基于BP神经网络的人脸方向识别

Face Direction Recognition Based on BP Neural Network

摘要: 人脸识别具有重要的实际应用价值，已成为计算机智能识别领域的热门研究课题。传统的人脸识别系统需要人的正面进行识别，而且仅对正面进行识别，因此在识别效率和准确率上存在很大缺陷。本文提出了基于BP神经网络的人脸方向识别方法，并利用MATLAB2014平台进行了人脸方向识别试验。统计试验结果表明，该方法预测误差很小，结果接近真实值。利用本文所提出的方法，可以从多个方向进行人脸识别，从而提高了人脸识别的效率和正确率。

Abstract: Face recognition has important practical application value and has become a hot research topic in the field of computer intelligent identification. The traditional face recognition system needs to be recognized by the front of people, and only the front face is recognized. Therefore, there are many defects in the recognition efficiency and accuracy. In this paper, a face direction recognition method based on BP neural network is proposed and MATLAB 2014 platform is used to detect the direction of face. It shows that the forecasting error is very small and the results are closer to the true value. By using the method proposed in this paper, face recognition can be carried out in several directions, which improves the efficiency and accuracy of face recognition.