Skip navigation
Skip navigation

Invariant object recognition using circular pairwise convolutional networks

Teo, Choon-Hui; Tay, Yong Haur

Description

Invariant object recognition (IOR) has been one of the most active research areas in computer vision. However, there is no technique able to achieve the best performance in all possible domains. Out of many techniques, convolutional network (CN) is proven to be a good candidate in this area. Given large numbers of training samples of objects under various variation aspects such as lighting, pose, background, etc., convolutional network can learn to extract invariant features by itself. This...[Show more]

CollectionsANU Research Publications
Date published: 2006
Type: Book chapter
URI: http://hdl.handle.net/1885/28094

Download

File Description SizeFormat Image
01_Teo_Invariant_object_recognition_2006.pdf130.61 kBAdobe PDF    Request a copy
02_Teo_Invariant_object_recognition_2006.pdf353.56 kBAdobe PDF    Request a copy
03_Teo_Invariant_object_recognition_2006.pdf670.03 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator