Wednesday, March 24th, 2010, 787 days ago
Approaches for hands detection using openCV
As far as in my mind, there are three approaches that people have taken to detect hands using openCV, though not all of them have been tested by myself (a little shame). One is to use accurate HAAR-classifiers to locate and detect gestures which is considered as quite stable way but costing very much. Another is to use adaptive skin detection algorithms combined with motion analysis which seems easier to do than previous one. And the last is to use human skin colour segmentation to detect the contours of hands combined with hand convexity detection to recognise hands’ gestures [please refer to: hand gesture recognition using openCV].
HAAR-classifier database is rarely provided with open source projects. But we found some helpful papers which may give some thoughts of classifier training and test.
About hands database:
Application of classifiers:
Real-time hand tracking using a set of cooperative classifiers based on HAAR-like features
Alternative skin detection based approach gesture recognition through angle space:
Gesture recognition through angle space
POSTS MAY BE OF INTEREST
- A failed example of hand gesture recognition using openCV haartraining classifiers
- Writing a simple hand gesture picture sampler for classifier training
- Happy Chinese New Year of Dragon!!!
- Breaking Asus Xtion pro into parts
- The error of ‘VIDIOC_QUERYMENU: Invalid argument’
- Installing OpenNI for Linux-ARM in Ubuntu Pandaboard
- Merry Xmas and Happy New Year 2012
- A successful way to disable all WordPress’s auto-saves and revisions
- Say goodbye to slow-(Go)daddy
- The sun set
- Backyard’s flowers
- Mapping object positions to mouse coordinates in openCV
- Cherry trees flowering
- New office new start
- An example of detecting object motions using openCV
Wow this is a great resource.. I’m enjoying it.. good article
this post is very usefull thx!
thanks for giving valuable information
cheers
Thanks for all these relevant information !
I would have but a question, though : I’m currently working with a gray-level video, on which I must detect an hand (its contours, basically). So, from your article, I guess only the HAAR-classifier method is usable in that case ? Or do you know other methods that could possibly work in my case?
Thank you, once again !
My opinion is, even in a grey level video, if there is strong contrast between the backgrounds and the hand, then it is possible to use colour extractions, or else the haar-classifier is a better choice.
Cheers
thanks is twas really usefull to me especially the document considering NN as clasifiers
Hi
How to do haar training for hand detection?? Can u explain..
-Newbie