Finger Spelling Identification by Employing Picture Processing

Abstract

Human hands are delicate instruments. Hand gestures and finger gestures are excellent ways of emphasizing what we say, but on the other hand they can also reveal our true intentions. In this paper introduced a continuous Indian sign language recognition sy wherever each the hands are used for playacting any gesture. Recognizing a sign language gestures from continuous gestures could be a terribly difficult analysis issue. In this paper, a new skeleton approach is proposed for 3D hand gesture recog Specifically, we exploit the geometric shape of the hand to extract an effective descriptor from hand skeleton connected joints returned by the Intel RealSense depth camera. This paper solve the problem using gradient based key frame extraction technique. These key frames are useful for splitting continuous language gestures into sequence of signs further as for removing uninformative frames. After splitting of gestures every sign has been treated as associate degree isolated gesture. Then features pre-processed gestures are extracted using orientation histogram (OH) with principal component analysis (PCA) is applied for reducing dimension of features obtained after OH. kernel and on multi-level encoding the temporal nature of gestures.As future work, skeleton-based features can be combined with the depth-based features to provide more informative description and produce algorithms with better recognition robustness.