|
|||||
|
|
| 一种人脸识别的新方法 | |
| 引用本文： | 李月龙,尹建芹,李金屏. 一种人脸识别的新方法[J]. 济南大学学报(自然科学版), 2006, 20(4): 315-317 |
| 作者姓名： | 李月龙 尹建芹 李金屏 |
| 作者单位： | 济南大学,信息科学与工程学院,山东,济南,250022;济南大学,信息科学与工程学院,山东,济南,250022;济南大学,信息科学与工程学院,山东,济南,250022 |
| 基金项目： | 山东省高校学术骨干培养计划 |
| 摘 要： | 针对人脸识别过程中出现的无法有效区分多姿态人脸的问题，引入了离散余弦变换（DCT）和K—L变换来减小不同姿态所造成的影响，考虑到K—L变换可以对图象进行压缩，用K—L变换来降低图象数据的维数，并利用主成分分析的思想，只取一部分特征向量来表示数据。通过径向基（RBF）函数神经网络来达到识别不同人脸的目的。RBF网络的训练采用粒子群算法（PSO）。经实验证明，此方法可以达到较高的识别精度。 |
| 关 键 词： | 模式识别与智能系统 人脸识别 离散余弦(DCT)变换 K-L变换 径向基函数(RBF)网络 粒子群算法(PSO) |
| 文章编号： | 1671-3559(2006)04-0315-03 |
| 修稿时间： | 2005-12-30 |
A New Method of Face Recognition |
|
| LI Yue-long,YIN Jian-qin,LI Jin-ping. A New Method of Face Recognition[J]. Journal of Jinan University(Science & Technology), 2006, 20(4): 315-317 | |
| Authors: | LI Yue-long YIN Jian-qin LI Jin-ping |
| Abstract: | During face recognition,there exists a serious problem that it is very difficult to distinguish faces of various gestures.The discrete cosine transform(DCT) is introduced to reduce negative effects.K-L transformation can be used to compress images.According to primary component analysis(PCA),we utilize K-L to decrease data dimensions,i.e,only parts of vectors are used for data representation.Finally,RBF neural network is enrolled to recognize various faces.The task to train RBF is finished by PSO.It is proved by our experience that this method has a high accuracy. |
| Keywords: | pattern recognition and intelligent system face recognition discrete cosine transformation K-L transformation RBF neural network particle swarm optimization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |