图像识别的原理（【专知荟萃19】图像识别Image Recognition知识资料全集（入门/进阶/论文/综述/视频/专家，附查看））

《php基础教程》

点击上方“专知”关注获取专业AI知识!

【导读】主题荟萃知识是专知的核心功能之一，为用户提供AI领域系统性的知识学习服务主题荟萃为用户提供全网关于该主题的精华（Awesome）知识资料资源网收录整理，使得AI从业者便捷学习和解决工作问题！在专知人工智能主题知识树。

基础上，主题荟萃由专业人工编辑和算法工具辅助协作完成，并保持动态更新！另外欢迎对此创作主题荟萃感兴趣的同学，请加入我们专知AI资源网创作者计划，共创共赢！ 今天专知为大家呈送第十八篇专知主题荟萃-图像识别知识资料大全集荟萃

（入门/进阶/综述/视频/代码/专家等），请大家查看！专知访问www.zhuanzhi.ai,  或关注微信公资源网众号后台回复" 专知"进入专知，搜索主题“图像识别”查看此外，我们也提供该文网页桌面手机端（www.zhuanzhi.ai）完整访问，可直接点击访问收录链接地址，以及pdf版下载链接，请文章末尾查看。资源网

！此为初始版本，请大家指正补充，欢迎在后台留言！欢迎大家分享转发~图像识别 Image Recognition 专知荟萃入门学习进阶文章Imagenet result20132014201520162资源网017

综述Tutorial视频教程Datasets代码领域专家入门学习如何识别图像边缘？  阮一峰[http://www.ruanyifeng.com/blog/2016/07/edge-recogn资源网ition.html]

CS231n课程笔记翻译：图像分类笔记[https://zhuanlan.zhihu.com/p/20894041][http://cs231n.github.io/classi资源网fication/]深度学习、图像分类入门，从VGG16卷积神经网络开始 [http://blog.csdn.net/Errors_In_Life/article/details/65950699\]资源网

The 9 Deep Learning Papers You Need To Know About (Understanding CNNs Part 3) 翻译[http://blog.csdn.ne资源网t/darkprince120/article/details/53024714]

深度学习框架Caffe图片分类教程[http://blog.csdn.net/qq_31258245/article/资源网details/75093380\]MobileNet教程：用TensorFlow搭建在手机上运行的图像分类器

[https://zhuanlan.zhihu.com/p/28199892]图像验证码和资源网大规模图像识别技术[http://www.infoq.com/cn/articles/CAPTCHA-image-recognition]

卷积神经网络如何进行图像识别[http://www.infoq资源网.com/cn/articles/convolutional-neural-networks-image-recognition]图像识别与验证码

[https://zhuanlan.zhihu.com资源网/securityCode]图像识别(知乎话题) - [https://www.zhihu.com/topic/19588774/top-answers?page=1]

进阶文章Imagenet res资源网ultMicrosoft (Deep Residual Learning] [http://arxiv.org/pdf/1512.03385v1.pdfSlide](http://image-net.资源网org/challenges/talks/ilsvrc2015_deep_residual_learning_kaiminghe.pdf]][[] Kaiming He, Xiangyu Zhang,资源网 Shaoqing Ren, Jian Sun, Deep Residual Learning for Image Recognition, arXiv:1512.03385.

Microsoft (P资源网ReLu/Weight Initialization] [http://arxiv.org/pdf/1502.01852] Kaiming He, Xiangyu Zhang, Shaoqing Re资源网n, Jian Sun, Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classifica资源网tion, arXiv:1502.01852.

Batch Normalization [http://arxiv.org/pdf/1502.03167] Sergey Ioffe, Christian资源网 Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shi资源网ft, arXiv:1502.03167.

GoogLeNet [http://arxiv.org/pdf/1409.4842] Christian Szegedy, Wei Liu, Yangqing资源网 Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabin资源网ovich, CVPR, 2015.

VGG-Net [http://www.robots.ox.ac.uk/~vgg/research/very_deep/] [http://arxiv.org/pd资源网f/1409.1556] Karen Simonyan and Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale V资源网isual Recognition, ICLR, 2015.

AlexNet [http://papers.nips.cc/book/advances-in-neural-information-pro资源网cessing-systems-25-2012] Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, ImageNet Classificatio资源网n with Deep Convolutional Neural Networks, NIPS, 2012.

