OpenCV视觉处理核心课程
观看链接:https://www.bilibili.com/video/av29500928?from=search&seid=4700863932001463989
第一讲 工欲善其事必先利其器——图像处理基础
Open Libraries/projects:
OpenCV:http://opencv.org/
HALCON:http://www.halcon.com/
下载——三个链接:
1)http://opencv.org/ (最新发布)
2)https://sourceforge.net/projects/opencvlibrary/ (File文件夹下)
两个开源项目:
1)Open BR:http://openbiometrics.org/
2)EasyBR:https://gitee.com/easypr/EasyPR
第二讲 初探计算机视觉
Image Watch:
1、Image Watch 的下载链接:https://marketplace.visualstudio.com/items?itemName=VisualCPPTeam.ImageWatch
2、OpenCV关于Image Watch的介绍页面 链接:https://opencv.org/image-debugger-plug-in-for-visual-studio/
3、OpenCV2.4 在线文档关于Image Watch 的介绍文档:https://docs.opencv.org/2.4/doc/tutorials/introduction/windows_visual_studio_image_watch/windows_visual_studio_image_watch.html#windows-visual-studio-image-watch
4、更详细的信息参见Image Watch的官方 网站:https://www.microsoft.com/en-us/research/group/interactive-visual-media/?from=http%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fum%2Fredmond%2Fgroups%2Fivm%2Fimagewatchhelp%2Fimagewatchhelp.htm
view ——>other windows ——> Image watch
OpenCV推荐资料:
手册:http://docs.opencv.org/
教程: http://docs.opencv.org/doc/tutorials/tutorials.html
进阶:https://github.com/opencv/opencv/wiki
项目:
手写字符识别 MNIST database of handwritten digits :http://yann.lecun.com/exdb/mnist/
Python基础教程:https://www.runoob.com/python/python-tutorial.html
第三讲 空域图像处理的洪荒之力
Template matching (eg. DIC/DSCM):http://docs.opencv.org/2.4/doc/tutorials/imgproc/histograms/template_matching/template_matching.html
第四讲:机器视觉中的特征提取与描述
KAZE链接:OpenCV学习笔记(27)KAZE 算法原理与源码分析(一)非线性扩散滤波
第五讲:坐标变换与视觉测量
Calibration in OpenCV推荐:1)https://docs.opencv.org/2.4/doc/tutorials/calib3d/camera_calibration/camera_calibration.html
2)《Learning OpenCV》
相机Matlab标定工具箱(理论与原理)问题:http://www.vision.caltech.edu/bouguetj/calib_doc/index.html
下载cmake:http://www.cmake.org/download/
第六讲:深度学习在图像识别中的应用
无
第七讲:图像检索
1)图像特征GIST:MATLAB实现参见:http://people.csail.mit.edu/torralba/code/spatialenvelope/LMgist.m
C版本实现参见:http://lear.inrialpes.fr/src/lear_gist-1.2.tgz
2)深度学习与计算机视觉(11)_基于deep learning的快速图像检索系统a——https://blog.csdn.net/han_xiaoyang/article/details/50856583
项目地址:https://github.com/HanXiaoyang/image_retrieval
3)用VisualSearchSearver和CIFAR-10构建一个简易图像检索系统
(1)https://github.com/AKSHAYUBHAT/VisualSearchServer
(2)http://www.cs.toronto.edu/~kriz/cifar.html ——适合自己的小型电脑
参考任何一个电商图像搜索方法
比如:https://github.com/bobbens/cvpr2016_stylenet
利用以下数据集构建图像检索系统
http://mmlab.ie.cuhk.edu.hk/projects/DeepFashion.html
第八讲:图像标注与问答
Google Research Blog:PAMI paper: https://arxiv.org/pdf/1609.06647v1.pdf
数据库和比赛:1)COCO Captioning Challenge:https://competitions.codalab.org/competitions/3221
2)Evaluation metric:http://mscoco.org/dataset/#download
3)Visual Genome:https://visualgenome.org/
Recurrent Neural Networks (RNN)
• http://www.wildml.com/2015/09/recurrent-neural-networkstutorial-part-1-introduction-to-rnns/
• http://colah.github.io/posts/2015-08-Understanding-LSTMs/
(highly recommended)
• http://deeplearning.net/tutorial/lstm.html
LSTM推荐:http://colah.github.io/posts/2015-08-Understanding-LSTMs/
(译)理解 LSTM 网络 (Understanding LSTM Networks by colah)——https://www.cnblogs.com/mfryf/p/7904017.html
几个最新方法
案例1:neuraltalk2:https://github.com/karpathy/neuraltalk2
此代码入门:http://tylerneylon.com/a/learn-lua/
译Lua 15 分钟快速入门(Learn Lua in 15 Minutes)——https://blog.csdn.net/sdfsdr/article/details/51258680
学习Torch:https://github.com/torch/torch7/wiki/Cheatsheet
2. denseCap:https://github.com/jcjohnson/densecap
值得思考的问题:
【人体姿态】Stacked Hourglass算法详解:https://blog.csdn.net/shenxiaolu1984/article/details/51428392
第九讲:3D计算机视觉
Photos from tourists (photo tourism):http://phototour.cs.washington.edu/
全景拼接:http://hli2020.github.io/2016/02/20/pano/
Three-image 2D-to-3D reconstruction method:http://www.cs.unc.edu/~marc/tutorial/node45.html
资源和参考文献:http://web.stanford.edu/class/cs231a/
第十讲:机器视觉项目实战
NLP之——Word2Vec详解:https://www.cnblogs.com/guoyaohua/p/9240336.html