Face Perception using Tensor Approach

Principal Component Analysis (PCA) is one of the common statistical techniques that can also be used for face perception. This approach introduces a single two-dimensional representation for facial attributes, allowing only one attribute to be different at a time. While a face consists of a set of edges that will define the shape and positions of facial features, these face properties may contribute differently and influence the actual face recognition performance. Therefore in this paper, we propose to extend the traditional PCA approach to a multidimensional tensor-based method. This approach could efficiently separate the facial attributes. Experiment was conducted and the obtained results have shown a higher recognition rates compared to the traditional PCA method.

[1]  G. Rhodes,et al.  A comparative view of face perception. , 2010, Journal of comparative psychology.

[2]  Jacey-Lynn Minoi,et al.  A tensor-based multivariate statistical model for 3D face and facial expression recognition , 2011, 2011 7th International Conference on Information Technology in Asia.

[3]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[4]  V. Bruce,et al.  Face processing: Human perception and principal components analysis , 1996, Memory & cognition.

[5]  Doris Y. Tsao,et al.  Mechanisms of face perception. , 2008, Annual review of neuroscience.

[6]  Demetri Terzopoulos,et al.  Multilinear image analysis for facial recognition , 2002, Object recognition supported by user interaction for service robots.

[7]  A. Young,et al.  Understanding the recognition of facial identity and facial expression , 2005, Nature Reviews Neuroscience.

[8]  A. Young,et al.  Understanding face recognition. , 1986, British journal of psychology.

[9]  Isma Hamid,et al.  Multi-modal medical image fusion using 2DPCA , 2017, 2017 2nd International Conference on Image, Vision and Computing (ICIVC).

[10]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[11]  Jun Wang,et al.  A 3D facial expression database for facial behavior research , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[12]  Timothy J. Andrews,et al.  Brain regions involved in processing facial identity and expression are differentially selective for surface and edge information , 2014, NeuroImage.

[13]  Andrew J. Calder,et al.  PII: S0042-6989(01)00002-5 , 2001 .

[14]  Christopher P. Benton,et al.  Representation of facial identity includes expression variability , 2019, Vision Research.

[15]  Giuseppe Iaria,et al.  The correlates of subjective perception of identity and expression in the face network: An fMRI adaptation study , 2009, NeuroImage.

[16]  Martin Eimer,et al.  Facial identity and facial expression are initially integrated at visual perceptual stages of face processing , 2016, Neuropsychologia.

[17]  J. Haxby,et al.  The distributed human neural system for face perception , 2000, Trends in Cognitive Sciences.

[18]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[19]  H. Hécaen,et al.  Agnosia for faces (prosopagnosia). , 1962, Archives of neurology.

[20]  Jasmin Kevric,et al.  Biomedical Signal Processing and Control , 2016 .

[21]  A. Young,et al.  In the Eye of the Beholder: The Science of Face Perception , 1998 .

[22]  Saritha Kinkiri,et al.  Reducing data storage requirements for machine learning algorithms using principle component analysis , 2016, 2016 International Conference on Applied System Innovation (ICASI).