{"title":"New Approach to Face Recognition Using Co-occurrence Matrix and Bayesian Neural Networks","authors":"El houssaine Hssayni, M. Ettaouil","doi":"10.1109/ICOA49421.2020.9094501","DOIUrl":null,"url":null,"abstract":"Faces represent complex multidimensional significant visual stimuli and developing a computational model for face recognition is difficult. In this paper we present a new approach to the face recognition problem by combining Co-occurrence Matrix and Bayesian Neural Networks. Firstly, we use Co-occurrence Matrix to extract the relevant information in a face image, which are important for identification. Using this we can represent face pictures with several coefficients instead of having to use the whole picture. Then, Bayesian Neural networks are used to recognize the face through learning correct classifcation of the coeficients calculated by the Co-occurrence Matrix. The experimental results on the ORL database illustrate that the proposed approach has better performance in term of accuracy compared to old approaches.","PeriodicalId":253361,"journal":{"name":"2020 IEEE 6th International Conference on Optimization and Applications (ICOA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE 6th International Conference on Optimization and Applications (ICOA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOA49421.2020.9094501","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Faces represent complex multidimensional significant visual stimuli and developing a computational model for face recognition is difficult. In this paper we present a new approach to the face recognition problem by combining Co-occurrence Matrix and Bayesian Neural Networks. Firstly, we use Co-occurrence Matrix to extract the relevant information in a face image, which are important for identification. Using this we can represent face pictures with several coefficients instead of having to use the whole picture. Then, Bayesian Neural networks are used to recognize the face through learning correct classifcation of the coeficients calculated by the Co-occurrence Matrix. The experimental results on the ORL database illustrate that the proposed approach has better performance in term of accuracy compared to old approaches.