Search code examples
image-processingface-recognitionsurf

What are T-junctions in the Speeded-Up Robust Features paper

In the paper entitled "Speeded-Up Robust Features (SURF)" Bay et. al. mention that

... ‘interest points’ are selected at distinctive locations in the image, such as corners, blobs, and T-junctions.

Can someone explain to me what they mean by T-junctions?

Note: I'm using the SURF algorithm provided by OpenCV.

I'm not sure if this is the best place to ask this kind of question, but I could not find a better one.

Thanks in advance

Reference:

Bay, Herbert, et al. "Speeded-up robust features (SURF)." Computer vision and image understanding 110.3 (2008): 346-359.

Solution

  • It's actually pretty simple. It's a feature that looks like a T. Think of a street T-junction.

    For example one edge that touches another edge perpendicularly.