摘要
指纹图像的周期性和局部方向性是指纹图像的重要结构特征,充分利用这两个结构特征是提高指纹增强算法的重要方法.对一般图像增强算法处理指纹图像分析后,发现了一般图像增强算法无法满足指纹识别系统的要求.为了提高指纹增强算法的综合性能,作者以指纹图像局部方向和周期为参数,并设计了基于梯度得求局部方向的算法,再以Gabor变换为基础,设计了基于结构的自适应滤波算法.试验结果表明,该算法具有很高的实用价值,能够满足一般指纹识别系统性能要求.
Periods and local direction of fingerprint image are the important structure characters . The two characters of structure are important in the fingerprint enhancement. It can＇t fill automatic fingerprint identification system after researching the fingerprint image enhanced by ordinary enhancement ways. To improve the ability of fingerprint image enhancement way, the writer designs the orientation algorithm based on the grads, and then uses the local directions and periods to design a fast and effective fingerprint enhancemnermt algorithm based on Gabor transforms. The experimentations show that algorithm has a high practical value and can fill the automatic fingerprint identification system.
出处
《湖南工程学院学报（自然科学版）》
2007年第2期52-55,59,共5页
Journal of Hunan Institute of Engineering(Natural Science Edition)
关键词
指纹识别
周期性
方向性
图像增强
自适应滤波
fingerprint identification
periods
direction
image-enhancement
adaptive-filter
