J
Juwei Lu
Researcher at University of Toronto
Publications - 30
Citations - 3804
Juwei Lu is an academic researcher from University of Toronto. The author has contributed to research in topics: Facial recognition system & Linear discriminant analysis. The author has an hindex of 17, co-authored 29 publications receiving 3662 citations. Previous affiliations of Juwei Lu include Nanyang Technological University.
Papers
More filters
Proceedings ArticleDOI
Generalizing capacity of face database for face recognition
Stan Z. Li,Juwei Lu +1 more
TL;DR: A novel method for generalizing the representational capacity of available face database using the feature line representation, which covers more of the face space than the feature points and thus expands the capacity of the available database.
Proceedings ArticleDOI
A kernel machine based approach for multi-view face recognition
TL;DR: This work proposes a kernel machine based discriminant analysis method, which deals with the nonlinearity of the face patterns' distribution and effectively solves the "small sample size" (SSS) problem which exists in most face recognition tasks.
Book ChapterDOI
A comparative study of skin-color models
TL;DR: A comparative study on skin-color models generally used for facial region location, which includes two 2D Gaussian models developed in normalized RGB and HSV color spaces respectively, a 1D lookup table model of hue histogram, and an adaptive 3D threshold box model are reported.
Kernel Discriminant Learning with Application to Face Recognition
TL;DR: A new kernel discriminant learning method is introduced, which attempts to deal with the two problems by using regularization and subspace de- composition techniques, and outperforms existing kernel methods, at a significantly reduced computational cost.
Book ChapterDOI
Global Feedforward Neural Network Learning for Classification and Regression
Kar-Ann Toh,Juwei Lu,Wei-Yun Yau +2 more
TL;DR: This paper addresses the issues of global optimality and training of a Feedforward Neural Network (FNN) error funtion incorporating the weight decay regularizer and proposes an iterative algorithm for global FNN learning.