摘要
小波包分解变换作为传统小波变换方法的延展,能够实现更精细的分解并得到更多小波包子图。基于此方法,提出一种改进的虹膜识别算法。该方法先对虹膜内外边缘进行定位和归一化,再通过小波包分解得到小波包子图,计算每个子图的系数得到虹膜特征向量,最终根据不同子图计算两幅虹膜图像对应特征向量的Hamming距离。通过实验仿真,表明由加权Hamming距离分类器来识别计算的系数能有效提升虹膜的识别精度。
As an extension of the traditional wavelet transform method,wavelet packet decomposition transform can achieve finer decomposition and get more subgraphs of wavelet packets.Based on the method,an improved iris recognition algorithm is proposed.Firstly,the inner and outer edges of the iris are located and normalized,then the wavelet packet decomposition is used to get the subgraphs of wavelet packets,and the coefficients of each subgraph are calculated to get the iris feature vector.Finally,the Hamming distance of the corresponding feature vectors of two iris images is calculated according to different subgraphs.The experimental simulation shows that the weighted Hamming distance classifier can effectively improve the accuracy of iris recognition.
作者
王义
田小情
郑悦
WANG Yi;TIAN Xiaoqing;ZHENG Yue(College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China)
出处
《微处理机》
2023年第2期44-47,共4页
Microprocessors
基金
贵州省自然科学基金(黔科合基础【2019】1064)。
