指纹图像质量评估的研究与应用

指纹图像质量评估是自动指纹识别系统（AFIS）中重要的一个环节,它将在对指纹图像进行分割、细化等预处理操作之前对图像质量进行评估,去除不满足要求的指纹图像以提高后续处理的鲁棒性。文章分析了现有的指纹采集细则,对有效面积、干湿、位置偏移、方向模糊等方面对指纹图像质量的影响进行探讨,对采集到的指纹图像质量进行质量评测,为图像的预处理提供质量较高的指纹图像。实验证明,该方法对不合格的指纹图像有较好的过滤效果,有利于提高整个指纹识别系统的效率。

Research and Application of Fingerprint Image Quality Estimation

Fingerprint image quality estimation is an important step of Automatic Fingerprint Identify System （AFIS）. It will estimate fingerprint image quality before segmentation, thinning and other pre-processing, which remove unqualified fingerprint image in order to enhance the robustness of the follow-up treatment. The quality of fingerprint image from fingerprint machine seriously affects preprocess and identification. The exiting detailed regulations were analyzed, the influence on fingerprint quality form valid area range of gray level, dry-wet, position offset and ambiguous direction to deflect were qualified fingerprint images were provided. Experimental results show that it can filter unqualified fingerprint image effectively, and it is helpful to raise the efficiency of whole system.