Indian sign language to forecast text using leap motion sensor and RF classifier
Poonam Chavan, Tushar H. Ghorpade, Puja Padiya · 2016
These A compact and accurate device recently magnets attraction: The Leap Motion Sensor. It's a novel 3D acquisition device which has depth cameras to obtain various depth description of hand gesture, which can be used for accurate gesture recognition. This sensor device specially targeted for hand gesture recognition and provides only specific number of relevant points. Our proposed system involve recognition of Indian Sign Language (ISL) using Leap Motion Sensor. The device extracts significant characters/ attributes from the dataset such that high-accuracy angle between fingers cab be retrieved, and this can be used for robust prediction. Then, System maps all the frames recognized by sensor to attributes. Feature classifier is used to identify which gesture is being performed. Here, Random Forest (RF) classifier model is used as feature classification. Our method trains a RF to recognize hand gestures for given set of data presented in training dataset. A block-list classifier is used to remove all non-gestures frames, after which accurate gesture frames are recognized by RF to form a meaningful word. This meaningful word is then displayed on LCD. Our proposed method outweighs other state-of-art methods for gesture recognition.