Face Recognition with Local Binary Patterns, Spatial Pyramid Histograms and Naive Bayes Nearest Neighbor Classification

Simple item page
dc.contributor.authorMaturana Sanguineti, Daniel Ignacio
dc.contributor.authorMery Quiroz, Domingo
dc.contributor.authorSoto Arriaza, Álvaro Marcelo
dc.date.accessioned2022-05-11T20:26:42Z
dc.date.available2022-05-11T20:26:42Z
dc.date.issued2009
dc.description.abstractFace recognition algorithms commonly assume that face images are well aligned and have a similar pose -- yet in many practical applications it is impossible to meet these conditions. Therefore extending face recognition to unconstrained face images has become an active area of research. To this end, histograms of Local Binary Patterns (LBP) have proven to be highly discriminative descriptors for face recognition. Nonetheless, most LBP-based algorithms use a rigid descriptor matching strategy that is not robust against pose variation and misalignment. We propose two algorithms for face recognition that are designed to deal with pose variations and misalignment. We also incorporate an illumination normalization step that increases robustness against lighting variations. The proposed algorithms use descriptors based on histograms of LBP and perform descriptor matching with spatial pyramid matching (SPM) and Naive Bayes Nearest Neighbor (NBNN), respectively. Our contribution is the inclusion of flexible spatial matching schemes that use an image-to-class relation to provide an improved robustness with respect to intra-class variations. We compare the accuracy of the proposed algorithms against Ahonen's original LBP-based face recognition system and two baseline holistic classifiers on four standard datasets. Our results indicate that the algorithm based on NBNN outperforms the other solutions, and does so more markedly in presence of pose variations.
dc.fuente.origenIEEE
dc.identifier.doi10.1109/SCCC.2009.21
dc.identifier.isbn9781424477524
dc.identifier.issn1522-4902
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=5532353
dc.identifier.urihttps://doi.org/10.1109/SCCC.2009.21
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/63831
dc.information.autorucEscuela de ingeniería ; Maturana Sanguineti, Daniel Ignacio ; S/I ;126587
dc.information.autorucEscuela de ingeniería ; Mery Quiroz, Domingo ; S/I ; 102382
dc.information.autorucEscuela de ingeniería ; Soto Arriaza, Álvaro Marcelo ; S/I ; 73678
dc.language.isoen
dc.nota.accesoContenido parcial
dc.pagina.final132
dc.pagina.inicio125
dc.publisherIEEE
dc.relation.ispartofInternational Conference of the Chilean Computer Science Society (2009 : Santiago, Chile)
dc.rightsacceso restringido
dc.subjectFace recognition
dc.subjectHistograms
dc.subjectNearest neighbor searches
dc.subjectRobustness
dc.subjectLighting
dc.subjectAlgorithm design and analysis
dc.subjectPattern recognition
dc.subjectGray-scale
dc.subjectComputer science
dc.subjectImage recognition
dc.titleFace Recognition with Local Binary Patterns, Spatial Pyramid Histograms and Naive Bayes Nearest Neighbor Classificationes_ES
dc.typecomunicación de congreso
sipa.codpersvinculados126587
sipa.codpersvinculados102382
sipa.codpersvinculados73678
Files
Collections
Artículos de conferencia