Summary

1
Summary
Recognizing and Learning Object categories
2
Summary

• Methods reviewed here
• Bag of words
• Parts and structure
• Discriminative methods
• Combined Segmentation and recognition
• Resources online
• Slides
• Code
• Links to datasets

http//people.csail.mit.edu/torralba/iccv2005/
3
List properties of ideal recognition system

• Representation
• 1000s categories,
• Handle all invariances (occlusions, view point,
  )
• Explain as many pixels as possible (or answer as
  many questions as you can about the object)
• fast, robust
• Learning
• Handle all degrees of supervision
• Incremental learning
• Few training images

4
Online resources
http//people.csail.mit.edu/torralba/iccv2005/
5
Links to datasets
The next tables summarize some of the available
datasets for training and testing object
detection and recognition algorithms. These lists
are far from exhaustive.
Databases for object localization
Databases for object recognition
On-line annotation tools
Collections
6
LabelMe Dataset

• There are about 19,500 labelled objects

http//www.csail.mit.edu/brussell/research/LabelM
e/intro.html
Google search LabelMe MIT
7
LabelMe Screen Shot
8
Matlab toolbox
LMquery (database, 'object.name',
'car,building,road,tree')
9
Toolbox
LMquery (database, 'object.name',
'car,building,road,tree')
LMcookdatabase (database, 'objectname', 'screen',
'objectsize', 64 64, 'objectlocation',
'original','maximagesize', 128 128)
10
Example Annotations