Work

An Improved Retinex-Based Approach Based on Attention Mechanisms for Low-Light Image Enhancement

Year: 2024

Type: article

Abstract: Captured images often suffer from issues like color distortion, detail loss, and significant noise. Therefore, it is necessary to improve image quality for reliable threat detection. Balancing brightness enhancement with the preservation of natural colors and details is particularly challenging in low-light image enhancement. To address these issues, this paper proposes an unsupervised low-light image enhancement approach using a U-net neural network with Retinex theory and a Convolutional Block Attention Module (CBAM). This method leverages Retinex-based decomposition to separate and enhance the reflectance map, ensuring visibility and contrast without introducing artifacts. A local adaptive enhancement function improves the brightness of the reflection map, while the designed loss function addresses illumination smoothness, brightness enhancement, color restoration, and denoising. Experiments validate the effectiveness of our method, revealing improved image brightness, reduced color deviation, and superior color restoration compared to leading approaches.

Source: Electronics

DOI: 10.3390/electronics13183645

Authors: Shan Jiang, Yingshan Shi, Yingchun Zhang, Yingchun Zhang, Yulin Zhang, Yulin Zhang

Institution: Minzu University of China

Language: English

Topic: Image Enhancement Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,728

Funder: National Natural Science Foundation of China