Feature Analysis of Blind and Visual Signature Data Collection Protocols based on the identification performance

Ibrahem R., ERBİLEK M.

9th International Conference on Computational Intelligence and Communication Networks (CICN), Girne, Cyprus (Kktc), 16 - 17 September 2017, pp.127-130, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/cicn.2017.29
  • City: Girne
  • Country: Cyprus (Kktc)
  • Page Numbers: pp.127-130
  • Middle East Technical University Northern Cyprus Campus Affiliated: No

Abstract

In this paper, we analyse the differences and similarities of features in the context of blind and visual signing data collection protocols with respect to the signature biometrics identification performance. As a result of this performed experimental analysis, powerful features which maximises system accuracy while minimising the performance differential across different signature data collection protocols (visual and blind signing) is extensively tested and documented.