Deep underwater image enhancement through integration of red color correction based on blue color channel and global contrast stretching

• Main Authors: Kamil Zakwan, Mohd Azmi, Ahmad Shahrizan, Abdul Ghani, Zulkifli, Md. Yusof, Zuwairie, Ibrahim
• Format: Book Section
• Language: English; English
• Published: Springer Singapore 2018
• Subjects: Q Science (General); S Agriculture (General); TC Hydraulic engineering. Ocean engineering; TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://umpir.ump.edu.my/id/eprint/22418/1/26.%20Deep%20underwater%20image%20enhancement%20through%20integration%20of%20red%20color%20correction.pdf; http://umpir.ump.edu.my/id/eprint/22418/2/26.1%20Deep%20underwater%20image%20enhancement%20through%20integration%20of%20red%20color%20correction.pdf; http://umpir.ump.edu.my/id/eprint/22418/; https://link.springer.com/chapter/10.1007/978-981-13-3708-6_4

Deep underwater images experience some complicated problems, such as low contrast and blue-green illumination effect due to light attenuation in water medium. These problems reduce the extraction rate of valuable infor-mation from the image. This paper proposes a new method of enhancing un-derwater image. The proposed method consists of two major steps. The first step is explicitly designed to minimize the effect of blue-green illumination. This technique operates by correcting the red color channel by taking into ac-count the differences between the red color with blue color in term of total pixel value. The more significant the difference of total pixel value between these colors, the higher the pixel value will be added to improve the red color and vice versa. Then, the overall image contrast is improved through global contrast stretching technique that is applied to all color channels. Qualitative and quanti-tative evaluations prove the effectiveness of the proposed method.