摘要
针对KFDA算法中存在的问题,提出了基于大间距准则的混合核Fisher人脸特征提取算法;首先,将原始数据通过非线性映射投影到高维数据空间;然后,引入大间距准则和混合核函数使得同类样本在投影后离得更近,不同类样本在投影后离得更远;在PIE和AR人脸库中的仿真实验验证了算法的有效性和稳定性。
Mixed kernel fisher face feature extraction algorithm based on Maximum Margin Criterion is proposed,aiming at the existing problem of KFDA algorithm. First of all,the original data is projected to high-dimensional data space by nonlinear mapping. Then,the introduction of Maximum Margin Criterion and Mixed Kernel function makes the similar samples closer after projection,not similar samples farther after projection. In PIE and AR face database,the simulation results verify the effectiveness and stability of the algorithm in this paper.
出处
《重庆工商大学学报(自然科学版)》
2016年第3期43-46,共4页
Journal of Chongqing Technology and Business University:Natural Science Edition
基金
商洛学院科研基金项目(14SKY008)
关键词
大间距准则
混合核函数
FISHER判别分析
maximum margin criterion
mixed kernel function
Fisher discriminant analysis