Object Recognition (Nike logo)
Posted on : 22-10-2009 | By : Aleksey Kodubets | In : Demo, Demo video, Demo videos, OpenCV, YouTube
11
This is a demo video of the invariant orientation and scale fast object detection algorithm. The algorithm is a robust in cases when the object is deformed a little 🙂
The algorithm is a cross-platform solution.
Performance:
- on ARM11 530MHz, the algorithm gives 1 fps for 640×480 frame;
- on Intel P4 3Hz, the algorithm gives 12 fps and more for 640×480 frame.
Quality: 86%.
what algorithm are you using to achieve the result? recognization Rotated NIKE logo is difficult. If not for rotation, haar + adaboost can achieve!
Hi YCat,
You are right, this is a difficult task. This is not haar + adaboost, we rejected Viola-Jones approach since it doesn’t work at all if an object is rotated. Nike-logo detection is original own algorithm. For nike-logo detection we used template matching, key-points matching and other and of course original own heuristics.
it is really a great job
can i get the algorithm that u r using?
Hi Nomi,
Sorry, but we can’t provide you our source code due to our policy.
Thanks,
Alexander
Hi Alexander, I understand that the source code is confidential, but maybe u can give the (i am assuming) math formula that u guys use?
Hi Nomi
I’m very like your great work.Can I have get more details about the algorithm
Hi Nomi
Is your algorithm is similar to SIFT algorithm?
Hi,
I would like to know what algorithm is the most adequate to recognize objects, such as holes in the street, or garbage, from photographs picked with a mobile. The object that we want identify is circumscribed with a line.
Thanks in advance,
Maria
May I know if your service can be used for enterprise purpose. I mean is your product available for purchase?
Object Recognition is taking pace with time, I agree. I’d request you to kindly elaborate about the implementation of object recognition algorithms for detecting different objects through a web camera.