A model-based approach for rigid object recognition

Most object recognition systems require large databases of real images for classifier training. To collect real images for this purpose is a difficult and expensive process. This paper introduces a unified framework based on the creation and use of synthetic images for training various classifiers t...

Full description

Bibliographic Details
Main Authors: Chong, C., Tan, Tele, Lim, Fee-Lee
Other Authors: Y.Y. Tang
Format: Conference Paper
Published: IEEE Coputer Society Conference Publishing Services 2006
Online Access:http://hdl.handle.net/20.500.11937/18574
_version_ 1848749784177836032
author Chong, C.
Tan, Tele
Lim, Fee-Lee
author2 Y.Y. Tang
author_facet Y.Y. Tang
Chong, C.
Tan, Tele
Lim, Fee-Lee
author_sort Chong, C.
building Curtin Institutional Repository
collection Online Access
description Most object recognition systems require large databases of real images for classifier training. To collect real images for this purpose is a difficult and expensive process. This paper introduces a unified framework based on the creation and use of synthetic images for training various classifiers to achieve recognition of real-world objects. A 3D model of the object (i.e. trolley in this case) is constructed from a minimum of two photographs. The constructed 3D model is used to automatically generate the relevant synthetic images that are subsequently used to train the Adaboost and support vector machine-based recognition systems. Experimental results obtained are very encouraging suggesting that synthetically generated images generated by our approach can augment the real training samples used in current recognition systems
first_indexed 2025-11-14T07:26:26Z
format Conference Paper
id curtin-20.500.11937-18574
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:26:26Z
publishDate 2006
publisher IEEE Coputer Society Conference Publishing Services
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-185742022-10-27T07:56:24Z A model-based approach for rigid object recognition Chong, C. Tan, Tele Lim, Fee-Lee Y.Y. Tang S.P.Wang G. Lorette D.S. Young H. Yang Most object recognition systems require large databases of real images for classifier training. To collect real images for this purpose is a difficult and expensive process. This paper introduces a unified framework based on the creation and use of synthetic images for training various classifiers to achieve recognition of real-world objects. A 3D model of the object (i.e. trolley in this case) is constructed from a minimum of two photographs. The constructed 3D model is used to automatically generate the relevant synthetic images that are subsequently used to train the Adaboost and support vector machine-based recognition systems. Experimental results obtained are very encouraging suggesting that synthetically generated images generated by our approach can augment the real training samples used in current recognition systems 2006 Conference Paper http://hdl.handle.net/20.500.11937/18574 10.1109/ICPR.2006.103 IEEE Coputer Society Conference Publishing Services restricted
spellingShingle Chong, C.
Tan, Tele
Lim, Fee-Lee
A model-based approach for rigid object recognition
title A model-based approach for rigid object recognition
title_full A model-based approach for rigid object recognition
title_fullStr A model-based approach for rigid object recognition
title_full_unstemmed A model-based approach for rigid object recognition
title_short A model-based approach for rigid object recognition
title_sort model-based approach for rigid object recognition
url http://hdl.handle.net/20.500.11937/18574