Alignment based extraction of isolated signs from sign language videos İşaret dili videolarindan hizalama ile ayrik i̇şaret çikarimi


Santemiz P., Aran O., SARAÇLAR M., AKARUN ERSOY L.

2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009, Antalya, Türkiye, 9 - 11 Nisan 2009, ss.532-535, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu.2009.5136450
  • Basıldığı Şehir: Antalya
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.532-535
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

This paper presents a method to extract isolated signs from continuous sign language videos. We use sequences that approximately contain the sign that we are interested in and align the sequences to find the exact start and end frames. We compare different feature extraction methods, different alignment methods, and assess the performance of our system on a database from Turkish sign language. ©2009 IEEE.