Saturday, February 2, 2013

Object Recognition Day 01

Challenges in visual object recognition

 Matching and learning visual objects is challenging because of the following factors.

  1. Illumination conditions
  2. Object pose
  3. Camera viewpoint
  4. Partial occlusions
  5. Unrelated background clutter
  6. Computational complexity
  7. Scalability


State of the art of visual object recognition methods


A good feature extraction method needs to have the following properties.

  1. Being able to extract local invariant features (e.g. scale invariance, affine invariance)
  2. Fast to extract
  3. Robust to viewpoint variations
  4. Retaining enough discriminative power to allow for reliable matching

References

Kristen Grauman and Bastian Leibe (2011) . Visual Object Recognition (Synthesis Lectures on Artificial Intelligence & Machine Learning). Morgan & Claypool.

No comments:

Post a Comment

Mounting USB drives in Windows Subsystem for Linux

Windows Subsystem for Linux can use (mount): SD card USB drives CD drives (CDFS) Network drives UNC paths Local storage / drives Drives form...