Note that there are some explanatory texts on larger screens.

plurals
  1. PO
    text
    copied!<p>An alternative approach would be to extract features (keypoints) using the <a href="http://en.wikipedia.org/wiki/Scale-invariant_feature_transform" rel="noreferrer">scale-invariant feature transform</a> (SIFT) or <a href="http://en.wikipedia.org/wiki/SURF" rel="noreferrer">Speeded Up Robust Features</a> (SURF).</p> <p>It is implemented in <a href="http://en.wikipedia.org/wiki/OpenCV" rel="noreferrer">OpenCV</a> 2.3.1.</p> <p>You can find a nice code example using features in <em><a href="http://docs.opencv.org/2.4/doc/tutorials/features2d/feature_homography/feature_homography.html" rel="noreferrer">Features2D + Homography to find a known object</a></em></p> <p>Both algorithms are invariant to scaling and rotation. Since they work with features, you can also handle <a href="http://en.wikipedia.org/wiki/Ambient_occlusion" rel="noreferrer">occlusion</a> (as long as enough keypoints are visible).</p> <p><img src="https://i.stack.imgur.com/kF63R.jpg" alt="Enter image description here"></p> <p>Image source: tutorial example</p> <p>The processing takes a few hundred ms for SIFT, SURF is bit faster, but it not suitable for real-time applications. ORB uses FAST which is weaker regarding rotation invariance.</p> <h3>The original papers</h3> <ul> <li><a href="http://www.vision.ee.ethz.ch/~surf/eccv06.pdf" rel="noreferrer">SURF: Speeded Up Robust Features</a></li> <li><a href="http://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf" rel="noreferrer">Distinctive Image Features from Scale-Invariant Keypoints</a></li> <li><a href="http://www.willowgarage.com/sites/default/files/orb_final.pdf" rel="noreferrer">ORB: an efficient alternative to SIFT or SURF</a></li> </ul>
 

Querying!

 
Guidance

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload