A face image illumination quality evaluation method based on Gaussian low-pass filter

In this paper, according to the definition of the face image" illumination quality index (IQI) ", and from the method of illumination normalization, using a Gaussian low-pass filter (GLPF), which is based on single scale Retinex (SSR), to estimate the illumination of the probe face image and the reference image. The similarity score of the two estimated luminance images are calculated by normalized correlation, thus getting the illumination quality index of the probe face image. Finally, through analyzing the distribution of the IQI mean value and standard deviation, Gaussian low-pass filter and Logarithm Discrete Cosine Transformation (LogDCT) are compared, to verify the validity of the illumination quality index to measure the uneven degree of illumination.

[1]  Zia-ur Rahman,et al.  Retinex processing for automatic image enhancement , 2004, J. Electronic Imaging.

[2]  Ralph Gross,et al.  An Image Preprocessing Algorithm for Illumination Invariant Face Recognition , 2003, AVBPA.

[3]  Roberto Cipolla,et al.  A methodology for rapid illumination-invariant face recognition using image processing filters , 2009, Comput. Vis. Image Underst..

[4]  Dong Ren,et al.  Illumination normalization for robust face recognition using edge-preserving filtering , 2012, World Automation Congress 2012.

[5]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[6]  Sabah Jassim,et al.  Image-Quality-Based Adaptive Face Recognition , 2010, IEEE Transactions on Instrumentation and Measurement.

[7]  H. G. Adelmann,et al.  A frequency-domain Gaussian filter module for quantitative and and reproducible high-pass, low-pass, and bandpass filtering of images , 1997 .

[8]  Shimon Ullman,et al.  Face Recognition: The Problem of Compensating for Changes in Illumination Direction , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Dong Ren,et al.  A Robust Processing Chain for Face Recognition under Varying Illumination , 2011, Intell. Autom. Soft Comput..

[10]  Joongkyu Kim,et al.  Retinex method based on adaptive smoothing for illumination invariant face recognition , 2008, Signal Process..

[11]  Zia-ur Rahman,et al.  Properties and performance of a center/surround retinex , 1997, IEEE Trans. Image Process..