Imperial College London

STEFANOS ZAFEIRIOU, PhD

Faculty of EngineeringDepartment of Computing

Professor in Machine Learning & Computer Vision
 
 
 
//

Contact

 

+44 (0)20 7594 8461s.zafeiriou Website CV

 
 
//

Location

 

375Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Tzimiropoulos:2012:10.1109/TPAMI.2012.40,
author = {Tzimiropoulos, G and Zafeiriou, S and Pantic, M},
doi = {10.1109/TPAMI.2012.40},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
pages = {2454--2466},
title = {Subspace learning from image gradient orientations},
url = {http://dx.doi.org/10.1109/TPAMI.2012.40},
volume = {34},
year = {2012}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - We introduce the notion of subspace learning from image gradient orientations for appearance-based object recognition. As image data are typically noisy and noise is substantially different from Gaussian, traditional subspace learning from pixel intensities very often fails to estimate reliably the low-dimensional subspace of a given data population. We show that replacing pixel intensities with gradient orientations and the 2 norm with a cosine-based distance measure offers, to some extend, a remedy to this problem. Within this framework, which we coin Image Gradient Orientations (IGO) subspace learning, we first formulate and study the properties of Principal Component Analysis of image gradient orientations (IGO-PCA). We then show its connection to previously proposed robust PCA techniques both theoretically and experimentally. Finally, we derive a number of other popular subspace learning techniques, namely, Linear Discriminant Analysis (LDA), Locally Linear Embedding (LLE), and Laplacian Eigenmaps (LE). Experimental results show that our algorithms significantly outperform popular methods such as Gabor features and Local Binary Patterns and achieve state-of-the-art performance for difficult problems such as illumination and occlusion-robust face recognition. In addition to this, the proposed IGO-methods require the eigendecomposition of simple covariance matrices and are as computationally efficient as their corresponding 2 norm intensity-based counterparts. Matlab code for the methods presented in this paper can be found at http://ibug.doc.ic.ac.uk/resources.
AU - Tzimiropoulos,G
AU - Zafeiriou,S
AU - Pantic,M
DO - 10.1109/TPAMI.2012.40
EP - 2466
PY - 2012///
SN - 0162-8828
SP - 2454
TI - Subspace learning from image gradient orientations
T2 - IEEE Transactions on Pattern Analysis and Machine Intelligence
UR - http://dx.doi.org/10.1109/TPAMI.2012.40
UR - http://hdl.handle.net/10044/1/43175
VL - 34
ER -