Method for image fusion based on representation learning

Abstract

The invention discloses a method for image fusion based on representation learning, which comprises the steps of acquiring a multi-source image, learning features of the multi-source image through a learning framework of a deep neural network formed by a sparse adaptive encoder, a deep confidence network formed by a Boltzmann machine and a deep convolutional neural network, completing fusion of the multi-source image by using the automatically learned features, and establishing an image fusion model; studying a convex optimization problem of the image fusion model, and carrying out initialization on the networks by using unsupervised pre-training in deep learning, thereby enabling the networks to find an optimal solution quickly in the training process; and establishing a deep learning network for cooperative training according to the features of the multi-source image through two or more deep learning networks, thereby realizing an image fusion technology of representation learning. The method disclosed by the invention studies feature-level fusion of the image by using artificial intelligence and a deep learning based feature representation method. Compared with a traditional pixel-level fusion method, the method disclosed by the invention can better understand image information, and thus further improves the quality of image fusion.

Description

technical field [0001] The invention relates to the technical field of image fusion, in particular to an image fusion method based on representation learning. Background technique [0002] Due to the advancement of society and technology, the imaging detection band has developed from a single visible light-near infrared to multiple bands such as extreme ultraviolet / middle-far infrared / terahertz, forming various modern imaging detection and image acquisition technologies with rich bands. These technologies enable people to easily obtain a variety of image information. In various industries, people use various sensors to obtain a large amount of image information with various representations from various angles, that is, multi-modal image information. On the one hand, image information is acquired by different sensors, and the image information acquired by different sensors of the same object has different representations. On the other hand, even for image information of the...

AI Technical Summary

Problems solved by technology

[0004] So far, the research on the image fusion model and its mathematical theory is extremely incomplete, and there are many problems that need to be solved urgently. For example, is it possible to establish a unified mathematical theoretical framework for a common problem of actual image fusion? How to use image fusion technology to reconstruct real-time and accurate image information is also a major issue

Images