icarofua / igftt Goto Github PK

IGFTT features is open source and you can use that freely even in commercial applications. The code is released under BSD license. IGFTT which tackles the classic Computer Vision problem of detecting image keypoints for cases without a priori knowledge on the scene, camera poses and transformation. Compared to well-established algorithms with proven high performance, such as SIFT and SURF, the method at hand offers a dramatically faster alternative at comparable precision performance - a statement which we base on an extensive evaluation using an established framework.

If you use this code as part of your work, please cite the following paper:

IGFTT: towards an efficient alternative to SIFT and SURF. Icaro O. de Oliveira, Keiko V. Ono Fonseca and Eduardo Todt. In International Conferences in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG), Plzen, Czech Republic, June 2015.

To use python code you need:

• Python 3+
• opencv-python
• opencv-contrib-python
• numpy