{"title":"Face Feature Dynamic Recognition Method Based on Intelligent Image","authors":"Ming Wang","doi":"10.1109/ICVRIS.2018.00022","DOIUrl":null,"url":null,"abstract":"In order to improve the performance of dynamic face recognition, a face recognition technology based on intelligent image is proposed, the signature features of the face are extracted, the information is sampled with the feature information of the pupil, eyelid, facial features and facial expression of a face. The face image is segmented by adaptive template matching method, and the feature information of pupil and eyelid is extracted by three-dimensional dynamic scanning method. The best pixel feature of the target face image is obtained by using the matched filter detector, and the dynamic 3D feature information of the face is extracted, and the face dynamic recognition is carried out according to the feature extraction result. The simulation results show that the proposed method is more accurate. It can improve the accuracy and resolution of face recognition.","PeriodicalId":152317,"journal":{"name":"2018 International Conference on Virtual Reality and Intelligent Systems (ICVRIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 International Conference on Virtual Reality and Intelligent Systems (ICVRIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICVRIS.2018.00022","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
In order to improve the performance of dynamic face recognition, a face recognition technology based on intelligent image is proposed, the signature features of the face are extracted, the information is sampled with the feature information of the pupil, eyelid, facial features and facial expression of a face. The face image is segmented by adaptive template matching method, and the feature information of pupil and eyelid is extracted by three-dimensional dynamic scanning method. The best pixel feature of the target face image is obtained by using the matched filter detector, and the dynamic 3D feature information of the face is extracted, and the face dynamic recognition is carried out according to the feature extraction result. The simulation results show that the proposed method is more accurate. It can improve the accuracy and resolution of face recognition.