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.