Methods to describe and recognize sign language based on gesture components represented by symbols and numerical values

Signing Exact English (SEE): Modeling and recognition

“…Besides the above mentioned classification schemes, Sagawa and Takeuchi [18] employed rule-based matching to recognize gesture components such as the handshape, the direction of palm, linear motion and circular motion. The experiment was carried out with 60 sign language morphemes, and the accuracy on "unseen" signers was 94.7%.…”

A teaching system of Japanese sign language using sign language recognition and generation

“…The sign language recognition part estimates signed gestures inputted from a glove-based input device. The method in [8] is used to evaluate signed gestures. In the sign language generation part, the sign language animation using 3DCG is generated based on the information stored in the contents for sign language education.…”

“…We have developed the sign language recognition technology which recognizes the inputted signed gesture of Japanese sign language and translates it into Japanese text [8][9][10], and the sign language generation technology which translates Japanese text into Japanese sign language and displays it as a 3DCG (three dimensional computer graphics) animation [11][12]. The sign language recognition technology calculates the similarity between the inputted signed gesture and the gesture stored in the system.…”

Development of an information kiosk with a sign language recognition system

“…Each gesture primitive consists of the kind of gesture primitive, the part of the hand that represents the gesture primitive and the attributes, such as the start position and the motion direction, and the attributes of the gesture primitive. During the recognition process, the gesture primitives are identified from the inputted gesture, then the signed-word is recognized by the time and spatial relationship between the gesture primitives [2].…”

“…JSL will become even more important for hearingimpaired people not only to communicate with hearing people, but also to get information and services [1]. We previously developed a recognition system that translates JSL into spoken Japanese [2,3]. This system recognizes each signed-word from an inputted signed-sentence.…”