2013DeCAF: A Deep Convolutional Activation Fea资源网ture for Generic Visual Recognition. Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Z资源网hang, Eric Tzeng, Trevor Darrell

[http://arxiv.org/abs/1310.1531]2014CNN Features off-the-shelf: an A资源网stounding Baseline for Recognition CVPR 2014

[http://arxiv.org/abs/1403.6382]Deeply learned face repr资源网esentations are sparse, selective, and robust

[http://arxiv.org/abs/1412.1265]Deep Learning Face Repr资源网esentation by Joint Identification-Verification

- [https://arxiv.org/abs/1406.4773]Deep Learning Face资源网 Representation from Predicting 10,000 Classes. intro: CVPR 2014

[http://mmlab.ie.cuhk.edu.hk/pdf/YiS资源网un_CVPR14.pdf]Multiple Object Recognition with Visual Attention**

[https://arxiv.org/abs/1412.7755]20资源网15HD-CNN: Hierarchical Deep Convolutional Neural Network for Image Classification intro: ICCV 2015

[h资源网ttps://arxiv.org/abs/1410.0736]Delving Deep into Rectifiers: Surpassing Human-Level Performance on I资源网mageNet Classification. ImageNet top-5 error: 4.94%

[http://arxiv.org/abs/1502.01852]Multi-attribute 资源网Learning for Pedestrian Attribute Recognition in Surveillance Scenarios

[http://ieeexplore.ieee.org/d资源网ocument/7486476/]FaceNet: A Unified Embedding for Face Recognition and Clustering

[http://arxiv.org/a资源网bs/1503.03832]2016Humans and deep networks largely agree on which kinds of variation make object rec资源网ognition harder**

[http://arxiv.org/abs/1604.06486]FusionNet: 3D Object Classification Using Multiple资源网 Data Representations

[https://arxiv.org/abs/1607.05695]Deep FisherNet for Object Classification**[ht资源网tp://arxiv.org/abs/1608.00182]

Factorized Bilinear Models for Image Recognition**[https://arxiv.org/a资源网bs/1611.05709]Hyperspectral CNN Classification with Limited Training Samples**

[https://arxiv.org/abs资源网/1611.09007]The More You Know: Using Knowledge Graphs for Image Classification**

[https://arxiv.org/a资源网bs/1612.04844]MaxMin Convolutional Neural Networks for Image Classification**[http://webia.lip6.fr/~资源网thomen/papers/Blot_ICIP_2016.pdf]

Cost-Effective Active Learning for Deep Image Classification. TCSVT资源网 2016.[https://arxiv.org/abs/1701.03551]

DeepFood: Deep Learning-Based Food Image Recognition for Com资源网puter-Aided Dietary Assessment[http://arxiv.org/abs/1606.05675]

2017Deep Collaborative Learning for V资源网isual Recognition[https://www.arxiv.org/abs/1703.01229]Bilinear CNN Models for Fine-grained Visual R资源网ecognition

[http://vis-www.cs.umass.edu/bcnn/]Multiple Instance Learning Convolutional Neural Network资源网s for Object Recognition**

[https://arxiv.org/abs/1610.03155]B-CNN: Branch Convolutional Neural Netwo资源网rk for Hierarchical Classification

[https://arxiv.org/abs/1709.09890](Why Do Deep Neural Networks Sti资源网ll Not Recognize These Images?: A Qualitative Analysis on Failure Cases of ImageNet Classification

[h资源网ttps://arxiv.org/abs/1709.03439]Deep Mixture of Diverse Experts for Large-Scale Visual Recognition[h资源网ttps://arxiv.org/abs/1706.07901]

Sunrise or Sunset: Selective Comparison Learning for Subtle Attribut资源网e Recognition[https://arxiv.org/abs/1707.06335]

Convolutional Low-Resolution Fine-Grained Classificat资源网ion[https://arxiv.org/abs/1703.05393]综述A Review of Image Recognition with Deep Convolutional Neural 资源网Network

[https://link.springer.com/chapter/10.1007/978-3-319-63309-1_7\]Review on Image Recognition[h资源网ttp://pnrsolution.org/Datacenter/Vol3/Issue2/186.pdf]

深度学习在图像识别中的研究进展与展望[https://piazza-resources.s3.资源网amazonaws.com/i48o74a0lqu0/i4fcg2o44k63n6/deep_recognition.pdf?AWSAccessKeyId=AKIAIEDNRLJ4AZKBW6HA&E资源网xpires=1509460321&Signature=DxZ8LrEEStKQrKESDufA7i3qIGA%3D\]

图像物体分类与检测算法综述 黄凯奇 任伟强 谭铁牛 [http://cjc.ic资源网t.ac.cn/online/cre/hkq-2014526115913.pdf]Book Chapter - Objecter Recognition

[http://www.cse.usf.edu/资源网~r1k/MachineVisionBook/MachineVision.files/MachineVision_Chapter15.pdf\]Tutorial

