Fast quality assessment of face images for face recognition

Abstract

The captured face images are of all kinds of quality in a face recognition system, some poor quality images, for example blurry images, could degrade the performance of the face recognition system. It is obliged to assess the quality of the acquired images in order to eliminate the bad effects result from poor quality images. The current techniques of image quality assessment are not suitable for the quality assessment of face images. This paper analyzes the characters of face recognition and then proposes a quantitative clarity assessment method in detail. The experimental results show that the proposed method can assess the quality of the face images accurately and quickly. The method manages to satisfy the real-time requirement and can be adopted as a preprocessing step in the automatic face recognition system conveniently.