一种虹膜图像质量评价的方法

虹膜图像质量是影响虹膜识别系统精度的关键。从序列图像中挑选出符合要求的虹膜图像能有效地降低识别系统的拒识率和误识率。这里按照产生虹膜图像奇异的不同情形：失焦、运动模糊、眼睑遮挡及睫毛遮挡,充分利用虹膜自身的纹理分布特点,在算法中引入了评价区域局部化、小波包分解和能量加权等思想,分别设计相应算法加以评判。实验结果表明该评价方案快速有效,其评价结果和人眼主观评价相吻合。

Iris image quality assessment method

The quality of iris image is the key point to affect the accuracy of iris recognition system.Selecting good iris images from a sequence frames can efficiently depress the false rejection rate and false acceptance rate of the recognition system.Four main causes from various factor-oriented noises often degrade iris image quality:defocus,motion blur,eyelid occlusion,and eyelash occlusion.Considering the texture distribution characteristics on iris images,an image quality assessment method is proposed corresponding to different situations based on the ideas of evaluation area localizing,wavelet packet transform,and weighted energy.The experiment results show that the presented method is efficient and real-time in assessing the quality of iris images,and the evaluation results are coincident to the judgment of human eyes.