Turkish fingerspelling recognition with fast alignment, thick edge detection and correlation with penalization

ALTUN O., VARLI S.

IEEE 15th Signal Processing and Communications Applications Conference, Eskişehir, Turkey, 11 - 13 June 2007, pp.87-90, (Full Text) identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/siu.2007.4298841
  • City: Eskişehir
  • Country: Turkey
  • Page Numbers: pp.87-90
  • Yıldız Technical University Affiliated: Yes

Abstract

Fingerspelling is used for words that have no sign, or for words that the sign is unknown. In this work, the signs of Turkish Alphabet are recognized from video images. The methods used are fast alignment, thick edge extraction and correlation with penalization methods. A 99 percent success ratio is achieved.