{"title":"Underwater image processing: MSRCR algorithm based on the guided filter of sobel operator","authors":"Lu Teng, Feng Xue","doi":"10.1145/3291940.3291959","DOIUrl":null,"url":null,"abstract":"Aiming at solving the problems of \"halo pseudo-color\" and detail blur of underwater image by existing algorithm, a new color restoration of multi-scale Retinex(MSRCR) image enhancement algorithm based on guided filter of sobel operator is proposed. Using the sobel edge detection operator to calculate the gradient magnitude of the image, the fixed regularization parameter of the traditional guided filter is discriminated and it is adaptive in the edge region and the smooth region of image. Then, the Gaussian filter of traditional MSRCR is replaced with the guided filter based on the sobel edge detection operator. Experimental results shows that the proposed algorithm not only highlights the edge details and color fidelity, but also has lower computational complexity and higher efficiency.","PeriodicalId":429405,"journal":{"name":"Proceedings of the 13th International Conference on Underwater Networks & Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 13th International Conference on Underwater Networks & Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3291940.3291959","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Aiming at solving the problems of "halo pseudo-color" and detail blur of underwater image by existing algorithm, a new color restoration of multi-scale Retinex(MSRCR) image enhancement algorithm based on guided filter of sobel operator is proposed. Using the sobel edge detection operator to calculate the gradient magnitude of the image, the fixed regularization parameter of the traditional guided filter is discriminated and it is adaptive in the edge region and the smooth region of image. Then, the Gaussian filter of traditional MSRCR is replaced with the guided filter based on the sobel edge detection operator. Experimental results shows that the proposed algorithm not only highlights the edge details and color fidelity, but also has lower computational complexity and higher efficiency.