{"title":"基于改进亮度的自适应MSR","authors":"Bo Sun, Weifang Chen, Hongyu Li, W. Tao, Jiang Li","doi":"10.1109/ICIG.2007.137","DOIUrl":null,"url":null,"abstract":"A modified luminance based adaptive MSR is proposed in this paper. This new method addresses the problems existing in standard Retinex algorithms, such as halo artifacts and incorrect colors. The paper chooses an adaptive Gaussian function whose shape follows edges of image, thus reducing the artifacts along high contrast edges. In addition, only the luminance channel instead of all color bands is processed, which can produce a more consistent and reliable color rendition.","PeriodicalId":367106,"journal":{"name":"Fourth International Conference on Image and Graphics (ICIG 2007)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"18","resultStr":"{\"title\":\"Modified Luminance Based Adaptive MSR\",\"authors\":\"Bo Sun, Weifang Chen, Hongyu Li, W. Tao, Jiang Li\",\"doi\":\"10.1109/ICIG.2007.137\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A modified luminance based adaptive MSR is proposed in this paper. This new method addresses the problems existing in standard Retinex algorithms, such as halo artifacts and incorrect colors. The paper chooses an adaptive Gaussian function whose shape follows edges of image, thus reducing the artifacts along high contrast edges. In addition, only the luminance channel instead of all color bands is processed, which can produce a more consistent and reliable color rendition.\",\"PeriodicalId\":367106,\"journal\":{\"name\":\"Fourth International Conference on Image and Graphics (ICIG 2007)\",\"volume\":\"10 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-08-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"18\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fourth International Conference on Image and Graphics (ICIG 2007)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICIG.2007.137\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fourth International Conference on Image and Graphics (ICIG 2007)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIG.2007.137","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A modified luminance based adaptive MSR is proposed in this paper. This new method addresses the problems existing in standard Retinex algorithms, such as halo artifacts and incorrect colors. The paper chooses an adaptive Gaussian function whose shape follows edges of image, thus reducing the artifacts along high contrast edges. In addition, only the luminance channel instead of all color bands is processed, which can produce a more consistent and reliable color rendition.