Image quality assessment based on noise detection

A new technique for image quality assessment based on noise detection is devised in this paper. Many applications like face recognition, ear recognition etc. are dependent on training images. Poor quality training images lead to inefficient training which in turn degrades the performance of a biometric system. This paper has proposed a technique for quality estimation of biometric images. The technique does not need any reference image for image quality assessment. Experimental analysis has shown the efficiency of the proposed technique.