Informative algorithms related to opencv
Based on the idea proposed in Informative websites related to OpenCV by Sturkmen, I think that it would also be useful to create a list about implementations based on papers and publications:
- implemented with OpenCV and/or
- that can be used/integrated easily with OpenCV
(maybe one toy example with each one would be fantastic)
As OpenCV is under the open-source BSD license, it would also be interesting that these algorithms would be BSD or similar. So, I am going to put my list (Maybe some algorithms should not be in this list, so do it together!).
TRACKING
Object tracking
Real-time Compressive Tracking
(http://www4.comp.polyu.edu.hk/~cslzha...) implementation integrated with opencv
Zhang, K., Zhang, L., & Yang, M. H. (2012). Real-time compressive tracking. In Computer Vision–ECCV 2012 (pp. 864-877). Springer Berlin Heidelberg.
- Accurate scale estimation for robust visual tracking
Implemented in DLIB library http://dlib.net/
Danelljan, M., Häger, G., Khan, F., & Felsberg, M. (2014). Accurate scale estimation for robust visual tracking. In British Machine Vision Conference, Nottingham, September 1-5, 2014. BMVA Press. (winning algorithm from last year's Visual Object Tracking Challenge. )
FACE PROCESSING
Face pre-processing
Tan&Triggs processing
A efficient image pre-processing normalization algorithm to deal with difficult lighting conditions: Tan, X., & Triggs, B. (2010). Enhanced local texture feature sets for face recognition under difficult lighting conditions. Image Processing, IEEE Transactions on, 19(6), 1635-1650.
implementation: https://github.com/bytefish/opencv/bl... (BSD license)
- Real-Time Face Pose Estimation
One Millisecond Face Alignment with an Ensemble of Regression Trees Kazemi, V., & Sullivan, J. (2014, June). One millisecond face alignment with an ensemble of regression trees. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on (pp. 1867-1874). IEEE.
Implemented in DLIB library http://dlib.net/
demo snippet: https://gist.github.com/berak/b23262a...
- Face landmarks detector (face alignment)
Cao X, Wei Y, Wen F, et al. Face alignment by explicit shape regression[J]. International Journal of Computer Vision, 2014, 107(2): 177-190.
implementation: https://github.com/delphifirst/FaceX/
demo snippet: https://gist.github.com/berak/79aeb39...
- Eye localization: Average of Synthetic Exact Filters
Bolme, D. S., Draper, B., & Beveridge, J. R. (2009, June). Average of synthetic exact filters. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on (pp. 2105-2112). IEEE.
implementation: https://github.com/laoyang/ASEF
- Eye localization: Accurate eye centre localisation by means of gradient
Timm, F., & Barth, E. (2011, March). Accurate Eye Centre Localisation by Means of Gradients. In VISAPP (pp. 125-130).
implementation: https://github.com/trishume/eyeLike
- Eye pupil localization (tracking)
Markuš, N., Frljak, M., Pandžić, I. S., Ahlberg, J., & Forchheimer, R. (2014). Eye pupil localization with an ensemble of randomized trees. Pattern recognition, 47(2), 578-587.
implementation: https://github.com/chrisjryan/eye-tra...
youtube video: https://www.youtube.com/watch?v=7J30y...
(This method uses the OpenCV library to identify eyes on faces and prepare these sub-images with previously-landmarked pupil information.)
FACE DETECTION
- PICO Face detection
N. Markus, M. Frljak, I. S. Pandzic, J. Ahlberg and R. Forchheimer, "Object ...
oh, nice ;)
would you prefer people writing comments, or edit directly ?
i think that edit directly is a better approach. Afterwards, some filtering/ordering/classification should be necessary.....
btw, @StevenPuttemans , any updates on sticky pages on this site ?
not yet :D I have to be patient according to Alexander. If this doesn't get added soon, I will start making wiki pages based on this input (got the privilege to edit those online)
^^ terrific idea ! maybe we can even find a way so folks can edit here and it shows up there (after some moderating/filtering)
I think that use of a question as documentation is a bad workaround because it will be lost soon in the sea of Q&A. Infos organization is discussed here many time and main issue seems to be time and resource of peoples... may be a collaborative wiki can help.
@pklab I agree with you, therefore I am going to port them to wiki pages once they stabalize. We are looking into it :D