Hacker News Comments on
Learning OpenCV: Computer Vision with the OpenCV Library
·
2
HN comments
- This course is unranked · view top recommended courses
Hacker News Stories and Comments
All the comments and stories posted to Hacker News that reference this book.It's rather problematic. I'd start with sciweavers ( http://www.sciweavers.org/ ), since they have a lot of readable, new papers, but the vast majority of the references are fairly math-heavy and somewhat removed from the applications. A very good resource is the Oreilly book ( http://www.amazon.com/Learning-OpenCV-Computer-Vision-Librar... ) on OpenCV, and the OpenCV source code ( https://code.ros.org/svn/opencv/trunk/opencv/ ). Imagemagick source ( http://www.imagemagick.org/script/index.php ) is also amazing for learning how basic operations are done in code.Learning to read the style of older research papers and to pull applications out of them is very useful though. It's surprising how often something seemingly overacademized and useless, when translated into code, turns out to be very useful and smart.
⬐ weaksauceThanks for the links! The first one looks like it has a lot of good info.I guess I should clarify that I am not afraid of the math heavy papers (image processing is by nature math heavy) but what I meant by overly academic is proving something just to write a paper. For instance sometimes they write a paper on a solved problem to take the overall asymptotic running time down a bit but increase the constant factor and code complexity by a large amount. Think quickSelect vs Deterministic select. Quickselect only breaks down if every random pick of the pivot is the worst one whereas the deterministic select guarantees O(n) but with a constant in the 10's (I could be off on this number but it's high)
⬐ oashHi, I would like to thank you too about the useful links you posted. I like to add also http://citeseer.ist.psu.edu/. It is a huge library of pdfs. However, what i really liked about your first link i.e., Sciweavers.org is that they enable you to browse the output of conference papers visually using different types of cool 3D widgets. Therefore, you do not have to read every paper title or abstract to know what the paper is about. This could save us significant time while trying to find related work of a given conference. For example, see their widget in action of ICIP-2009 or CVPR-2009 http://www.sciweavers.org/gallery/wall.html?u=cvpr-2009 http://www.sciweavers.org/gallery/wall.html?u=icip-2009Also, they sort conference papers using different criteria (most featured, views, most impact, etc) and hence can quickly find good papers to read or implement.
O'Reilly "Learning OpenCV" is very well written and covers a wide range of topics.http://www.amazon.com/Learning-OpenCV-Computer-Vision-Librar...