%0 Conference Proceedings
%T Recognition of Occluded Faces Based on Multi-subspace Classification
%+ Faculty of Computer Science and Information Systems [Szczecin]
%A Forczmański, Paweł
%A Łabędź, Piotr
%Z Part 4: Pattern Recognition and Image Processing
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 12th International Conference on Information Systems and Industrial Management (CISIM)
%C Krakow, Poland
%Y Khalid Saeed
%Y Rituparna Chaki
%Y Agostino Cortesi
%Y Sławomir Wierzchoń
%I Springer
%3 Computer Information Systems and Industrial Management
%V LNCS-8104
%P 148-157
%8 2013-09-25
%D 2013
%R 10.1007/978-3-642-40925-7_15
%K face recognition
%K subspace method
%K dimensionality reduction
%K PCA
%Z Computer Science [cs]
%Z Humanities and Social Sciences/Library and information sciencesConference papers
%X In the paper we investigate a problem of face recognition in uncontrolled environment – distorted by occlusion, shadows and other local modifications. Such problems are very common for real-world conditions, thus the presented algorithm allows to eliminate them. It is based on dimensionality reduction approach (two-dimensional Karhunen-Loéve Transform) and distance-based classification. We use simple transformations involving face normalization and individual facial regions extraction as a pre-processing. Then, we perform independent recognition of extracted facial regions and combine the results in order to make a final classification. The results of experiments conducted on images taken from 9 publicly available datasets show that a quite simple algorithm is capable of successful recognition without high computing power requirements, as opposite to more sophisticated methods presented in the literature. As it was proved, the presented approach gives significantly better efficiency than a whole image-based recognition.
%G English
%Z TC 8
%2 https://inria.hal.science/hal-01496061/document
%2 https://inria.hal.science/hal-01496061/file/978-3-642-40925-7_15_Chapter.pdf
%L hal-01496061
%U https://inria.hal.science/hal-01496061
%~ SHS
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC8
%~ IFIP-CISIM
%~ IFIP-LNCS-8104