An Image Preprocessing Algorithm for Illumination Invariant Face Recognition

By Ralph Gross, Vladimir Brajovic. International Conference on Audio- and Video-Based Biometric Person Authentication, 2003

392 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/07c90e85ac0f74b977babe245dea0f0abcf177e3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xiaogang Wang
2. Dacheng Tao
3. S. Li
4. Luc Van Gool
5. Yi Yang
6. Ming-Hsuan Yang
7. Andrew Zisserman
8. Bernt Schiele

Citations in the corpus

• Face Liveness Detection from a Single Image with Sparse Low Rank Bilinear Discriminative Model (2010, background): “[4] and Logarithmic Total Variation (LTV) smoothing by Chen et al.”
• Face Recognition Under Varying Illumination Using Gradientfaces (2009, methodology): “The authors in [20] and [21] proposed the self-quo-tient image (SQI) model to extend the QI theory, which parallels the former idea of Brajovic [22].”
• Total variation models for variable lighting face recognition (2006, background): “Some face recognition results of relevant works are reported in [16], [36].”
• Illumination Invariant Face Recognition Using Near-Infrared Images (2007, methodology): “Gross and Brajovic [27] and Wang et al. [28] developed reflectance estimation methods by using the idea of the ratio of the original image and its smooth version from Retinex [29] and center-surround filters [30].”
• Facial expression recognition from near-infrared videos (2011, background): “The use of illumination normalizationmethods are shown to improve recognition performance when there are illumination variations in the faces, but have not led to illumination invariant face representation due to significant difficulties, especially uncontrolled illumination directions [1,8,9,31].”
• Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions (2007, background): “However because they threshold at exactly the value of the central pixel i c they tend to be sensitive to noise, particularly in near-uniform image regions, and to smooth weak illumination gradients.”