Title :
Turkish Fingerspelling Recognition with Fast Alignment, Thick Edge Detection and Correlation with Penalization
Author :
Oguz Altun;Songul Albayrak
Author_Institution :
Yildiz Teknik ?niversitesi Bilgisayar M?hendisli?i B?l?m?. oguz@ce.yildiz.edu.tr
fDate :
6/1/2007 12:00:00 AM
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.
Keywords :
"Image edge detection","Chromium","Image recognition","Gaussian processes"
Conference_Titel :
Signal Processing and Communications Applications, 2007. SIU 2007. IEEE 15th
Print_ISBN :
1-4244-0719-2
DOI :
10.1109/SIU.2007.4298841
