基于GA-BP神经网络的人脸检测  

Face Detection Based on GA-BP Neural Network

作　　者：焦利宝[1] 彭龑[1] 陈春兰[1] 

机构地区：[1]四川理工学院,四川自贡643000

出　　处：《现代电子技术》2008年第16期154-156,共3页Modern Electronics Technique

摘　　要：传统的BP神经网络算法收敛过慢、局部收敛不理想,影响其工作性能。针对以上不足以及人脸图像数据大等问题。提出GA-BP神经网络对人脸图像进行检测的新方法:将遗传学习算法和误差反向传播算法相结合的混合算法来训练前馈人工神经网络,使网络收敛速度加快和避免局部极小。通过实验表明该网络不仅收敛速度快,而且易达到最优解。证明该网络对人脸图像检测具有高的检测精度。The constringency of the conventional BP neural network algorithm is too slow and local constringency is not ideal,which effect working performance. The lack above and face image data too big, a new method that the face detection method based on GA-BP neural network is introduced in this paper. Making the Genetic Algorithm （GA） search algorithm is used to train the network with updating the weights to minimize the error between the network output and the desired output. Then the Back-Propagation （BP） algorithm is used to further train the artificial neural network used for face detection. The experiment indicate This network convergence rate is not only quick,moreover easy to achieve the optimal solution. This net- work has the high detection precision to the face image detection.

关 键 词：人脸检测 BP网络 遗传算法 GA-BP网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]