.png){kind=icon}
返回
Underwater Image Enhancement Method via Multi-Interval Subhistogram Perspective Equalization
.png){kind=icon}
PRE
AI
DOI：10.1109/JOE.2022.3223733.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Due to the selective attenuation of light in water, captured underwater images exhibit poor visibility and cause considerable challenges for vision tasks. The structural and statistical properties of different regions of degraded underwater images are damaged at different levels, resulting in a global nonuniform drift of the feature representation, causing further degradation of visual performance. To handle these issues, we present an underwater image enhancement method via multi-interval subhistogram perspective equalization to address the issues posed by underwater images. We estimate the degree of feature drifts in each area of an image by extracting the statistical characteristics of the image, using this information to guide feature enhancement to achieve adaptive feature enhancement, thereby improving the visual effect of degraded images. We first design a variational model that uses the difference between data items and regular items to improve the color correction performance of the method based on subinterval linear transformation. In addition, a multithreshold selection method, which adaptively selects a threshold array for interval division, is developed. Ultimately, a multi-interval subhistogram equalization method, which performs histogram equalization in each subhistogram to improve the image contrast, is presented. Experiments on underwater images with various scenarios demonstrate that our method significantly outperforms many state-of-the-art methods qualitatively and quantitatively.
Keyword:
Histograms
Image color analysis
Image restoration
Image enhancement
Data models
Optical imaging
Degradation
Multiple intervals
multiscale fusion (MF)
subhistogram equalization (SHE)
underwater image
期刊
IF:
5.3
论文数:
2.6K
被引数:
7.4K
机构
引用论文
分享收藏分享收藏Underwater Image Enhancement Using a Multiscale Dense Generative Adversarial Network使用多尺度密集生成对抗网络的水下图像增强
PREAI
分享收藏A risk stratifying tool to facilitate safe late-stage percutaneous endoscopic gastrostomy in ALS
OAAI
OAAI分享收藏Three Adaptive Sub-Histograms Equalization Algorithm for Maritime Image Enhancement三种自适应子直方图均衡的海事图像增强算法.png)
IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏分享收藏
查看更多内容