segmentation as selective
play

Segmentation as selective search for object recognition Elie Cattan - PowerPoint PPT Presentation

Segmentation as selective search for object recognition Elie Cattan 6/12/2013 Introduction Object recognition Exhaustive search Quick computation needed Selective search Introduction This paper Coarse location


  1. Segmentation as selective search for object recognition Elie Cattan 6/12/2013

  2. Introduction  Object recognition  Exhaustive search ◦ Quick computation needed  Selective search

  3. Introduction  This paper ◦ Coarse location ◦ Emphasizing recall ◦ Fast to compute

  4. State of the art – exhaustive search  Search object and part of the objects (Felzenszwalb et al.)  Branch and bound (Lampert et al.)  Use of random (Alexe et al.)  Class dependent vs class independent

  5. State of the art – selective search  Gu et al. Work ◦ But only a single hierarchy  Foreground/Background segmentations (Carreira et al.) ◦ With precise object delineations

  6. Algorithm  The oversegmentation ◦ Felzenszwalb et al.

  7. Algorithm  Group similar regions ◦ S = Ssize + Stexture  Multiple color spaces

  8. Algorithm  Results :

  9. Object recognition system  Bag of feature ◦ SIFT + OpponentSIFT + RGB-SIFT ◦ 4096 words  Training + retraining

  10. Experiments  Flat vs hierarchical  Object recognition  Object delineation  Accuracy

  11. Experiment 1  Flat vs Hierarchical  Multiple colour spaces

  12. Experiment 2  This paper vs State of the art – object recognition

  13. Experiment 3  This paper vs State of the art – object delineation

  14. Experiment 4  Accuracy

  15. Conclusion  Many approximate locations  Set of complementary segmentations  Very effective for object recognition

  16. Questions

Recommend


More recommend