Extraction of Isolated Signs from Sign Language Videos via Multiple Sequence Alignment
نویسندگان
چکیده
In this work, we present an alignment-based method to perform sign segmentation and to extract isolated signs from continuous sign language videos. Sign videos contain many modalities, the most prominent of which are hand gestures, manifested as hand motion and shape, which are represented by a variety of extracted features in this work. We compare two different alignment approaches, Dynamic Time Warping (DTW) and Hidden Markov Models (HMMs), and analyze their behaviour with different feature sets on a database from Turkish sign language. Our experiments show that simple hand shape descriptors perform better than the high level ones and the accuracy of HMMs is better than DTW.
منابع مشابه
Modelling and recognition of the linguistic components in American Sign Language
The manual signs in sign languages are generated and interpreted using three basic building blocks: handshape, motion, and place of articulation. When combined, these three components (together with palm orientation) uniquely determine the meaning of the manual sign. This means that the use of pattern recognition techniques that only employ a subset of these components is inappropriate for inte...
متن کاملSegment, Track, Extract, Recognize and Convert Sign Language Videos to Voice/Text
This paper summarizes various algorithms used to design a sign language recognition system. Sign language is the language used by deaf people to communicate among themselves and with normal people. We designed a real time sign language recognition system that can recognize gestures of sign language from videos under complex backgrounds. Segmenting and tracking of non-rigid hands and head of the...
متن کاملChallenges in Development of the American Sign Language Lexicon Video Dataset (ASLLVD) Corpus
The American Sign Language Lexicon Video Dataset (ASLLVD) consists of videos of >3,300 ASL signs in citation form, each produced by 1-6 native ASL signers, for a total of almost 9,800 tokens. This dataset, including multiple synchronized videos showing the signing from different angles, will be shared publicly once the linguistic annotations and verifications are complete. Linguistic annotation...
متن کاملDetection and Recognition of Multi-language Traffic Sign Context by Intelligent Driver Assistance Systems
Design of a new intelligent driver assistance system based on traffic sign detection with Persian context is concerned in this paper. The primary aim of this system is to increase the precision of drivers in choosing their path with regard to traffic signs. To achieve this goal, a new framework that implements fuzzy logic was used to detect traffic signs in videos captured along a highway f...
متن کاملA Cooperative Multiagent Architecture for Turkish Sign Tutors
A sign is a combination of hand movements, facial expressions, and head movements. A sign with only hand movements is called manual signs, whereas signs which also include head movements or facial expressions are called non-manual signs. The aim of the Sign Language Tutoring Tool is to help users learn isolated signs by watching recorded videos and enable them try the same signs [1]. The system...
متن کامل