A neural network model with adaptive structure for image annotation

Zenghai Chen, Hong Fu, Zheru Chi, Dagan Feng

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-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 languageEnglish
Title of host publication11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
Pages1865-1870
Number of pages6
DOIs
Publication statusPublished - 1 Dec 2010
Event11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010 - Singapore, Singapore
Duration: 7 Dec 201010 Dec 2010

Conference

Conference11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010
Country/TerritorySingapore
CitySingapore
Period7/12/1010/12/10

Keywords

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

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this