高级检索
    古红英 潘云鹤. 基于纹理特征融合约减的虹膜识别研究[J]. 计算机研究与发展, 2006, 43(1): 126-131.
    引用本文: 古红英 潘云鹤. 基于纹理特征融合约减的虹膜识别研究[J]. 计算机研究与发展, 2006, 43(1): 126-131.
    Gu Hongying and Pan Yunhe. Iris Recognition Study Based on Texture Feature Fusion and Selection[J]. Journal of Computer Research and Development, 2006, 43(1): 126-131.
    Citation: Gu Hongying and Pan Yunhe. Iris Recognition Study Based on Texture Feature Fusion and Selection[J]. Journal of Computer Research and Development, 2006, 43(1): 126-131.

    基于纹理特征融合约减的虹膜识别研究

    Iris Recognition Study Based on Texture Feature Fusion and Selection

    • 摘要: 为了获得更完整的虹膜特征,通过空域和频域两个角度提取纹理特征,以变化分数维和小波特征值共同构成虹膜的初始特征序列.然后使用多目标遗传算法对所抽取的特征序列进行优化约减,最后以优化好的特征序列来训练虹膜分类器对虹膜进行识别.并针对虹膜认证实际应用中变化的安全性要求,使用了非对称的支持向量机.实验结果表明,结合时域和频域的特征序列较好地反映了虹膜的纹理变化特性,提高了虹膜识别的正确率.

       

      Abstract: Iris recognition is a prospering biometric method, but some technical difficulties still exist. To get more representative iris features, features from space and frequency domain are extracted at the same time. Both variation fractal dimension and wavelet features are extracted to form the feature sequence. Multi-objective genetic algorithm is employed to optimize the features. Finally the selected features of different iris patterns are used to train iris classifiers. Furthermore, traditional SVM is modified as non-symmetrical support vector machine to satisfy the variant security requirements in real iris recognition applications. Experimental data shows that the new feature sequence represents the variation details in the iris patterns properly. Therefore the correctness is improved.

       

    /

    返回文章
    返回