深度卷积神经网络在计算机视觉中的应用研究综述.docVIP

深度卷积神经网络在计算机视觉中的应用研究综述 卢宏涛 张秦川 上海交通大学计算机科学与工程系 X 关注成功！ 加关注后您将方便地在 我的关注中得到本文献的被引频次变化的通知！ 新浪微博 腾讯微博 人人网 开心网 豆瓣网 网易微博 摘????要： 随着大数据时代的到来,含更多隐含层的深度卷积神经网络(Convolutional neural networks,CNNs)具有更复杂的网络结构,与传统机器学习方法相比具有更强大的特征学习和特征表达能力。使用深度学习算法训练的卷积神经网络模型自提出以来在计算机视觉领域的多个大规模识别任务上取得了令人瞩目的成绩。本文首先简要介绍深度学习和卷积神经网络的兴起与发展,概述卷积神经网络的基本模型结构、卷积特征提取和池化操作。然后综述了基于深度学习的卷积神经网络模型在图像分类、物体检测、姿态估计、图像分割和人脸识别等多个计算机视觉应用领域中的研究现状和发展趋势,主要从典型的网络结构的构建、训练方法和性能表现3个方面进行介绍。最后对目前研究中存在的一些问题进行简要的总结和讨论,并展望未来发展的新方向。 关键词： 深度学习; 卷积神经网络; 图像识别; 目标检测; 计算机视觉; 作者简介：卢宏涛(1967-),男,教授,博士生导师,研究方向:机器学习、模式识别、计算机视觉和图像分析与处理,E-mail:htlu@。 作者简介：张秦川(1993-),男,博士研究生,研究方向:深度学习、图像分类和目标检测。 收稿日期：2015-12-10 基金：国家自然科学基金资助项目 Applications of Deep Convolutional Neural Network in Computer Vision Lu Hongtao Zhang Qinchuan Department of Computer Science and Engineering,Shanghai Jiao Tong University; Abstract： Deep learning has recently achieved breakthrough progress in speech recognition and image recognition.With the advent of big data era,deep convolutional neural networks with more hidden layers and more complex architectures have more powerful ability of feature learning and feature representation.Convolutional neural network models trained by deep learning algorithm have attained remarkable performance in many large scale recognition tasks of computer vision since they are presented.In this paper,the arising and development of deep learning and convolutional neural network are briefly introduced,with emphasis on the basic structure of convolutional neural network as well as feature extraction using convolution and pooling operations.The current research status and trend of convolutional neural networks based on deep learning and their applications in computer vision are reviewed,such as image classification,object detection,pose estimation,image segmentation and face detection etc.Some related works are introduced from the following three aspects,i.e.,construction of typical network structures,training methods and p