A neural network model with adaptive structure for image annotation

Zenghai Chen; Hong Fu; Zheru Chi; Dagan Feng

doi:10.1109/ICARCV.2010.5707323

A neural network model with adaptive structure for image annotation

Zenghai Chen, Hong Fu, Zheru Chi, Dagan Feng

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

3 Citations (Scopus)

Abstract

A neural network model with adaptive structure for image annotation is proposed in this paper. The adaptive structure enables the proposed model to utilize both global and regional visual features, as well as correlative information of annotated keywords for annotation. In order to achieve an approximate global optimum rather than a local optimum, both genetic algorithm and traditional back-propagation algorithm, are combined for model training. The neural network model is experimented on a synthetic image dataset with controllable parameters, which has not been used in previous image annotation experiments. Experimental results demonstrate the effectiveness of the proposed model.

Original language	English
Title of host publication	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
Pages	1865-1870
Number of pages	6
DOIs	https://doi.org/10.1109/ICARCV.2010.5707323
Publication status	Published - 1 Dec 2010
Event	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010 - Singapore, Singapore Duration: 7 Dec 2010 → 10 Dec 2010

Conference

Conference	11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
Country/Territory	Singapore
City	Singapore
Period	7/12/10 → 10/12/10

Keywords

Back-propagation training algorithm
Genetic algorithm
Image annotation
Neural networks
Synthetic image dataset

ASJC Scopus subject areas

Artificial Intelligence
Control and Systems Engineering

More information

10.1109/ICARCV.2010.5707323

Cite this

@inproceedings{81389db0cae04ab090f36babc726553b,

title = "A neural network model with adaptive structure for image annotation",

abstract = "A neural network model with adaptive structure for image annotation is proposed in this paper. The adaptive structure enables the proposed model to utilize both global and regional visual features, as well as correlative information of annotated keywords for annotation. In order to achieve an approximate global optimum rather than a local optimum, both genetic algorithm and traditional back-propagation algorithm, are combined for model training. The neural network model is experimented on a synthetic image dataset with controllable parameters, which has not been used in previous image annotation experiments. Experimental results demonstrate the effectiveness of the proposed model.",

keywords = "Back-propagation training algorithm, Genetic algorithm, Image annotation, Neural networks, Synthetic image dataset",

author = "Zenghai Chen and Hong Fu and Zheru Chi and Dagan Feng",

year = "2010",

month = dec,

day = "1",

doi = "10.1109/ICARCV.2010.5707323",

language = "English",

isbn = "9781424478132",

pages = "1865--1870",

booktitle = "11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010",

note = "11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010 ; Conference date: 07-12-2010 Through 10-12-2010",

}

Chen, Z, Fu, H, Chi, Z & Feng, D 2010, A neural network model with adaptive structure for image annotation. in 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010., 5707323, pp. 1865-1870, 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010, Singapore, Singapore, 7/12/10. https://doi.org/10.1109/ICARCV.2010.5707323

A neural network model with adaptive structure for image annotation. / Chen, Zenghai; Fu, Hong; Chi, Zheru et al.
11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010. 2010. p. 1865-1870 5707323.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - A neural network model with adaptive structure for image annotation

AU - Chen, Zenghai

AU - Fu, Hong

AU - Chi, Zheru

AU - Feng, Dagan

PY - 2010/12/1

Y1 - 2010/12/1

N2 - A neural network model with adaptive structure for image annotation is proposed in this paper. The adaptive structure enables the proposed model to utilize both global and regional visual features, as well as correlative information of annotated keywords for annotation. In order to achieve an approximate global optimum rather than a local optimum, both genetic algorithm and traditional back-propagation algorithm, are combined for model training. The neural network model is experimented on a synthetic image dataset with controllable parameters, which has not been used in previous image annotation experiments. Experimental results demonstrate the effectiveness of the proposed model.

AB - A neural network model with adaptive structure for image annotation is proposed in this paper. The adaptive structure enables the proposed model to utilize both global and regional visual features, as well as correlative information of annotated keywords for annotation. In order to achieve an approximate global optimum rather than a local optimum, both genetic algorithm and traditional back-propagation algorithm, are combined for model training. The neural network model is experimented on a synthetic image dataset with controllable parameters, which has not been used in previous image annotation experiments. Experimental results demonstrate the effectiveness of the proposed model.

KW - Back-propagation training algorithm

KW - Genetic algorithm

KW - Image annotation

KW - Neural networks

KW - Synthetic image dataset

UR - http://www.scopus.com/inward/record.url?scp=79952431619&partnerID=8YFLogxK

U2 - 10.1109/ICARCV.2010.5707323

DO - 10.1109/ICARCV.2010.5707323

M3 - Conference article published in proceeding or book

SN - 9781424478132

SP - 1865

EP - 1870

BT - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

T2 - 11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010

Y2 - 7 December 2010 through 10 December 2010

ER -

A neural network model with adaptive structure for image annotation

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this