>Here's my recommendation of reading list for beginners in Computer Vision area. ## General Tutorials: - [Computer Vision: Models, Learning, and Inference](http://www.computervisionmodels.com/), ([Amazon](http://www.amazon.com/Computer-Vision-Models-Learning-Inference/dp/1107011795/ref=sr_1_1?s=books&ie=UTF8&qid=1334662414&sr=1-1)), by Simon J.D. Prince. > Best tutorial ever for beginners in CV area. Prof. Prince provides free e-print file and all the algorithms with elegant matlab implementations on his website. You can even find a lot of slides and faq on it. Enjoy! >**Computer Vision: A Modern Approach, 2nd Edition** by David A. Forsyth is also excellent but seems relatively advanced and not that strongly related to the trending machine learning methods. >**Computer Vision: Algorithms and Applications** by Richard Szeliski is a good manual for reference but seems too fragmental thus not appropriate for beginners. You can get some whole pictures from this book, then quickly jump to CVMLI to get more machine learning based ideas. - [Digital Image Processing, 3rd Edition](http://www.imageprocessingplace.com/DIP-3E/dip3e_main_page.htm), ([Amazon](http://www.amazon.com/Digital-Image-Processing-3rd-Edition/dp/013168728X)), by Rafael C. Gonzalez. >Classical textbook from which you could learn more about the image pre-processing for computer vision. <br> ## Application Tutorials: - [Digital Image Processing Using MATLAB, 2nd edition](http://www.imageprocessingplace.com/DIPUM-2E/dipum2e_main_page.htm), ([Amazon](http://www.amazon.com/Digital-Image-Processing-Using-MATLAB/dp/0982085400)), by Rafael C. Gonzalez. > You could find corresponding Matlab implementations based on the above theory-oriented version. - [OpenCV 2 Computer Vision Application Programming Cookbook](http://www.laganiere.name/opencvCookbook/), ([Amazon](http://www.amazon.com/OpenCV-Computer-Application-Programming-Cookbook/dp/1849513244)), by Robert Laganiere. > You might also be interested in *Mastering OpenCV with Practical Computer Vision Projects*, by Daniel Baggio, if you want to build some fancy projects based on Android, iOS and Microsoft Kinect. <br> ## Math Review: - [Linear Algebra Done Right](http://linear.axler.net/), ([Amazon](http://www.amazon.com/Linear-Algebra-Right-Undergraduate-Mathematics/dp/0387982582)), by Sheldon Axler. > The [Open Course](http://www-math.mit.edu/~gs/) from Prof. Gilbert Strang is also a good supplementary material for self-study. - [Probability and Stochastic Processes](http://www.wiley.com/WileyCDA/WileyTitle/productCd-EHEP000391.html), ([Amazon](http://www.amazon.com/Probability-Stochastic-Processes-Introduction-Electrical/dp/0471272140)), by Roy D. Yates. > As it claims, a friendly introduction for Electrical and Computer Engineers. <br> ## MOOC on Coursera: - [Image and video processing](https://class.coursera.org/images-002), by Guillermo Sapiro. >Beginner friendly. - [Machine Learning](https://class.coursera.org/ml-005), by Andrew Ng. >Great course, actually every beginner should take it. <br> ## Courses and Notes: - [CS231n: Convolutional Neural Networks for Visual Recognition](http://cs231n.stanford.edu/), by Fei-Fei Li in Stanford University. >Great course for basic ideas of Deep Learning. - [VGG Convolutional Neural Networks Practical](http://www.robots.ox.ac.uk/~vgg/practicals/cnn/), and [More Practicals](http://www.robots.ox.ac.uk/~vgg/practicals/overview/index.html), by Andrea Vedaldi and Andrew Zisserman. >Useful practical for Deep Learning based on Matlab. <br> ## Extra Machine Learning Tutorial: - [Machine Learning: a Probabilistic Perspective](http://www.cs.ubc.ca/~murphyk/MLbook/), ([Amazon](http://www.amazon.com/Machine-Learning-Probabilistic-Perspective-Computation/dp/0262018020)), by Kevin Patrick Murphy. > More suitable for beginners than PRML from Prof. Bishop. It also provides all the [Matlab implementations](https://github.com/probml/pmtk3) from which you will benifit a lot. - [Machine Learning in Action](http://www.manning.com/pharrington/), ([Amazon](http://www.amazon.com/Machine-Learning-Action-Peter-Harrington/dp/1617290181)), Peter Harrington. > Interesting machine learning tutorial based on Python. You can implement some tiny real systems quickly and be happy.