Journal
SENSORS
Volume 22, Issue 10, Pages -Publisher
MDPI
DOI: 10.3390/s22103667
Keywords
low-light; Image enhancement; attentive neural processes; super-pixel segmentation
Funding
- Natural Science Foundation of China [61501069]
- special project of technological innovation and application development of Chongqing [cstc2019jscx-msxmX0167]
- Science and Technology Project Fund of Sichuan Province [2019ZYZF0094]
Ask authors/readers for more resources
This study proposes a method for processing low-light images using shallow Convolutional Neural Networks and Attentive Neural Processes networks, which demonstrates excellent image enhancement effects and detailed feature restoration capabilities in experimental results.
Dealing with low-light images is a challenging problem in the image processing field. A mature low-light enhancement technology will not only be conductive to human visual perception but also lay a solid foundation for the subsequent high-level tasks, such as target detection and image classification. In order to balance the visual effect of the image and the contribution of the subsequent task, this paper proposes utilizing shallow Convolutional Neural Networks (CNNs) as the priori image processing to restore the necessary image feature information, which is followed by super-pixel image segmentation to obtain image regions with similar colors and brightness and, finally, the Attentive Neural Processes (ANPs) network to find its local enhancement function on each super-pixel to further restore features and details. Through extensive experiments on the synthesized low-light image and the real low-light image, the experimental results of our algorithm reach 23.402, 0.920, and 2.2490 for Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), and Natural Image Quality Evaluator (NIQE), respectively. As demonstrated by the experiments on image Scale-Invariant Feature Transform (SIFT) feature detection and subsequent target detection, the results of our approach achieve excellent results in visual effect and image features.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available