On single sample condition, current face recognition algorithm yields serious performance drop or even fail to work, therefore a face recognition algorithm based on LGBP and locality preserving discriminant analysis (LPDA) was proposed. Image enhancement and geometric transformation were firstly introduced to single sample face image for face reconstruction, making reconstruct image and original counterpart as a new training sample set. The feature of LGBP was then adopted for face image feature extraction. Afterwards LPDA was used for feature dimension reduction. Classification was finally accomplished by Euclidean distance- Nearest Neighbour Classifier. The validity of this algorithm was testified by ORL database, Yale database and FERET database.
Digital Object Identifier (DOI)
Xin, Minghai; Zhou, Yali; and Yan, Jingjie
"Single Sample Face Recognition using LGBP and Locality Preserving Discriminant Analysis,"
Applied Mathematics & Information Sciences: Vol. 09:
1, Article 48.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol09/iss1/48