Multiscale Local Phase Quantization for Robust Component-Based Face Recognition Using Kernel Fusion of Multiple Descriptors

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 35; no. 5; pp. 1164 - 1177
• Main Authors: Chan, Chi Ho, Tahir, Muhammad Atif, Kittler, Josef, Pietikainen, Matti
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.05.2013; IEEE Computer Society
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Biometric Identification - methods; Computer science; control theory; systems; Data processing. List processing. Character string processing; Databases, Factual; Discriminant Analysis; Exact sciences and technology; Face; Face - anatomy & histology; face image representation; Face recognition; Histograms; Humans; Image Processing, Computer-Assisted; Kernel; kernel discriminant analysis; kernel fusion; Lighting; local binary pattern; local phase quantization; Memory organisation. Data processing; Pattern recognition. Digital image processing. Computational geometry; Software; Vectors; Image processing; local phase quantization; Electronic countermeasure; Texture; System decomposition; Image matching; local binary pattern; Efficiency; Signal quantization; Classification; Facies; Database; Illumination; Robustness; Combined system; Pattern extraction; Computer vision; Discriminant analysis; Merging sort; kernel discriminant analysis; Face recognition; blurring image; Software component; Blurred image; Computational geometry; Luminance; Multiscale method; kernel fusion; Alignment defect; face image representation

Face recognition subject to uncontrolled illumination and blur is challenging. Interestingly, image degradation caused by blurring, often present in real-world imagery, has mostly been overlooked by the face recognition community. Such degradation corrupts face information and affects image alignmen...