Unsupervised Discriminant Projection Analysis for Feature Extr
Year: 2006
Type: conference-paper
Abstract: This paper develops an unsupervised discriminant projection (UDP) technique for feature extraction. UDP takes the local and non-local information into account, seeking to find a projection that maximizes the non-local scatter and minimizes the local scatter simultaneously. This characteristic makes UDP more intuitive and more powerful than the up-to-date method - locality preserving projection (LPP, which considers the local information only) for classification tasks. The proposed method is applied to face biometrics and examined using the ORL and FERET face image databases. Our experimental results show that UDP consistently outperforms LPP, PCA, and LDA
Authors: Jian Yang, D. Zhang, Zhong Jin, Jing-yu Yang
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: 基于生物特征的身份识别研究
OpenAlex ID: W2172156772
