基于小波包分解的虹膜图像识别方法研究

Iris Image Identification Based on Wavelet Packet Decomposition

针对虹膜图像的纹理特征表示主要集中在中高频能量部分,对图像进行小波包分解,并提取出特征向量,运用变维方式对奇异值特征向量做进一步处理,进而将获得的特征向量做为虹膜图像的识别特征向量,依据欧氏距离分类器对他们做识别分类。最后的试验结果证明了这种算法的有效性与合理性。

The iris image＇s texture features are mainly concentrated on the high-frequency energy part,so it first carries out the image wavelet packet decomposition,extracts the feature vectors,processes the singular value eigenvectors for the variable dimension feature vector and takes the achieved feature vectors as the iris recognition＇s feature vectors,finally,classifies and identifies them according to Euclidean distance theory.The results and data achieved through the test show that this algorithm is reasonable and effective.