DMCA
Volterrafaces: Discriminant Analysis using Volterra Kernels ∗
| Citations: | 11 - 3 self |
BibTeX
@MISC{Kumar_volterrafaces:discriminant,
author = {Ritwik Kumar and Arunava Banerjee and Baba C. Vemuri},
title = {Volterrafaces: Discriminant Analysis using Volterra Kernels ∗},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper we present a novel face classification system where we represent face images as a spatial arrangement of image patches, and seek a smooth non-linear functional mapping for the corresponding patches such that in the range space, patches of the same face are close to one another, while patches from different faces are far apart, in L2 sense. We accomplish this using Volterra kernels, which can generate successively better approximations to any smooth non-linear functional. During learning, for each set of corresponding patches we recover a Volterra kernel by minimizing a goodness functional defined over the range space of the sought functional. We show that for our definition of the goodness functional, which minimizes the ratio between intra-class distances and inter-class distances, the problem of generating Volterra approximations, to any order, can be posed as a generalized eigenvalue problem. During testing, each patch from the test image that is classified independently, casts a vote towards image classification and the class with the maximum votes is chosen as the winner. We demonstrate the effectiveness of the proposed technique in recognizing faces by extensive experiments on Yale, CMU PIE and Extended Yale B benchmark face datasets and show that our technique consistently outperforms the state-of-the-art in learning based face discrimination. 1. Prologue World events, specially in the last decade, have lead to an increased interest in the field of biometrics based person identification. Face recognition in particular, has attracted prolific research in the computer vision and pattern recognition community. Even though impressive strides have been made towards providing an ultimate solution to this problem, significant and interesting problems remain. If we try to organize the epitome of literature present in this field, a dichotomy of approaches emerges. The first
Keyphrases
volterra kernel discriminant analysis range space prolific research inter-class distance approach emerges last decade smooth non-linear functional image classification extended yale benchmark face datasets sought functional goodness functional cmu pie intra-class distance computer vision l2 sense better approximation extensive experiment face image corresponding patch maximum vote spatial arrangement interesting problem test image ultimate solution image patch person identification smooth non-linear functional mapping face discrimination face recognition prologue world event generalized eigenvalue problem impressive stride pattern recognition community novel face classification system literature present volterra approximation
