Tree structures with attentive objects for image classification using a neural network

Hong FU, Shuya ZHANG, Zheru CHI, David Dagan FENG, Xiaoyu ZHAO

Research output: Chapter in Book/Report/Conference proceedingChapters

1 Citation (Scopus)

Abstract

This paper presents an image classification method based on a neural network model dealing with tree structures of attentive objects. Apart from regions provided by image segmentation, attentive objects, which are extracted from a segmented image by an attention-driven image interpretation algorithm, are used to construct the tree structure to represent an image. Three combinations of tree structures are investigated, including "image + attentive-object + segments", "image + attentive-objects", as well as "image + segments". Structure based neural networks are trained to classify the images by using the Back Propagation Through Structure (BPTS) algorithm. Experimental results show that the "image + attentive objects" structure is more favorable, comparing with both the other two structures proposed by us and a start-of-art tree structure reported in the literature, in terms of classification rate and computational time. Copyright © 2009 IEEE.
Original languageEnglish
Title of host publicationThe 2009 International Joint Conference on Neural Networks IJCNN 2009 conference proceedings
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages898-902
ISBN (Electronic)9781424435531
ISBN (Print)9781424435487
DOIs
Publication statusPublished - 2009

Citation

Fu, H., Zhang, S., Chi, Z., Feng, D. D., & Zhao, X. (2009). Tree structures with attentive objects for image classification using a neural network. In The 2009 International Joint Conference on Neural Networks IJCNN 2009 conference proceedings (pp. 898-902). Piscataway, NJ: IEEE.

Fingerprint Dive into the research topics of 'Tree structures with attentive objects for image classification using a neural network'. Together they form a unique fingerprint.