27-04-2011, 09:56 AM
PRESENTED BY:
Devansh Tripathi
[attachment=12892]
Goal
• Recognition of object categories
• Unassisted learning
Some object categories
Difficulties:
• Size variation
• Background clutter
• Occlusion
• Intra-class variation
Main issues
• Representation
• Learning
• Recognition
Model: Constellation of Parts
f Fischler & Elschlager 1973
f Yuille ‘91
f Brunelli & Poggio ‘93
f Lades, v.d. Malsburg et al. ‘93
f Cootes, Lanitis, Taylor et al. ‘95
f Amit & Geman ‘95, ‘99
f Perona et al. ‘95, ‘96, ’98, ’00
f Agarwal & Roth ‘02
Detection & Representation of regions
• Find regions within image
• Use Kadir and Brady's salient region operator [IJCV ’01]