Progressive Iris Image Quality Evaluation Model
Shi Fu-xun · Jisuanji gongcheng · 2010
Since there is no unified standard for iris image quality assessment at present,the recognition rejection rate and false acceptance rate cannot always be decreased efficiently.Aiming at this problem,this paper proposes a novel model for the assessment of iris image.According to the characteristics of different interfering factors in the iris image,regionalization and weighted methods are adopted on the basis of a prior knowledge in order to perform an incremental pixel-level evaluation of various interfering factors in iris images.The image-level overall evaluation based on pixel-level assessment results proceeds.Experimental results show that the pixel level iris image quality assessment has a better performance in blur recognition and interference term identification,image-level assessment of iris image quality assessment is consistent with the manual.