{"title":"彩色人脸图像唇形检测的一种高效算法","authors":"Behrooz Zali-Vargahan, H. Kalbkhani, M. Shayesteh","doi":"10.1109/IRANIANCEE.2013.6599705","DOIUrl":null,"url":null,"abstract":"In this paper, we present a new algorithm for finding lip area in color face images. Lip detection is used in many applications such as face detection, lip reading, and speech recognition. Our algorithm selects proper color space and saturation component for better separation of skin pixels from lip pixels. We consider the lower half part of image. We propose a modified Lip-Map algorithm to find lip area. Then, we apply wavelet transform to reduce the effect of noise. Next, the location of lips is obtained by considering the variance of different segments of lip area. We extract lip pixels from skin pixels by Top-Hat transform and region growing algorithm. To evaluate the performance of the proposed algorithm, we use four databases named as CVL, IMM, GTAV, and CID, in which the size of face image and the rotation of face are variable. Experimental results demonstrate that the proposed algorithm has better performance than previously presented methods.","PeriodicalId":383315,"journal":{"name":"2013 21st Iranian Conference on Electrical Engineering (ICEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"An efficient algorithm for lip detection in color face images\",\"authors\":\"Behrooz Zali-Vargahan, H. Kalbkhani, M. Shayesteh\",\"doi\":\"10.1109/IRANIANCEE.2013.6599705\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we present a new algorithm for finding lip area in color face images. Lip detection is used in many applications such as face detection, lip reading, and speech recognition. Our algorithm selects proper color space and saturation component for better separation of skin pixels from lip pixels. We consider the lower half part of image. We propose a modified Lip-Map algorithm to find lip area. Then, we apply wavelet transform to reduce the effect of noise. Next, the location of lips is obtained by considering the variance of different segments of lip area. We extract lip pixels from skin pixels by Top-Hat transform and region growing algorithm. To evaluate the performance of the proposed algorithm, we use four databases named as CVL, IMM, GTAV, and CID, in which the size of face image and the rotation of face are variable. Experimental results demonstrate that the proposed algorithm has better performance than previously presented methods.\",\"PeriodicalId\":383315,\"journal\":{\"name\":\"2013 21st Iranian Conference on Electrical Engineering (ICEE)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-05-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 21st Iranian Conference on Electrical Engineering (ICEE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IRANIANCEE.2013.6599705\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 21st Iranian Conference on Electrical Engineering (ICEE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IRANIANCEE.2013.6599705","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
An efficient algorithm for lip detection in color face images
In this paper, we present a new algorithm for finding lip area in color face images. Lip detection is used in many applications such as face detection, lip reading, and speech recognition. Our algorithm selects proper color space and saturation component for better separation of skin pixels from lip pixels. We consider the lower half part of image. We propose a modified Lip-Map algorithm to find lip area. Then, we apply wavelet transform to reduce the effect of noise. Next, the location of lips is obtained by considering the variance of different segments of lip area. We extract lip pixels from skin pixels by Top-Hat transform and region growing algorithm. To evaluate the performance of the proposed algorithm, we use four databases named as CVL, IMM, GTAV, and CID, in which the size of face image and the rotation of face are variable. Experimental results demonstrate that the proposed algorithm has better performance than previously presented methods.