【摘要】 提出了一种基于小波包变换和支持向量机的虹膜识别方法。用小波包变换对归一化的虹膜图像进行2层分解,并计算出每个子频带的能量;通过选择具有最大能量值的特征作为小波基特征,以减少进入支持向量机的样本数目和提高识别准确率;最后,用支持向量机对虹膜特征进行模式匹配。实验结果表明,该方法取得了较好的识别效果。更多还原

【Abstract】 An iris recognition method using wavelet packet transformation and SVM is presented.First wavelet packet transformation is used to decomposition normalized iris image for 2 levels,and every sub-band energy is calculated;Then the feature vectors with the highest energy values are regarded as wavelet basis features before they are input to SVM,in order to reduce the samples of SVM and im-prove veracity.At last,SVM is used to match iris features.The experiment indicates that the approach could provide a good result for the iris recognition.更多还原