Visibility Dehazing based on Channel-Weighted Analysis and Illumination Enhancement

• Main Authors: LI, CHIH-HSUAN, 李治軒
• Other Authors: Lee, Jung-San
• Format: Others
• Language: en_US
• Published: 2017
• Online Access: http://ndltd.ncl.edu.tw/handle/36250754204916969607

碩士 === 逢甲大學 === 資訊工程學系 === 105 === The air pollution and foggy weather often result in serious distortion while taking photos or recognizing patterns. He et al. have introduced the dark channel prior to solve this dehazing problem. Unfortunately, it cannot function well once the color difference of target image is large. More precisely, the dehazed result looks unnatural. Thus, we aim to develop a brand-new visibility dehazing technique based on the channel-weighted analysis and illumination tuning. The channel-weighted analysis is adopted to eliminate the unnatural effect, while the illumination tuning is applied to refine the details. Simulation results have demonstrated that the new method can guarantee the readability of a hazed image after removing noise, including the foggy photo and sandstorm one.