CVPR tutorial : Larg资源网e-Scale Visual Recognition[http://www.europe.naverlabs.com/Research/Computer-Vision/Highlights/CVPR-资源网tutorial-Large-Scale-Visual-Recognition]

Image Recognition with Tensorflow[https://www.tensorflow.org资源网/tutorials/image_recognition\]Visual Object Recognition Tutorial by Bastian Leibe & Kristen Grauman

[资源网https://www.google.com.au/url?sa=t&rct=j&q=&esrc=s&source=web&cd=32&cad=rja&uact=8&ved=0ahUKEwiWrq3W资源网5JrXAhWFLpQKHQPuCcI4HhAWCC8wAQ&url=http%3A%2F%2Fz.cs.utexas.edu%2Fusers%2Fpiyushk%2Fcourses%2Fspr12%资源网2Fslides%2FAAAI-tutorial-2.ppt&usg=AOvVaw3tQkyK0zW7nZ28LhrGzCUC]

视频教程CS231n: Convolutional Neural Net资源网works for Visual Recognition[http://cs231n.stanford.edu/]李飞飞: 我们怎么教计算机理解图片？

- [https://www.youtube.co资源网m/watch?v=40riCqvRoMs]DatasetsMNIST: handwritten digits (http://yann.lecun.com/exdb/mnist/)

NIST: sim资源网ilar to MNIST, but largerPerturbed NIST: a dataset developed in Yoshua’s class (NIST with tons of de资源网formations)

CIFAR10 / CIFAR100: 32×32 natural image dataset with 10/100 categories ( http://www.cs.ut资源网oronto.ca/~kriz/cifar.html)

Caltech 101: pictures of objects belonging to 101 categories (http://www.资源网vision.caltech.edu/Image_Datasets/Caltech101/)

Caltech 256: pictures of objects belonging to 256 cate资源网gories (http://www.vision.caltech.edu/Image_Datasets/Caltech256/)

Caltech Silhouettes: 28×28 binary i资源网mages contains silhouettes of the Caltech 101 datasetSTL-10 dataset is an image recognition dataset 资源网for developing unsupervised feature learning, deep learning, self-taught learning algorithms. It is 资源网inspired by the CIFAR-10 dataset but with some modifications. http://www.stanford.edu/~acoates//stl1资源网0/

The Street View House Numbers (SVHN) Dataset – http://ufldl.stanford.edu/housenumbers/NORB: binocu资源网lar images of toy figurines under various illumination and pose (http://www.cs.nyu.edu/~ylclab/data/资源网norb-v1.0/)

Imagenet: image database organized according to the WordNethierarchy (http://www.image-ne资源网t.org/)Pascal VOC: various object recognition challenges (http://pascallin.ecs.soton.ac.uk/challenge资源网s/VOC/)

Labelme: A large dataset of annotated images, http://labelme.csail.mit.edu/Release3.0/browser资源网Tools/php/dataset.php

COIL 20: different objects imaged at every angle in a 360 rotation(http://www.c资源网s.columbia.edu/CAVE/software/softlib/coil-20.php)

COIL100: different objects imaged at every angle in资源网 a 360 rotation (http://www1.cs.columbia.edu/CAVE/software/softlib/coil-100.php)

代码AlexNet [https://g资源网ithub.com/BVLC/caffe/tree/master/models/bvlc_alexnet\]ZFnet [https://github.com/rainer85ah/Papers2Co资源网de/tree/master/ZFNet]

VGG[https://github.com/machrisaa/tensorflow-vgg]GoogLeNet [https://github.com/B资源网VLC/caffe/tree/master/models/bvlc_googlenet\]

ResNet[https://github.com/KaimingHe/deep-residual-netwo资源网rks]HD-CNN[https://sites.google.com/site/homepagezhichengyan/home/hdcnn/code]

Factorized Bilinear Mod资源网els for Image Recognition[https://github.com/lyttonhao/Factorized-Bilinear-Network]

MaxMin Convolutio资源网nal Neural Networks for Image Classification[https://github.com/karandesai-96/maxmin-cnn]

Multiple Ob资源网ject Recognition with Visual Attention[https://github.com/jrbtaylor/visual-attention]Learning Spatia资源网l Regularization with Image-level Supervisions for Multi-label Image Classification

[https://github.c资源网om/zhufengx/SRN_multilabel/\]Deep Learning Face Representation from Predicting 10,000 Classes

[https:资源网//github.com/stdcoutzyx/DeepID_FaceClassify\]FaceNet: A Unified Embedding for Face Recognition and C资源网lustering

[https://github.com/davidsandberg/facenet]DeepFood: Deep Learning-Based Food Image Recognit资源网ion for Computer-Aided Dietary Assessment

