For those interested in learning vision from a machine learning perspective I would suggest "Computer Vision: Models, Learning, and Inference" [1]. Szelinski's book is also great but gives a more classical overview of computer vision.<p>[1] <a href="http://www.computervisionmodels.com/" rel="nofollow">http://www.computervisionmodels.com/</a>
Most of my attempts at getting into CV fail because my knowledge of Maths is incredibly rusty. I did Maths up to university level, but haven't used it since.<p>Are there any good courses / books or other resources that would specifically help at getting up to speed with the maths knowledge required to understand a book like this?
Aude Olivia's course at MIT is also a good resource:<p>6.869: Advances in Computer Vision (Fall 2015)<p><a href="http://6.869.csail.mit.edu/fa15/index.html" rel="nofollow">http://6.869.csail.mit.edu/fa15/index.html</a><p>Or just jump right into the deep end with OpenCV:<p><a href="http://opencv.org/" rel="nofollow">http://opencv.org/</a>
The only one risky thing is that in computer vision right now things change each 6 months. So, one will never know which techniques are still state of the art, and which were outclassed by some ConvNets 4 years ago.
This is maybe the best textbook on the basics of image processing, computer vision and computational photography. The author is from MS Research and they do know this stuff.