颜色恒定性
人工智能
计算机视觉
色彩平衡
对比度(视觉)
直方图均衡化
遮罩(插图)
伽马校正
颜色直方图
颜色校正
计算机科学
颜色归一化
轻巧
能见度
水下
彩色图像
滤波器(信号处理)
数学
直方图
图像(数学)
图像处理
光学
物理
艺术
视觉艺术
海洋学
地质学
作者
Manigandan Muniraj,D. Vaithiyanathan
标识
DOI:10.1016/j.compeleceng.2022.107909
摘要
In underwater, light attenuation causes non-uniform illumination that degrades underwater image. To enhance the degraded image, we propose an underwater image enhancement method that includes color correction, color constancy, multi-scale retinex (MSR), edge-aware and texture smoothing filters, and contrast stretching. The formulated color correction compensates the red and blue channels by masking. Color constancy transforms non-uniform illumination into uniform illumination. Furthermore, the gamma correction in the color constancy improves the contrast of the image. The distorted colors are restored using the MSR with contrast limited adaptive histogram equalization (CLAHE). The edges are preserved using a fast local laplacian filter (FLLF), while the detailed texture of the image is smoothed using a rolling guidance filter (RGF) The contrast stretching enhances the image by stretching the pixel values. The qualitative and quantitative evaluation of the proposed algorithm outperforms the existing methods in terms of naturalness, contrast, visibility and enhancement of low-light images.
科研通智能强力驱动
Strongly Powered by AbleSci AI