Basically, we have studied the image processing-based illumination normalization methods including histogram modification (equalization or specification), log transform, Gamma Intensity Correction (GIC), phase image, and relative gradients edges etc.  However, to better model the problem, we have also investigated model-based methods, such as the spherical harmonics methods. 

• Virtual Face View for Illumination Insensitive Face Recognition

To solve lighting problem, providing multiple training samples to the recognition system is a rational choice. However, enough samples are not always available for many practical applications. It is an alternative to augment the training set by generating virtual views from one single face image, that is, relighting the given face images of the given face. Based on this strategy, we have presented some attempts by presenting a ratio-image based face relighting method. See our ICASSP2003 paper, also ICASSP2002 or contact Dr.Shiguang Shan

• Gamma Intensity Correction

Evaluations of the state-of-the-art of both academic face recognition algorithms and commercial systems have shown that recognition performance of most current technologies degrades due to the variations of illumination. This paper investigates several illumination normalization methods and proposes some novel solutions. The main contribution of this paper includes: (1) A Gamma Intensity Correction (GIC) method is proposed to normalize the overall image intensity at the given illumination level; (2) A Region-based strategy combining GIC and the Histogram Equalization (HE) is proposed to further eliminate the side-lighting effect; (3) A Quotient Illumination Relighting (QIR) method is presented to synthesize images under a pre-defined normal lighting condition from the provided face images captured under non-normal lighting condition. These methods are evaluated and compared on the Yale illumination face database B and Harvard illumination face database. Considerable improvements are observed. Some conclusions are given at last. See our AMFG2003 paper or contact Dr.Shiguang Shan.

• Empirical Comparisons of Several Preprocessing Methods
  for Illumination Insensitive Face Recognition

Illumination variation is one of the bottlenecks of face recognition systems. In the past few years, many approaches to coping with illumination variations have been proposed which can be categorized into model-based and preprocessing-based. Although the model-based approaches seem more perfect in theory, they commonly introduce more constraints, which make them not practical enough for the real applications. On the other hand, the preprocessing approaches commonly exploit simple and efficient image processing techniques. The typical approaches based on image processing include histogram equalization (HE), histogram specification (HS), logarithm transform (Log), Gamma intensity correction (GIC), and self-quotient image (SQI). In this paper, we perform extensive experiments to analyze and compare these methods empirically by evaluating them on three large-scale face databases: CMU-PIE database, FERET database and CAS-PEAL database. Our experimental results show that HE, HS and GIC can improve recognition performance for both images with and without illumination variations, while Log and SQI may decrease the recognition rate for face images without much illumination variations though they may facilitate the recognition of face images with illumination variations. See our ICASSP2005 paper or contact Dr.Shiguang Shan.

• Face Recognition with Harmonic De-lighting

We present an illumination normalization approach by relighting face images to a canonical illumination based on the harmonic images model. Benefiting from the observations that human faces share similar shape, and the albedos of the face surfaces are quasi-constant, we first estimate the nine low-frequency components of the illumination from the input facial image. The facial image is then normalized to the canonical illumination by re-rendering it using the illumination ratio image technique. For the purpose of face recognition, two kinds of canonical illuminations, the uniform illumination and a frontal flash with the ambient lights, are considered, among which the former encodes merely the texture information, while the latter encodes both the texture and shading information. Our experiments on the CMU-PIE face database and the Yale B face database have shown that the proposed relighting normalization can significantly improve the performance of a face recognition system when the probes are collected under varying lighting conditions.. See our ACCV2004, IJPRAI2005 paper, or contact Dr.Laiyun Qing.

• Eigen-Harmonics Faces

The performances of face recognition systems are heavily subject to the variations in lighting. We propose a novel approach for face recognition under generic illumination conditions, named as Eigen-harmonics faces in this paper. First, using bootstrap set consisting of 3D face models with texture, we render the spherical harmonic images for every face and train the PCA harmonics faces model. During registration, given a novel face image under arbitrary illumination, we estimate the lighting of the image and recover the PCA coefficients of the spherical harmonics images for this face. During testing, we recognize the face using the PCA coefficients. The experimental results on the images under a wide range of illumination conditions in the public CMU-PIE database are promising. See our FG2004 paper, or contact Dr.Laiyun Qing