摘 要：人脸识别可以靠很多技术手段来实现，而本文则主要探讨了通过深度机器学习卷积神经网络来实现人脸识别，人脸是图像识别中相对复杂的识别对象，提高识别精度相对困难，通过卷积神经网络可以有效地提高人脸识别精度，使其达到一个比较满意的程度。本文重点论述卷积神经网络进行人脸识别的过程与方法，介绍了如何通过改进卷积神经网络来提高识别精度。 为从事图像识别的研究者提供了一些可借鉴的研究思路。
关键词：深度机器学习；卷积神经网络；人脸识别
中图分类号：TP391.41；TP183 文献标识码：A 文章编号：2096-4706（2018）10-0102-03
Face Recognition Method Base on Convolution Neural Network
LU Hong
（Beijing Information Technology College，Beijing 100018，China）
Abstract：Face recognition can be realized by many technical means. In this paper，we mainly discuss the realization of facerecognition by deep machine learning convolution neural network. Face is a relatively complex recognition object in image recognition. Itis difficult to improve recognition accuracy. The face recognition can be effectively improved by convolution neural network. Accuracy isachieved to a satisfactory degree. This paper focuses on the process and method of face recognition based on convolution neural network，and introduces how to improve the recognition accuracy by improving convolution neural network. It provides some useful research ideasfor researchers engaged in image recognition.
Keyword：deep machine leaning；convolution neural network；face recognition
参考文献：
[1] Xiaocheng Luo，Ruihan Shen，Jian Hu，et al.A DeepConvolution Neural Network Model for Vehicle Recognition and FaceRecognition [J].Procedia Computer Science，2017（107）：715-720.
[2] 田壮壮，占荣辉，胡杰民，等. 基于卷积神经网络的SAR图像目标识别研究 [J]. 雷达学报，2016，5（3）：320-325.
[3] Sanjana Majumder，Devendran B.Face Recogniyion UsingLifting based DWT and Local Binary Pattern [J].Internatinal ResearchJournal of Engineering and Technology，2015（6）：830-834.
[4] Haichao Zhang，Yanning Zhang，Thomas S. Huang.Pose-robust face recognition via sparse representation [J].PatternRecognition，2013，46（5）：1511-1521.
作者简介：陆红（1963-），男，北京人，所长，副教授，硕士，研究方向：大数据、人工智能。