基于图像质量评价的嵌入式指纹采集系统  

Embedding fingerprint capture system based on image quality evaluation algorithm

作　　者：马泽忠[1] 黄鸿[2] 穆光辉[3] 许江红 

机构地区：[1]重庆后勤工程学院,重庆400040 [2]重庆大学光电技术及系统教育部重点实验室,重庆400030 [3]重庆大学通信工程学院,重庆400030 [4]重庆市土地勘测规划院,重庆400020

出　　处：《传感器与微系统》2008年第4期89-91,共3页Transducer and Microsystem Technologies

基　　金：重庆市科技攻关计划资助项目(CSTC.2004AA2001-8277-02);中国科学院知识创新计划资助项目(KZCX2-SW-319)

摘　　要：指纹图像质量的好坏对于嵌入式自动指纹识别系统的性能有着重要的影响。利用FPS200的参数可调的特征及其指纹图像本身的方向特征,提出了一种新的针对FPS200指纹传感器获取的图像质量评估方法。通过方向图检查其有效面积与图像的清晰程度,判断图像质量是否合格。若不合格,则调整FPS200的参数,直至获得高质量的指纹图像。实验表明:该方法可以明显提高嵌入式指纹识别系统的整体性能。Fingerprint image quality evaluation is crucial in eliminating poor fingerprint images. This will heavily affect the performance of embedded automatic fingerprint identification system. A new method based on the intrinsic directional features of fingerprint is proposed to evaluate the quality of images captured by FPS200 sensor. Using directional map, the available area of image and clearness are checked to calculate the overall image quality score that can be used to quantitatively determine the quality of the fingerprint image. If the quality of image is unsatisfied, then embedded AFIS adjusts the parameters of FPS200 sensor automatically until image of good quality is captured. The result shows that this method indeed can improve the performance of embedded AFIS.

关 键 词：FPS200指纹传感器 方向图 优势方向 质量评价系统 

分 类 号：TN86[电子电信—信息与通信工程]