摘要
针对虹膜图像采集过程中受光照条件不足、眼镜反光和眼皮遮挡等因素的影响而造成的图像质量不理想的问题,本文提出了一种基于BP神经网络的虹膜图像质量的分类方法。利用小波变换对每一幅虹膜图像进行特征提取,进而将提取的归一化虹膜图像数据作为BP神经网络的输入,以此对BP神经网络进行训练,实现了将3种被不同的影响因素影响的虹膜图像与未被影响图像进行区分的目的。仿真结果表明,该方法具有较高的虹膜分类精度以及较低的误差率。
We present a BP neural network based classification method for iris image quality in view of such bad-quality image issues as insufficient light condition, glasses reflection and eyelid shelter in the process of iris image acquisition. We initially employ two-dimensional wavelet transform to extract the features of an iris image, and then train a BP neural network with the extracted and normalized image as its input,finally. We therefore implement the goal of distinguishing the iris images affected by three different factors from unaffected images. Experimental results show that the method has higher classification accuracy and lower error rate.
出处
《山东科学》
CAS
2015年第2期108-112,共5页
Shandong Science
基金
山东省研究生教育创新计划(SDYY11115)
关键词
虹膜图像
质量分类
BP神经网络
小波变换
小波系数
iris image
quality classification
BP neural network
wavelet transform
wavelet coefficient
