Human and machine recognition of Fourier-Bessel filtered face images

Motivated by a recently proposed biologically-inspired face recognition approach, psychophysical experiments have been carried out. We measured recognition performance of polar frequency filtered face images using an 8-alternatives forced-choice method. Test stimuli were generated by converting the images from the spatial to the polar frequency domain using the Fourier-Bessel transformation (FBT), filtering of the resulting coefficients with band-pass filters, and finally taking the inverse FBT of the filtered coefficients. We also evaluated an automatic FBT-based face recognition model. Contrast sensitivity functions of the human observers peaked in the 8-11.3 radial and angular frequency range, with higher peak sensitivity in the former case. The automatic face recognition algorithm presented similar behavior. These results suggest that polar frequency components could be used by the human face processing system and that human performance can be constrained by the polar frequency information content

[1]  R. L. de Valois,et al.  Cartesian and non-Cartesian responses in LGN, V1, and V2 cells , 2001, Visual Neuroscience.

[2]  Roberto Marcondes Cesar Junior,et al.  Face Verification in Polar Frequency Domain: A Biologically Motivated Approach , 2005, ISVC.

[3]  Keiji Tanaka,et al.  Neuronal selectivities to complex object features in the ventral visual pathway of the macaque cerebral cortex. , 1994, Journal of neurophysiology.

[4]  D Riley,et al.  Comments on “Recognition of faces in the presence of two-dimensional sinusoidal masks” by Tieger and Ganz , 1980, Perception & psychophysics.

[5]  P. Bennett,et al.  Identification of band-pass filtered letters and faces by human and ideal observers , 1999, Vision Research.

[6]  D. V. van Essen,et al.  Selectivity for polar, hyperbolic, and Cartesian gratings in macaque visual cortex. , 1993, Science.

[7]  Frank Tong,et al.  The Face of Controversy , 2001, Science.

[8]  P. O. Bishop,et al.  Spatial vision. , 1971, Annual review of psychology.

[9]  I. Craw,et al.  Effects of high-pass and low-pass spatial filtering on face identification , 1996, Perception & psychophysics.

[10]  Robert F Hess,et al.  Sensitivity for global shape detection. , 2003, Journal of vision.

[11]  Harry Wechsler,et al.  The FERET database and evaluation procedure for face-recognition algorithms , 1998, Image Vis. Comput..

[12]  Stefan R. Schweinberger,et al.  Covert Recognition and the Neural System for Face Processing , 2003, Cortex.

[13]  H. Wilson,et al.  Concentric orientation summation in human form vision , 1997, Vision Research.

[14]  D. C. Essen,et al.  Neural responses to polar, hyperbolic, and Cartesian gratings in area V4 of the macaque monkey. , 1996, Journal of neurophysiology.

[15]  H. Wilson,et al.  Detection of global structure in Glass patterns: implications for form vision , 1998, Vision Research.

[16]  Roberto Marcondes Cesar Junior,et al.  Automatic Face Recognition System Based on Local Fourier-Bessel Feature , 2005, XVIII Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'05).

[17]  Shuguang Guan,et al.  Fourier-Bessel analysis of patterns in a circular domain , 2001 .

[18]  R. Näsänen.  Spatial frequency bandwidth used in the recognition of facial images , 1999, Vision Research.

[19]  Roberto Marcondes Cesar Junior,et al.  Face recognition based on polar frequency features , 2005, TAP.

[20]  Leo Ganz,et al.  Recognition of faces in the presence of two-dimensional sinusoidal masks , 1977 .

[21]  Y Zana,et al.  Contrast sensitivity functions to stimuli defined in Cartesian, polar and hyperbolic coordinates. , 2005, Spatial vision.

[22]  Denis G. Pelli,et al.  Accurate control of contrast on microcomputer displays , 1991, Vision Research.