【摘要】 提出了一种通过提取力场收敛特征进行多姿态人耳识别的新方法。首先把人耳图像转换为力场图像,通过计算力场的散度得到人耳收敛特征,然后使用零空间线性判别分析算法进一步提取特征并分类识别。实验结果表明,力场收敛特征比最初基于力场变换的势能阱特征更为稳定,而零空间线性判别分析方法也优于传统的主元分析降维方法,更好地解决了小样本问题,识别率得到进一步提高。该方法能够有效识别多姿态人耳图像。更多还原

【Abstract】 This paper examined the feature extraction method based on force field transformation and developed a new approach for multi-pose ear recognition.Firstly transformed the initial gray ear image to force field and calculated the divergence of the force field to obtain the convergence feature of ear.Then employed the algorithm of null-space based linear discriminant analysis(NLDA) to complement classification and recognition.The experimental results show that the proposed method is more robust and effective than the initial feature extraction method based on force field transformation,the potential well-based method and demonstrate effectiveness for multi-pose ear recognition.更多还原