计算机与现代化Issue(3)：48-51,4.DOI:10.3969/j.issn.1006-2475.2012.03.013
BP网络模型对人脸朝向的识别
Face Direction Recognization Using BP Neural Network Model
常乐 1陆熙 1李佳钰1
作者信息
- 1. 重庆大学城市建设与环境工程学院,重庆400030
- 折叠
摘要
Abstract
In this thesis, a BP neural network model is used to recognize the face direction, which established by simulating the human brain. Specific rules of recognition like brain operation is unclear, but lots of training can make the network effective to recognize the face direction exactly. First extracts the feature vector from each face images with the principal component analytic (PCA) method. Then inputs them to train the neural network that consists of three layers, and the input, hidden and output layers have 8, 17 and 4 neurons respectively. When training, adjusts the parameters to ensure its performance and convergence speed. Lastly, lots of the feature vectors are input to verify the model. By comparing the output and fact, it is found that the model is effective and reliable with an error rate of 6.7% merely.关键词
BP网络模型/人脸朝向/主成分分析Key words
BP neural network/ face direction recognition/ principal component analysis分类
信息技术与安全科学引用本文复制引用
常乐,陆熙,李佳钰..BP网络模型对人脸朝向的识别[J].计算机与现代化,2012,(3):48-51,4.
