当前位置: X-MOL 学术Imaging Sci. J. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep underwater image enhancement through colour cast removal and optimization algorithm
The Imaging Science Journal ( IF 1.1 ) Pub Date : 2019-08-18 , DOI: 10.1080/13682199.2019.1660484
Kamil Zakwan Mohd Azmi 1 , Ahmad Shahrizan Abdul Ghani 1 , Zulkifli Md Yusof 1 , Zuwairie Ibrahim 1
Affiliation  

ABSTRACT 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.

中文翻译:

通过色偏去除和优化算法增强水下深度图像

摘要 蓝绿色偏色效应和低对比度是深水水下图像普遍存在的问题。本文介绍了一种新方法,它包括两个主要步骤:基于绿色和蓝色通道的红色通道校正(RCCGB)和同时对比度拉伸和平均像素增强(SCSMPE)。RCCGB 旨在最大限度地减少蓝绿色照明的影响。这一步考虑了红色通道和其他通道在总像素值方面的差异。第二个主要步骤,SCSMPE 专门设计用于通过粒子群优化 (PSO) 同时执行对比度拉伸和提高平均像素值。基于目视观察,所提出的方法显着降低了蓝绿色色偏的影响,提高了图像对比度。此外,
更新日期:2019-08-18
down
wechat
bug