A real-time face tracker

J Yang, A Waibel - … Third IEEE Workshop on Applications of …, 1996 - ieeexplore.ieee.org
The authors present a real-time face tracker. The system has achieved a rate of 30+
frames/second using an HP-9000 workstation with a frame grabber and a Canon VC-Cl …

Fast normalized cross correlation for defect detection

DM Tsai, CT Lin - Pattern recognition letters, 2003 - Elsevier
Normalized cross correlation (NCC) has been used extensively for many machine vision
applications, but the traditional normalized correlation operation does not meet speed …

Three-dimensional face recognition

AM Bronstein, MM Bronstein, R Kimmel - International Journal of …, 2005 - Springer
An expression-invariant 3D face recognition approach is presented. Our basic assumption is
that facial expressions can be modelled as isometries of the facial surface. This allows to …

Face recognition: component-based versus global approaches

B Heisele, P Ho, J Wu, T Poggio - Computer vision and image …, 2003 - Elsevier
We present a component-based method and two global methods for face recognition and
evaluate them with respect to robustness against pose changes. In the component system …

Skin-color modeling and adaptation

J Yang, W Lu, A Waibel - Computer Vision—ACCV'98: Third Asian …, 1997 - Springer
This paper studies a statistical skin-color model and its adaptation. It is revealed that (1)
human skin colors cluster in a small region in a color space;(2) the variance of a skin color …

Projection functions for eye detection

ZH Zhou, X Geng - Pattern recognition, 2004 - Elsevier
In this paper, the generalized projection function (GPF) is defined. Both the integral
projection function (IPF) and the variance projection function (VPF) can be viewed as special …

Subspace iteration randomization and singular value problems

M Gu - SIAM Journal on Scientific Computing, 2015 - SIAM
A classical problem in matrix computations is the efficient and reliable approximation of a
given matrix by a matrix of lower rank. The truncated singular value decomposition (SVD) is …

F-CNN: An FPGA-based framework for training convolutional neural networks

W Zhao, H Fu, W Luk, T Yu, S Wang… - 2016 IEEE 27Th …, 2016 - ieeexplore.ieee.org
This paper presents a novel reconfigurable framework for training Convolutional Neural
Networks (CNNs). The proposed framework is based on reconfiguring a streaming datapath …

Finding faces in cluttered scenes using random labeled graph matching

TK Leung, MC Burl, P Perona - Proceedings of IEEE …, 1995 - ieeexplore.ieee.org
An algorithm for locating quasi-frontal views of human faces in cluttered scenes is
presented. The algorithm works by coupling a set of local feature detectors with a statistical …

Attention as an effect not a cause

RJ Krauzlis, A Bollimunta, F Arcizet, L Wang - Trends in cognitive sciences, 2014 - cell.com
Attention is commonly thought to be important for managing the limited resources available
in sensory areas of the neocortex. Here we present an alternative view that attention arises …