Color constancy method based on convolutional auto-encoder

Abstract

The invention discloses a color constancy method based on a convolutional auto-encoder, and the method comprises the steps: firstly obtaining a color-cast-free image, and making an image data set according to the color-cast-free image; training a convolutional auto-encoder through the image data set, and establishing a mapping network from a color cast image to a color cast-free image; and finally, achieving the color constancy of the image through a mapping network. According to the method, a good color constancy effect can be achieved, and the light source color information implied in the original image can be effectively extracted by utilizing the strong coding capability of the convolution auto-encoder, so that image color correction is carried out. According to the method, tests are carried out on a plurality of international universal color constancy databases, and results prove that the method can obtain a very good color constancy effect under the condition of using a small amount of parameters.

Description

technical field [0001] The invention belongs to the technical field of computer vision and image processing, and in particular relates to the design of a color constancy method based on a convolutional autoencoder. Background technique [0002] As a kind of perceptual constancy, color constancy is a very important function in the human visual system. It can help us maintain a stable perception of objects in the scene under changing light sources. Achieving good color constancy in computer systems is an important research direction in the field of computer vision, and has important practical significance for downstream tasks such as image enhancement, denoising, and recognition. The traditional color constancy method is based on some simple physical scene assumptions or machine learning methods, and has the characteristics of simple algorithm, easy implementation, and strong adaptability, but the effect is relatively poor. In recent years, with the rapid development of deep ...

AI Technical Summary

Problems solved by technology

Convolutional autoencoders are widely used in image denoising, signal compression, style transfer and other fields due to their powerful representation learning capabilities. However, in practical applications, as the number of network layers deepens, a large number of convolution and pooling operations The effective information of the image is continuously lost, which leads to the "information bottleneck" problem, so that it is difficult for the decoder to decode and reconstruct the original input, and the ideal image processing effect cannot be obtained.

Images