Hajar Chouhayebi, J. Riffi, Mohamed Adnane Mahraz, Ali Yahyaouy, H. Tairi, Nawal Alioua
{"title":"基于几何特征的面部表情识别","authors":"Hajar Chouhayebi, J. Riffi, Mohamed Adnane Mahraz, Ali Yahyaouy, H. Tairi, Nawal Alioua","doi":"10.1109/ISCV49265.2020.9204111","DOIUrl":null,"url":null,"abstract":"the goal of facial expression Recognition is to detect human emotion through facial images. But the biggest challenge of recognizing facial expression is how to extract distinctive characteristics from images of the human face to differentiate diverse emotions. To tackle this challenge, we propose a FER algorithm using geometric features. In the first step, facial landmarks are detected from input sequence video using Dlib Library and geometric features are extracted, considering the spatial position between landmarks. These feature vectors are then implemented in Support Vector Machine (SVM) classifier to classify facial expressions. The Experimental results demonstrate that our proposed method applied on a fusion of two databases (personal database and BUHMAP) shows 94.5% accuracy.","PeriodicalId":313743,"journal":{"name":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Facial expression recognition based on geometric features\",\"authors\":\"Hajar Chouhayebi, J. Riffi, Mohamed Adnane Mahraz, Ali Yahyaouy, H. Tairi, Nawal Alioua\",\"doi\":\"10.1109/ISCV49265.2020.9204111\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"the goal of facial expression Recognition is to detect human emotion through facial images. But the biggest challenge of recognizing facial expression is how to extract distinctive characteristics from images of the human face to differentiate diverse emotions. To tackle this challenge, we propose a FER algorithm using geometric features. In the first step, facial landmarks are detected from input sequence video using Dlib Library and geometric features are extracted, considering the spatial position between landmarks. These feature vectors are then implemented in Support Vector Machine (SVM) classifier to classify facial expressions. The Experimental results demonstrate that our proposed method applied on a fusion of two databases (personal database and BUHMAP) shows 94.5% accuracy.\",\"PeriodicalId\":313743,\"journal\":{\"name\":\"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISCV49265.2020.9204111\",\"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 International Conference on Intelligent Systems and Computer Vision (ISCV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCV49265.2020.9204111","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Facial expression recognition based on geometric features
the goal of facial expression Recognition is to detect human emotion through facial images. But the biggest challenge of recognizing facial expression is how to extract distinctive characteristics from images of the human face to differentiate diverse emotions. To tackle this challenge, we propose a FER algorithm using geometric features. In the first step, facial landmarks are detected from input sequence video using Dlib Library and geometric features are extracted, considering the spatial position between landmarks. These feature vectors are then implemented in Support Vector Machine (SVM) classifier to classify facial expressions. The Experimental results demonstrate that our proposed method applied on a fusion of two databases (personal database and BUHMAP) shows 94.5% accuracy.