Nighttime face recognition at large standoff: Cross-distance and cross-spectral matching

• Published in: Pattern Recognition Vol. 47; no. 12; pp. 3750 - 3766
• Main Authors: Kang, Dongoh, Han, Hu, Jain, Anil K., Lee, Seong-Whan
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.12.2014; Elsevier BV; Elsevier
• Subjects: Applied sciences; Cross-distance matching; Cross-spectral matching; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Heterogeneous face matching; Image processing; Image restoration; Information, signal and communications theory; K-means clustering; Locally Linear Embedding (LLE); Nighttime face recognition; Pattern recognition; Signal and communications theory; Signal processing; Signal representation. Spectral analysis; Signal, noise; Telecommunications and information theory; Nighttime face recognition; Cross-distance matching; Image restoration; Locally Linear Embedding (LLE); Cross-spectral matching; Heterogeneous face matching; K-means clustering; Biometrics; Performance evaluation; Automatic classification; State of the art; Image processing; K means algorithm; Degradation; Linear combination; Visible radiation; Safety; Monitoring; Damaging; Face recognition; Pattern recognition; Signal classification; Image method; Cross spectral density; Image quality; Near infrared radiation; Automatic recognition

Face recognition in surveillance systems is important for security applications, especially in nighttime scenarios when the subject is far away from the camera. However, due to the face image quality degradation caused by large camera standoff and low illuminance, nighttime face recognition at large...