SLIDE 1
Segmentation as selective search for object recognition
Elie Cattan
6/12/2013
Introduction
Object recognition Exhaustive search
- Quick computation needed
Segmentation as selective search for object recognition Elie Cattan - - PowerPoint PPT Presentation
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
SLIDE 2
SLIDE 3
Introduction
This paper
- Coarse location
- Emphasizing recall
- Fast to compute
SLIDE 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
SLIDE 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
SLIDE 6
Algorithm
The oversegmentation
- Felzenszwalb et al.
SLIDE 7
Algorithm
Group similar regions
- S = Ssize + Stexture
Multiple color spaces
SLIDE 8
Algorithm
Results :
SLIDE 9
Object recognition system
Bag of feature
- SIFT + OpponentSIFT + RGB-SIFT
- 4096 words
Training + retraining
SLIDE 10
Experiments
Flat vs hierarchical Object recognition Object delineation Accuracy
SLIDE 11
Experiment 1
Flat vs Hierarchical Multiple colour spaces
SLIDE 12
Experiment 2
This paper vs State of the art – object
recognition
SLIDE 13
Experiment 3
This paper vs State of the art – object
delineation
SLIDE 14
Experiment 4
Accuracy
SLIDE 15
Conclusion
Many approximate locations Set of complementary segmentations Very effective for object recognition
SLIDE 16