Title :
Learning signs from subtitles: A weakly supervised approach to sign language recognition
Author :
Cooper, Helen ; Bowden, Richard
Author_Institution :
CVSSP, Univ. Of Surrey, Guildford, UK
Abstract :
This paper introduces a fully automated, unsupervised method to recognise sign from subtitles. It does this by using data mining to align correspondences in sections of videos. Based on head and hand tracking, a novel temporally constrained adaptation of a priori mining is used to extract similar regions of video, with the aid of a proposed contextual negative selection method. These regions are refined in the temporal domain to isolate the occurrences of similar signs in each example. The system is shown to automatically identify and segment signs from standard news broadcasts containing a variety of topics.
Keywords :
data mining; face recognition; gesture recognition; unsupervised learning; contextual negative selection method; data mining; hand tracking; head tracking; standard news broadcast segment; subtitle recognition; temporal domain; unsupervised sign language recognition; Broadcasting; Data mining; Face recognition; Handicapped aids; Head; Labeling; Multimedia communication; Natural languages; Shape; Vocabulary;
Conference_Titel :
Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on
Conference_Location :
Miami, FL
Print_ISBN :
978-1-4244-3992-8
DOI :
10.1109/CVPR.2009.5206647