proposes an essential image analysis method based on multi-scale attention and label loss, introduces the circular convolution attention mechanism and confrontation idea into the essential decomposition problem, and constructs a multi-scale attention MSA for essential image analysis Net network, the network structure follows the basic framework of the Generative Adversarial Network (GAN), including two parts, the generator and the discriminator. The generator consists of two parts: attention subnetwork and codec subnetwork, which are used to decompose the image into reflection map and light map. The role of the discriminator is to give the probability that the image is the correct essential image for any input image. At the same time, the present invention also provides a new label loss function for improving the reflection map decomposition effect. The loss function is constructed based on the label image (ground truth) in the data set, which can make the reflection map obtained by network decomposition have better local Texture consistency effects and quantitative evaluation metrics.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to an essential image analysis method. Background technique [0002] Image understanding and analysis is one of the important basic research in the field of computer vision. In complex natural scenes, the same target may have differences in image surface color, grayscale mutations, etc. due to many factors such as light intensity, shadow occlusion, and attitude changes, resulting in huge differences in the observation effect of the same object in the same scene. If the image is directly processed, it will greatly increase the difficulty of image analysis and understanding, which will affect the performance of the algorithm. To solve this problem, the best way to deal with it is to dig out the inherent mode of the target object in the image—essential features, and then send the essential features of the object to the subsequent algorithm for processing. Essential feature...

AI Technical Summary

Problems solved by technology

However, since the features in the reflection map and the light map do not satisfy the completely mutually exclusive characteristics, the network often cannot achieve the ideal separation effect, and the separation of the reflection map and the light map is not complete, so a more ingenious network structure and loss are required. Function design to further improve the quality of essential image analysis

Images