WRITER INDENTIFICATION BASED ON HYPER SAUSAGE NEURON

Sahmin, Samsuryadi and Shamsuddin, Siti Mariyam (2011) WRITER INDENTIFICATION BASED ON HYPER SAUSAGE NEURON. Proceedings of the 3rd International Conference on Computing and Informatics, ICOCI.

[img] Microsoft Word - Published Version
Download (260Kb)
    [img]
    Preview
    PDF - Published Version
    Download (119Kb) | Preview

      Abstract

      This paper proposes biomimetic pattern recognition (BPR) based on hyper sausage neuron (HSN) and applies it in writer identification. HSN is used to cover the training set. HSN’s coverage can be seen as a topological product of a one-dimensional line segment and an n-dimensional supersphere. The feature extraction is moment invariants such as united moment invariants (UMI) and aspect united moment invariants (AUMI). The experiments result show that AUMI-HSN method is more effective than UMI-HSN method for identifying the authorship of handwriting.

      Item Type: Article
      Uncontrolled Keywords: biomimetic pattern recognition, hyper sausage neuron, writer identification, united moment invariants, aspect united moment invariants
      Subjects: Q Science > QA Mathematics
      Q Science > QA Mathematics > QA75 Electronic computers. Computer science
      Q Science > QA Mathematics > QA76 Computer software
      Divisions: Faculty of Computer Science > Department of Informatics Engineering
      Depositing User: S.Si, M.Kom. Samsuryadi Sahmin
      Date Deposited: 18 Jan 2012 14:48
      Last Modified: 29 Feb 2012 04:00
      URI: http://eprints.unsri.ac.id/id/eprint/198

      Actions (login required)

      View Item