An underwater image enhancement and restoration method based on convolutional neural network

Abstract

An underwater image enhancement and restoration method based on a convolutional neural network, comprising: degrading a plurality of conventional images by using the underwater image to be processed, and then forming a training set with the plurality of conventional images and their corresponding degraded conventional images, and Input into the convolutional neural network for training in turn; after that, input the aforementioned underwater image to be processed into the trained convolutional neural network to output the first image; perform CIELAB color space transformation on the image, and extract the L of the image. Brightness channel, A color channel, and B color channel; finally, texture enhancement is performed on the aforementioned underwater image to be processed, and the texture-enhanced image is replaced by the L brightness channel of the first image, and is combined with the A color channel in the first image. Combined with the B color channel to get the final image. This method solves the problem of missing underwater image training data, and avoids the complex calculation of traditional underwater imaging models, which better improves the quality of underwater images.

Description

technical field [0001] The invention relates to the field of underwater image enhancement and restoration, in particular to an underwater image enhancement and restoration method based on a convolutional neural network. Background technique [0002] Obtaining underwater images is of great significance to the exploration and development of underwater environments. In the process of capturing underwater images, due to the rapid attenuation of red light during propagation and the scattering of light by particles in the water, the captured underwater images usually have low contrast, unbalanced brightness, unclear texture and chromatic aberration. serious shortcomings. Therefore, people usually perform enhancement and restoration processing on underwater images to ensure the smooth development of underwater environmental operations. [0003] In recent years, underwater image processing technology has received more and more attention from scholars, and a variety of underwater i...

AI Technical Summary

Problems solved by technology

These methods have a certain effect on the color correction of underwater images and the improvement of texture clarity, but there are still subjective unnatural color differences and texture distortions.

Ancuti et al. proposed to fuse the parameters of the underwater images processed by the three methods of color improvement, gamma correction and texture enhancement, but this kind of algorithm is complex and the image is prone to artifacts caused by over-enhancement

In addition, traditional methods require a large amount of environmental data such as water scattering coefficients, scene depth, etc., which are difficult to obtain from a single image

Images