No-reference low-illumination image enhancement method based on deep convolutional neural network

Abstract

The invention relates to a no-reference low-illumination image enhancement method based on a deep convolutional neural network, and belongs to the field of image processing. The method comprises the following steps: firstly, constructing a feature extraction module comprising two branches by using a deep convolutional neural network, and extracting an irradiation component and a reflection component from an input low-illumination image; and then, denoising the reflection component, and integrating the denoised reflection component into an optimization network to obtain an optimized reflection component; then, inputting the irradiation component into the optimization network to obtain an optimized irradiation component; and finally, multiplying the optimized irradiation component by the reflection component to obtain a final enhancement result. According to the method, the reflection component extracted from the input image is fully utilized, the interference of noise in the image is effectively reduced, and the detail expression capability is improved.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to a no-reference low-illuminance image enhancement method based on a deep convolutional neural network. Background technique [0002] Low-light environments generally refer to poor lighting conditions, such as cloudy, nighttime, and indoor scenes. In addition, imaging noise is inevitably introduced during the imaging process of the camera. These noises will be further exacerbated by low-illumination conditions, so it is very necessary to properly enhance and denoise low-illumination images. [0003] At present, low-light image enhancement methods can be mainly divided into traditional methods and deep learning methods. The representative ones in the traditional methods are the method based on histogram equalization and the method based on Retinex theory. Stretching of dynamic range. The method based on the Retinex theory mainly starts from the Retinex theory, and extracts the illu...

AI Technical Summary

Problems solved by technology

Another big problem facing low-light image enhancement is how to avoid the noise in the original image from being amplified synchronously due to enhancement.

In this regard, there are methods to use image denoising technology as an enhanced pre-processing or post-processing process, which may lead to the loss of detailed information in the image

Another way of thinking is to integrate denoising into the process of image enhancement, but this brings new difficulties to the design of the network and loss function

Images