DocumentCode :
481023
Title :
Partial PCA in frequency domain
Author :
Rama, Antonio ; Rurainsky, Jürgen ; Tarrés, Francesc ; Eisert, Peter
Volume :
2
fYear :
2008
fDate :
10-12 Sept. 2008
Firstpage :
463
Lastpage :
466
Abstract :
Partial principal component analysis has demonstrated to be a robust face recognition approach for big pose variations. The main idea behind P2CA is to use 3D (2.5D) data during the training stage but only a single 2D image in the recognition stage, to achieve a practical system for face recognition which is robust against pose variations. Nevertheles this approach present two major drawbacks: First one is that the training data should be well aligned to obtain good results; the second drawback is computational cost since the face space is computed maintaining the spatial dimensionality of the images. Thus, in this paper, we address both problems. First, we propose a two step procedure for a more accurate alignment of the 2.5D training texture maps. This alignment is done by applying a global and local affine transformation to all texture maps, while the local alignment is applied to some facial features using a triangulation mesh. Second, the computational cost is also reduced by applying P2CA in the frequency domain and perform the normalized cross correlation as similarity measure. Introducing these two improvements the recognition accuracy increases by 4% due to the alignment procedure and the computational time is reduced by a factor between 10 and 100 (depending on the number of eigenvectors used) due to the application of P2CA in the frequency domain.
Keywords :
face recognition; frequency-domain analysis; image texture; principal component analysis; 2D image recognition; face recognition; frequency domain analysis; partial principal component analysis; spatial dimensionality; triangulation mesh; Computational efficiency; Face recognition; Facial features; Frequency domain analysis; Frequency measurement; Image recognition; Performance evaluation; Principal component analysis; Robustness; Training data; Face Recognition; Partial Principal Component Analysis; face feature alignment; texture maps;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
ELMAR, 2008. 50th International Symposium
Conference_Location :
Zadar
ISSN :
1334-2630
Print_ISBN :
978-1-4244-3364-3
Type :
conf
Filename :
4747543
Link To Document :
بازگشت