Title :
Thermal Faceprint: A New Thermal Face Signature Extraction for Infrared Face Recognition
Author :
Akhloufi, Moulay ; Bendada, Abdelhakim
Author_Institution :
Comput. vision Lab., Laval Univ., Quebec City, QC
Abstract :
In this work we present an efficient approach for physiological features extraction from infrared face images. The physiological features represent the network of blood vessels under the face skin. These networks are unique to each individual. The proposed technique permits the construction of Faceprints (similar to fingerprints) from thermal infrared images of faces. The extracted faceprint is unique and can be used in infrared face recognition.
Keywords :
face recognition; feature extraction; infrared imaging; blood vessels; infrared face recognition; physiological feature extraction; thermal face signature extraction; thermal faceprint; Biomedical imaging; Blood vessels; Computer vision; Data mining; Face detection; Face recognition; Feature extraction; Infrared imaging; Skin; Temperature; Biometrics; Face recognition; Infrared imaging; Segmentation;
Conference_Titel :
Computer and Robot Vision, 2008. CRV '08. Canadian Conference on
Conference_Location :
Windsor, Ont.
Print_ISBN :
978-0-7695-3153-3
DOI :
10.1109/CRV.2008.43