基于粒子群算法和神经网络的人脸识别分类器研究 |
点此下载全文 |
引用本文:段向军.基于粒子群算法和神经网络的人脸识别分类器研究[J].计算技术与自动化,2011,(2):115-117 |
摘要点击次数: 1578 |
全文下载次数: 184 |
|
|
中文摘要:针对BP神经网络作为人脸识别分类器具有的收敛速度慢、易陷入局部极小等缺点,提出利用改进的粒子群优化算法(PSO)改善BP网络训练的方法,建立一种基于改进的PSO BP神经网络,更合理有效地确定神经网络的连接权值和阈值,将其应用到人脸识别系统中的分类环节中,并与单独使用BP神经网络分类的结果相比较,实验表明,该方法识别速度快,识别效果更好。 |
中文关键词:人脸识别 奇异值分解 BP神经网络 粒子群优化算法 |
|
Face Recognition Classifier Based on PSO and Neural Network |
|
|
Abstract:Because BP neural network for face recognition classifier has slow convergence and easy to fall into the local minimum, using particle swarm optimization (PSO) to improve the BP network training method, establishing an algorithm based on the improved PSO BP neural network, which can more reasonable and effectively to determine the neural network connection weights and thresholds, applying this method to the classification of the face recognition system, and compared results with using the BP neural network classification only, experiment shows that the recognition speed is quicker and recognition result is better. |
keywords:face recognition singular value decomposition BP neural network particle swarm optimization |
查看全文 查看/发表评论 下载pdf阅读器 |