查询结果:   李康顺,李凯,张文生.一种基于改进BP神经网络的PCA人脸识别算法[J].计算机应用与软件,2014,31(1):158 - 161.
中文标题
一种基于改进BP神经网络的PCA人脸识别算法
发表栏目
人工智能与识别
摘要点击数
937
英文标题
PCA FACE RECOGNITION ALGORITHM BASED ON IMPROVED BP NEURAL NETWORK
作 者
李康顺 李凯 张文生 Li Kangshun Li Kai Zhang Wensheng
作者单位
江西理工大学理学院 江西 赣州 341000 华南农业大学信息学院 广东 广州 510642 中国科学院自动化研究所 北京 100190   
英文单位
School of Science, Jiangxi University of Science & Technology, Ganzhou 341000, Jiangxi, China School of Information, South China Agricultural University, Guangzhou 510642, Guangdong, China Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China   
关键词
人脸识别 主成分分析 BP神经网络 附加动量 弹性梯度下降法
Keywords
Face recognition Principal component analysis BP neural network Additional momentum Elastic gradient descent method
基金项目
国家自然科学基金项目(70971043);江西省教育厅科学技术研究项目(GJJ112348)
作者资料
李康顺,教授,主研领域:图像识别,演化计算。李凯,硕士生。张文生,研究员。 。
文章摘要
人脸识别作为模式识别领域的热点研究问题受到了广泛的关注。传统BP算法虽然具有自学习、自适应以及强大的非线性映射能力并且在人脸图像识别准确率上占有很大的优势,但算法具有收敛缓慢、训练过程振荡、易陷入局部极小点等缺点。针对传统BP算法的不足提出一种基于改进BP神经网络的PCA人脸识别算法,该算法采用PCA算法提取图像的主要特征,并结合一种新的权值调整方法改进BP算法进行图像分类识别。仿真实验表明,通过使用该算法对ORL人脸数据库的图像进行识别,其结果比传统算法具有更快的收敛速度和更高的识别率。
Abstract
Face recognition, as a focus of the research in pattern recognition field, has gained increasing attention. Traditional BP algorithm has a strong ability in self-learning, self-adaptivity and nonlinear mapping. Moreover, it has a significant predominance in human face recognition accuracy. However, the algorithm also has shortages including slow convergence, training process oscillation and easy to fall into local minima. In light of these deficiencies of traditional BP neural network, we propose a PCA face recognition algorithm which is based on improved BP neural network. The algorithm uses PCA algorithm to extract principal features of face image and uses a new weight adjustment method to improve the BP algorithm for image classification and recognition. Simulation experimental results show that faster convergence speed and higher recognition rate are achieved when using the improved algorithm to identify the images in ORL face database than the traditional algorithm.
下载PDF全文