Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/56247
Title: Image database retrieval using GMM-AIB framework
Authors: Li, J.
Li, J.
Yan, S. 
Wang, G.
Keywords: AIB clustering
Ensemble learning
Gaussian mixed model
Image representation
Multi-instance learning
Scene recognition
Single-instance bag
Issue Date: 15-Nov-2012
Source: Li, J.,Li, J.,Yan, S.,Wang, G. (2012-11-15). Image database retrieval using GMM-AIB framework. Journal of Computational Information Systems 8 (22) : 9141-9149. ScholarBank@NUS Repository.
Abstract: Multi-Instance learning (MIL) is a learning framework proposed recently and has been successfully used in scene and video classification and recognition. A novel Multi-Instance (MI) bag generating method is proposed in this paper, based on a Gaussian Mixed Model (GMM). The generated GMM is treated as an MI bag, of which the color and locally stable invariant components (SIFT) are the instances. Then, Agglomerative Information Bottleneck clustering is employed to transform the MIL problem into single-instance learning problem so that single-instance classifiers can be used for classification. Finally, ensemble learning is involved to further enhance classifiers' generalization ability. Experimental results demonstrate that the performance of the proposed framework for image recognition is superior to some common MI algorithms on average in a 5-category scene recognition task. Copyright © 2012 Binary Information Press.
Source Title: Journal of Computational Information Systems
URI: http://scholarbank.nus.edu.sg/handle/10635/56247
ISSN: 15539105
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

32
checked on Dec 15, 2017

Google ScholarTM

Check


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