Deep underwater image enhancement through colour cast removal and optimization algorithm
Blue–green colour cast effect and low contrast are common problems suffered by deep underwater images. This paper introduces a new method which consists of two major steps: red channel correction based on green and blue channels (RCCGB), and simultaneous contrast stretching and mean pixel enhancemen...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Taylor & Francis
2019
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/42579/1/2019%20-%20Deep%20underwater%20image%20enhancement%20through%20colour%20cast%20removal%20and%20optimization%20algorithm.pdf http://umpir.ump.edu.my/id/eprint/42579/7/Deep%20underwater%20image%20enhancement%20through%20colour%20cast%20removal_ABST.pdf http://umpir.ump.edu.my/id/eprint/42579/ https://doi.org/10.1080/13682199.2019.1660484 https://doi.org/10.1080/13682199.2019.1660484 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Blue–green colour cast effect and low contrast are common problems suffered by deep underwater images. This paper introduces a new method which consists of two major steps: red channel correction based on green and blue channels (RCCGB), and simultaneous contrast stretching and mean pixel enhancement (SCSMPE). The RCCGB is designed to minimize the effect of blue–green illumination. This step considers the differences between the red channel and other channels in terms of total pixel values. The second major step, SCSMPE is specifically designed to perform contrast stretching and improve the mean pixel value simultaneously through particle swarm optimization (PSO). Based on the visual observation, the proposed method significantly reduces the effect of the blue–green colour cast and improves the image contrast. Furthermore, the average quantitative values for 300 underwater images also demonstrate the superiority of the proposed method. |
|---|