Object categorization

✍ Scribed by Pinz, Axel

• Publisher: Now Publishers, Inc
• Year: 2006
• Tongue: English
• Leaves: 111
• Series: Foundations and trends in computer graphics and vision 1 no. 4
• Category: Library

✦ Synopsis

This article presents foundations, original research and trends in the field of object categorization by computer vision methods. The research goals in object categorization are to detect objects in images and to determine the object's categories. Categorization aims for the recognition of generic classes of objects, and thus has also been termed 'generic object recognition'. This is in contrast to the recognition of specific, individual objects. While humans are usually better in generic than in specific recognition, categorization is much harder to achieve for today's computer architectures. Read more...

Abstract:

Presents foundations, original research and trends in the field of object categorization by computer vision methods. This work provides a review of existing representations, algorithms, systems and databases for visual object categorization. It includes original research in categorization and presents a prototype system for categorization. Read more...

✦ Table of Contents

Content: Introduction
Problem statement
Historical development
Potential applications
Outline of this review article
Categorization as an Issue of ...
... classification
... learning
... representation
... localization
... datasets
... evaluation
... system integration
Building Blocks for Categorization
Scale in space and time
Saliency, key-features, points and regions of interest
Object models
Learning and recognition
A Prototype System for Categorization
Region-based image categorization
Detection and localization with a Boundary-Fragment-Model (BFM)
Discussion
Final Remarks
Acknowledgements.

✦ Subjects

Computer vision;Pattern recognition systems