{"title":"基于灰度边缘颜色常数的计算方法研究","authors":"Xinyu Sun, K. Xie, Sen Lin, Ao Yang, Hongbo Zhao","doi":"10.1109/AEMCSE50948.2020.00090","DOIUrl":null,"url":null,"abstract":"On the basis of gray edge hypothesis, further considering the influence of image edge information and high frequency noise on light color estimation, a color constancy calculation method based on gray edge algorithm is proposed. In this paper, Shi-gehler data set is used, because the color card in the original data set will affect the image correction, so the color card in the data set is set black, making the experimental results more accurate. In order to ensure the suppression of high-frequency noise, the Gaussian filter is replaced by the bilateral filter to estimate the illumination chroma, and the von kries diagonal transformation model is used to correct the color deviation image. The experimental results show that the strategy improves the accuracy of illumination estimation and the effect of color constancy.","PeriodicalId":246841,"journal":{"name":"2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research on Calculation Method Based on Gray Edge Color Constant\",\"authors\":\"Xinyu Sun, K. Xie, Sen Lin, Ao Yang, Hongbo Zhao\",\"doi\":\"10.1109/AEMCSE50948.2020.00090\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"On the basis of gray edge hypothesis, further considering the influence of image edge information and high frequency noise on light color estimation, a color constancy calculation method based on gray edge algorithm is proposed. In this paper, Shi-gehler data set is used, because the color card in the original data set will affect the image correction, so the color card in the data set is set black, making the experimental results more accurate. In order to ensure the suppression of high-frequency noise, the Gaussian filter is replaced by the bilateral filter to estimate the illumination chroma, and the von kries diagonal transformation model is used to correct the color deviation image. The experimental results show that the strategy improves the accuracy of illumination estimation and the effect of color constancy.\",\"PeriodicalId\":246841,\"journal\":{\"name\":\"2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE)\",\"volume\":\"41 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AEMCSE50948.2020.00090\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AEMCSE50948.2020.00090","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Research on Calculation Method Based on Gray Edge Color Constant
On the basis of gray edge hypothesis, further considering the influence of image edge information and high frequency noise on light color estimation, a color constancy calculation method based on gray edge algorithm is proposed. In this paper, Shi-gehler data set is used, because the color card in the original data set will affect the image correction, so the color card in the data set is set black, making the experimental results more accurate. In order to ensure the suppression of high-frequency noise, the Gaussian filter is replaced by the bilateral filter to estimate the illumination chroma, and the von kries diagonal transformation model is used to correct the color deviation image. The experimental results show that the strategy improves the accuracy of illumination estimation and the effect of color constancy.