[https://github.com/deercoder/DeepFood]领域专家Yangqing Jia[htt资源网p://daggerfs.com/]Ross Girshick[http://www.rossgirshick.info/]

Xiaodi Hou[http://www.houxiaodi.com/]K资源网aiming He[http://kaiminghe.com/]Jian Sun[http://www.jiansun.org/]

Xiaoou Tang[https://www.ie.cuhk.edu资源网.hk/people/xotang.shtml]Shuicheng Yan[https://www.ece.nus.edu.sg/stfpage/eleyans/]

初步版本，水平有限，有错误或者不完善资源网的地方，欢迎大家提建议和补充（到专知网站www.zhuanzhi.ai 主题下评论），会一直保持更新，敬请关注http://www.zhuanzhi.ai 和关注专知公众号，获取最新AI相关知识。

欢迎资源网转发分享专业AI知识！特别提示-专知目标跟踪主题：请PC登录www.zhuanzhi.ai或者点击阅读原文，注册登录，顶端搜索“目标跟踪” 主题，查看评论获得专知荟萃全集知识等资料，直接PC端访问体验资源网更佳！如下图所示~

此外，请关注专知公众号（扫一扫最下面专知二维码，或者点击上方蓝色专知），后台回复“图像识别”或者“Image” 就可以在手机端获取专知图像识别资料查看链接地址，直接打开荟萃资料的链接资源网地址~~请扫描专知小助手，加入专知人工智能群交流~

往期专知荟萃知识资料全集获取（关注本公众号-专知，获取下载链接），请查看：【专知荟萃01】深度学习知识资料大全集（入门/进阶/论文/代码/数据/综述/资源网领域专家等）（附pdf下载）【专知荟萃02】自然语言处理NLP知识资料大全集（入门/进阶/论文/Toolkit/数据/综述/专家等）（附pdf下载）

【专知荟萃03】知识图谱KG知识资料全集（入门/进阶资源网/论文/代码/数据/综述/专家等）（附pdf下载）【专知荟萃04】自动问答QA知识资料全集（入门/进阶/论文/代码/数据/综述/专家等）（附pdf下载）

【专知荟萃05】聊天机器人Chatbot知识资料资源网全集（入门/进阶/论文/软件/数据/专家等）(附pdf下载)【专知荟萃06】计算机视觉CV知识资料大全集（入门/进阶/论文/课程/会议/专家等）(附pdf下载)

【专知荟萃07】自动文摘AS知识资料全集资源网（入门/进阶/代码/数据/专家等）(附pdf下载)【专知荟萃08】图像描述生成Image Caption知识资料全集（入门/进阶/论文/综述/视频/专家等）【专知荟萃09】目标检测知识资料全集（入门/资源网进阶/论文/综述/视频/代码等）

【专知荟萃10】推荐系统RS知识资料全集（入门/进阶/论文/综述/视频/代码等）【专知荟萃11】GAN生成式对抗网络知识资料全集（理论/报告/教程/综述/代码等）【专知资源网荟萃12】信息检索 Information Retrieval 知识资料全集（入门/进阶/综述/代码/专家，附PDF下载）

【专知荟萃13】工业学术界用户画像 User Profile 实用知识资料全集资源网（入门/进阶/竞赛/论文/PPT，附PDF下载）【专知荟萃14】机器翻译 Machine Translation知识资料全集（入门/进阶/综述/视频/代码/专家，附PDF下载）

【专知荟萃15】图像检索资源网Image Retrieval知识资料全集（入门/进阶/综述/视频/代码/专家，附PDF下载）【专知荟萃16】主题模型Topic Model知识资料全集（基础/进阶/论文/综述/代码/专家，附PDF下资源网载）

【专知荟萃17】情感分析Sentiment Analysis 知识资料全集（入门/进阶/论文/综述/视频/专家，附查看）【专知荟萃18】目标跟踪Object Tracking知识资料全集（入门/进资源网阶/论文/综述/视频/专家，附查看）

-END-欢迎使用专知专知，一个新的认知方式！专注在人工智能领域为AI从业者提供专业可信的知识分发服务, 包括主题定制、主题链路、搜索发现等服务，帮你又好又快找到所资源网需知识使用方法>>访问www.zhuanzhi.ai。

, 或点击文章下方“阅读原文”即可访问专知中国科学院自动化研究所专知团队@2017 专知专 · 知关注我们的公众号，获取最新关于专知以及人工智能的资源网资讯、技术、算法、深度干货等内容扫一扫下方关注我们的微信公众号。

点击“阅读原文”，使用专知！

亲爱的读者们，感谢您花时间阅读本文。如果您对本文有任何疑问或建议，请随时联系我。我非常乐意与您交流。