基于深度卷积神经网络的人脸识别的研究与应用-软件工程专业论文.docxVIP

优秀毕业论文 精品参考文献资料 AbstractFace Abstract Face recognition is one of the most studied topics in computer vision literature， not only because of the challenging nature of face as an object，but also due to the countless applications that require the application of face recognition as a first step．In recent years，with the wide spread use of smartphone，millions of photos are uploaded everyday to the social networks such as Weibo，WeChat and SO on，which include many faces．Deep learning is an important breakthrough in artificial intelligence of the past ten years，it simulates the hierarchical structure of human brain，processing data from lower level to higher level，and gradually composing more and more semantic concepts． This dissertation focuses on face detection and recognition based on deep learning． Firstly,the dissertation introduces the。background and the importance of the research，then gives an overview of the concept of face recognition，artificial neural networks and convolutional neural networks(CNN)．Secondly，the method of face detection and recognition based on deep learning is described in detail，including DDFD and VGG-Face．The structure，model，algorithm and the training of deep convolutional neural networks are illustrated．Fine-tuning the deep CNN model makes it more appropriate to our practical application．By visualizing the feature extraction ofthe deep CNN，we understand it easier and make it more transparency．Finally,the operation process of the practical application and the experimental results are showed． Experimental results show that the method based on deep learning for face detection and face recognition is remarkable，which Can improve the performance of face detection and recognition and．is robust to face poses，lighting and occlusions． Key Words：Face Recognition；Convolutional Neural Networks；Deep Learning II 万方数据 目录目 目录 目 录 第一章绪论 。1 1．1研究背景与意义 ．1 1．2国内外研究现状 ．3 1．3论文主要研究内容 。4 1．4论文组织结构 ．．5 第二章相关理论介绍 。6 2．1人脸识别 。6 2．2人工神经网络 7 2．2．1激发函数 7 2．2．2神经网络 8 2．3卷积神经