Hand Gesture Recognition Using Leap Motion Controller

Sign Language is one of the widely used methods of communication within the hearing impaired people. Sign language is a mode of communication that provides a way of interaction to those hard of hearing, using a collection of gestures and symbols. Hand gesture recognition is a major step for sign language recognition which uses the gestures and symbols to interpret the thoughts of the person. Hand recognition by conventional methods using 2-D cameras suffer from instability due to lighting and skin color variations. The upcoming depth sensors overcome the limitations of the conventional cameras. A Leap Motion controller helps to obtain descriptive information of hand gestures. It tracks the hand and finger movements in digital format and gives few key points associated with each gesture. These key points are used for training and recognition. The paper illustrates the use of Leap Motion controller for hand gesture recognition of indian sign language signs using four similarity measures namely Euclidean distance measure, Cosine similarity, Jaccard similarity and Dice similarity.45 gestures of Indian Sign Language including 26 alphabets (a to z), 10 numbers (1 to 10) and 9 words are tested with 10 different signers. Average recognition accuracy that is achieved with cosine similarity is 90 %, Euclidean distance measure is 88.22 %, Jaccard similarity is 86 % and with dice similarity is 83.11 % using 8 features.