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

Authors:
Hong Fu;Shuya Zhang;Zheru Chi;David Dagan Feng;Xiaoyu Zhao
Affiliations:
Center for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong;Institute of DSP and Software Technology, Ningbo University, Ningbo, China;Center for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong;Center for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong and School of Information Technologies, The ...;Center for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 12
Cited 0

Unsupervised Segmentation of Color-Texture Regions in Images and Video

IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Learning in Adaptive Processing of Data Structures

Neural Processing Letters
Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Genetic Evolution Processing of Classification

IEEE Transactions on Knowledge and Data Engineering
Attention-driven image interpretation with application to image retrieval

Pattern Recognition
A new image classification technique using tree-structured regional features

Neurocomputing
An efficient algorithm for attention-driven image interpretation from segments

Pattern Recognition
Structured-Based neural network classification of images using wavelet coefficients

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
Supervised neural networks for the classification of structures

IEEE Transactions on Neural Networks
A general framework for adaptive processing of data structures

IEEE Transactions on Neural Networks
Support vector machines for histogram-based image classification

IEEE Transactions on Neural Networks
An improved algorithm for learning long-term dependency problems in adaptive processing of data structures

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

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.