Fusion of mSSIM and SVM for reduced-reference facial image quality assessment
CCBR'12 Proceedings of the 7th Chinese conference on Biometric Recognition
| Hi-index | 0.00 |
In recent years face recognition has received substantial attentions from both research communities and the commercial, but remain challenging in real applications. One of the problems faced by face recognition system in real-time applications is the face image with poor quality conditions affecting the performance of the system especially in the face detection and face identification/verification phases. Quality problems observed such as shadows, hotspots, video artifacts, blurring, salt & pepper noise and movement blurring are common noises that affect the face recognition that uses webcam as the image capturing device. This paper proposes a solution of how the image quality for the face recognition can be improved. Image quality assessment is introduced to measure the quality of signal during the image acquisition and image restoration is proposed to restore degraded image by certain noise.