object class recognition

19
Object Class Recognition Abhitej John.B B.Tech 4/4 CS08765

Upload: abhitej-john

Post on 12-Jul-2015

150 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Object Class Recognition

Object Class Recognition

Abhitej John.BB.Tech 4/4

CS08765

Page 2: Object Class Recognition

Outline

Introduction

OCR’s role today

Algorithms in OCR

Neural Networks

Random forests

Conclusion

References

Page 3: Object Class Recognition

What is OCR?

A sub domain of Computer Vision

Related Domains – Pattern Recognition, Image Processing, Artificial Intelligence

Sub domains – object recognition, Video tracking,

Applications – Face detection, barcode decoding, Robotics

“Computer vision is the science and technology of machines that see”

Page 4: Object Class Recognition

What is Ocr? (continued..)

Steps involved

Segmentation (pixel color, intensity, texture..)

Clustering methods, Histogram based methods, edge detection, neural networks

Recognition

Geometry based, Appearance based and Feature based models.

Classification/ Detection

Neural Networks, Bayesian classifiers, Decision trees

Page 5: Object Class Recognition

Why OCR?

Applications.

Face/handwriting recognition systems

Autonomous vehicle navigation

Robotics

Gesture recognition

Content based image retrieval

Search by image

Page 6: Object Class Recognition

How OCR is done

Challenges

Object Variations – rotation, pose, scale

Occlusion

Illumination

Multiple objects

Learning an object model

Page 7: Object Class Recognition

How OCR is done (Continued..)

Page 8: Object Class Recognition

How OCR is Done (Continued..)

Classification of algorithms

Geometry based models

Appearance based models

Feature based models

Account for image variations

Page 9: Object Class Recognition

OCR with neural networks

Pre-processing step to extract shapes

Shape descriptors

Shape interpretation

Object representation

Object Interpretation

Classified object

Page 10: Object Class Recognition

OCR with Neural Networks

Shape interpretation

Object recognition Self Organizing Map

Object Classification Neural Network

Page 11: Object Class Recognition

OCR with neural networks

Training

Shape interpretation Neural Network

SOM for shape combinations

Classifier Neural Network

Recognition

Page 12: Object Class Recognition

OCR with Random forests

Random Forest

Classification

Features – multi class classifier, efficiency

Improvement on decision trees

Growing a tree If the number of cases in the training set is N, sample N cases at random - but with replacement, from

the original data. This sample will be the training set for growing the tree.

If there are M input variables, a number m<<M is specified such that at each node, m variables are selected at random out of the M and the best split on these m is used to split the node. The value of m is held constant during the forest growing.

Each tree is grown to the largest extent possible. There is no pruning.

Page 13: Object Class Recognition

OCR with random forests

Features

Node function

Abstest and difftest

Page 14: Object Class Recognition

OCR with Random foretss

Training and Testing

Choosing the training data

Tree creation based on information gain

Final outcome to test

Page 15: Object Class Recognition

OCR with random forests

A similar approach

Steps involved – segmentation, classification

Computing features

Node – appearance and shape

Page 16: Object Class Recognition

Conclusion

Other algorithms for recognizing object classes:

K-nearest neighbors and other clustering methods

SIFT

Decision trees

Bayesian classifiers

Unsupervised learning

Page 17: Object Class Recognition

Conclusion

Concepts covered

Computer Vision

Object Class Recognition

Neural Networks

Self Organizing Map

Random Forests

Page 18: Object Class Recognition

References

Florian Schroff, Antonio Criminisi, and Andrew Zisserman, Object Class Segmentation using Random Forests, in Proc. British Machine Vision Conference (BMVC), 2008

Object Recognition: A Shape-Based Approach using Artificial Neural Networks; Jelmer de Vries; MSc thesis, University of Utrecht Department of Computer Science, 2006

J. Winn and A. Criminisi, “Object Class Recognition at a Glance”. IEEE Computer Vision and Pattern Recognition (CVPR), New York, 2006.

Pinto N, Cox DD, DiCarlo JJ (2008) Why is Real-World Visual Object Recognition Hard? PLoS Comput Biol 4(1): e27. doi:10.1371/journal.pcbi.0040027.

J. Winn, A. Criminisi, and T. Minka. Object Categorization by Learned Universal Visual Dictionary. ICCV, 2005.

Page 19: Object Class Recognition

Thank You