Skip to main content
placeholder image

The hierarchical cluster model for image region segmentation

Conference Paper


Abstract

  • The hierarchical cluster model (HCM), a neural network inspired by the human brain [1], is demonstrated for the purpose of region segmentation in digital images. Starting with an over segmented image, regions are merged based on evidence of a valid edge between the two regions. Unlike the work in [1], in which the HCM is used to recall a set of pre-trained memory patterns, the HCM in our work demonstrates unsupervised decision making capabilities.

Publication Date

  • 2002

Citation

  • Randall, J., Guan, L., Zhang, X., & Li, W. Q. (2002). The hierarchical cluster model for image region segmentation. In Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002 Vol. 1 (pp. 693-696). doi:10.1109/ICME.2002.1035876

Scopus Eid

  • 2-s2.0-34247561250

Start Page

  • 693

End Page

  • 696

Volume

  • 1

Abstract

  • The hierarchical cluster model (HCM), a neural network inspired by the human brain [1], is demonstrated for the purpose of region segmentation in digital images. Starting with an over segmented image, regions are merged based on evidence of a valid edge between the two regions. Unlike the work in [1], in which the HCM is used to recall a set of pre-trained memory patterns, the HCM in our work demonstrates unsupervised decision making capabilities.

Publication Date

  • 2002

Citation

  • Randall, J., Guan, L., Zhang, X., & Li, W. Q. (2002). The hierarchical cluster model for image region segmentation. In Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002 Vol. 1 (pp. 693-696). doi:10.1109/ICME.2002.1035876

Scopus Eid

  • 2-s2.0-34247561250

Start Page

  • 693

End Page

  • 696

Volume

  • 1