Open AccessA low illumination image enhancement algorithm based on adaptive fractional differentiation
Author(s) -
Liangyan Wang,
Xingqun Zhan,
Chunling Wang,
Zihong Chen,
Yunfei Xia
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1634/1/012126
Subject(s) - image (mathematics) , image enhancement , differential (mechanical device) , pixel , algorithm , mathematics , interference (communication) , computer science , computer vision , noise (video) , edge enhancement , enhanced data rates for gsm evolution , artificial intelligence , physics , telecommunications , channel (broadcasting) , thermodynamics
Using fixed order fractional differential for image enhancement, some regions of the image may not achieve the desired enhancement effect. According to the characteristics of human vision and low illumination image, an adaptive order fractional differential enhancement algorithm is proposed. Three different differential orders are selected for enhancement, and one of them is adaptively selected for each pixel according to the comparison results of gradient values. The experimental results show that the adaptive order can not only enhance the image with high gradient value such as the edge, but also reduce the noise interference in the flat area, which has better visual effect than fixed order enhancement.