基于复合结构分类器的人耳识别

在基于独立分量分析的人耳识别方法研究基础上,提出复合结构分类器的人耳识别通用模型. 该模型首先根据人耳的几何特征对人耳进行粗分类;然后应用独立分量分析的方法提取代数特征,支持向量机进行细分类,最后给出分类结果. 这与人类由粗到细的识别过程是相符合的,能够克服单一独立分量分析识别方法的特征提取时间过长、特征数过多的缺点,同时避免了归一化过程中丢失比例结构特征的问题. 实验结果表明,该模型取得了较高的识别率,尤其适用于规模大的复杂人耳库.

Ear recognition based on compound structure classifier

Based on the research of ear recognition with independent component analysis (ICA), a new compound structure classifier (CSCER) ear recognition model was proposed. The model made rough classification to the human ears first according to their geometric features, then ICA was used to extract the algebra features and support vector machine (SVM) was for detailed classification, finally the results were achieved, which was in accordance with human natural recognition process. The model overcame the single ICA disadvantages of costing too much time and with too many features, also avoided losing structure feature when ear images were preprocessed. The experiment shows that the model can achieve high recognition rate and is suitable for complex ear image libraries.