基于FastICA的模糊强噪背景下指纹盲提取研究

Fingerprint Blind Source Selection Based on FastICA in the Condition of Faintness and High Noise

独立分量分析作为盲源信号分离的一种有效方法在许多方面都获得了成功的应用。这里对独立分量分析的基本理论和FastICA的算法实现做了简要介绍。针对犯罪现场嫌疑人遗留的指纹都非常模糊、杂乱,不能进行鉴定的特点,提出一种基于FastICA的指纹提取方法,它通过对遗留在犯罪现场的模糊混合指纹进行盲分离,提取出清晰的单个指纹,从而鉴定犯罪嫌疑人。对实测数据进行盲分离的结果表明,快速独立分量分析方法是一种有效的指纹提取方法,该方法可分离出强噪声环境下的模糊指纹,具有很高的可靠性。

Independent Component Analysis （ICA） is an effective approach for the separation of blind signal, and has attracted broad attention and has been successfully used in many fields. The basic theory of ICA and algorithm of FastICA are briefly introduced. In the condition of fingerprint left behind in alibi are almost faintness and high noise,a novel method based on FastICA is presented which selected clear and single fingerprint by blind source separation to identify the suspect. The result of blind source separation for the data show that the FastICA is an effective method in the fingerprint blind selection, fingerprint in the condition of faintness and high noise can be estimated and come back,which is of high reliability.