{"title":"使用图形关系和统计的面部标记检测和去除","authors":"M. Hosseini, M. Jamzad","doi":"10.1109/IRANIANCEE.2017.7985432","DOIUrl":null,"url":null,"abstract":"Face Analysis is an important task in image processing. Most of these tasks centralized on face recognition and detection. One of different ways for deceiving automatic face analysis systems is mark notation on the skin. On the other hand some applications attempts to eliminate defects of the face. Hence, in this paper we try to detect and remove skin marks on the face, whether they're natural or not. Our algorithm passes face image through appropriate filters to get mark candidates and then create a graph space using 8-point neighborhood relations of mark candidates image pixels. Then we compute probabilities of each mark candidate using four measures based on intensity of occurrence, shape density, uniqueness in local area and color difference. Then using a threshold, we distinguish marks and false candidates. Finally we use the most similar adjacent area around mark to remove the mark from skin. Our algorithm represents significant accuracy in mole detection and removal.","PeriodicalId":161929,"journal":{"name":"2017 Iranian Conference on Electrical Engineering (ICEE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Facial mark detection and removal using graph relations and statistics\",\"authors\":\"M. Hosseini, M. Jamzad\",\"doi\":\"10.1109/IRANIANCEE.2017.7985432\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Face Analysis is an important task in image processing. Most of these tasks centralized on face recognition and detection. One of different ways for deceiving automatic face analysis systems is mark notation on the skin. On the other hand some applications attempts to eliminate defects of the face. Hence, in this paper we try to detect and remove skin marks on the face, whether they're natural or not. Our algorithm passes face image through appropriate filters to get mark candidates and then create a graph space using 8-point neighborhood relations of mark candidates image pixels. Then we compute probabilities of each mark candidate using four measures based on intensity of occurrence, shape density, uniqueness in local area and color difference. Then using a threshold, we distinguish marks and false candidates. Finally we use the most similar adjacent area around mark to remove the mark from skin. Our algorithm represents significant accuracy in mole detection and removal.\",\"PeriodicalId\":161929,\"journal\":{\"name\":\"2017 Iranian Conference on Electrical Engineering (ICEE)\",\"volume\":\"31 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 Iranian Conference on Electrical Engineering (ICEE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IRANIANCEE.2017.7985432\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 Iranian Conference on Electrical Engineering (ICEE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IRANIANCEE.2017.7985432","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Facial mark detection and removal using graph relations and statistics
Face Analysis is an important task in image processing. Most of these tasks centralized on face recognition and detection. One of different ways for deceiving automatic face analysis systems is mark notation on the skin. On the other hand some applications attempts to eliminate defects of the face. Hence, in this paper we try to detect and remove skin marks on the face, whether they're natural or not. Our algorithm passes face image through appropriate filters to get mark candidates and then create a graph space using 8-point neighborhood relations of mark candidates image pixels. Then we compute probabilities of each mark candidate using four measures based on intensity of occurrence, shape density, uniqueness in local area and color difference. Then using a threshold, we distinguish marks and false candidates. Finally we use the most similar adjacent area around mark to remove the mark from skin. Our algorithm represents significant accuracy in mole detection and removal.