Accurate Personal Identification by Hand Gesture Recognition

Gesture recognition is a topic in computer science and language technology with the goal of interpreting
human gestures via mathematical algorithms. Gestures can originate from any bodily motion or state but
commonly originate from the face or hand. Current focuses in the field include emotion recognition from
face and hand gesture recognition. In this paper, we present an automatic hand gesture recognition
approach from different images based on scale invariant feature transform and shape based features. We
present an approach for identifying and recognizing different hand sign expression of the human. The
objective of the proposed system is to design an approach which automatically detects the hand and
identifies the different hand sign expression of the human. The proposed approach presents a very low
degree of complexity, which makes it suitable for real-time applications, the feature points or key points
detected and mapped along with the hand sign image. Depending upon the selected features and the
measured region properties of the human hand sign, the different sign expression of the human was further
classified using SVM. The proposed method is superior compared with other state-of-the-art approaches and
that the analysis of the general image quality of the hand sign images reveals highly valuable information