Optimizing Hand Gesture Recognition:. Enhanced Methods Using MFSM, MHMM, and DTW

      Аннотация: One very interesting field of research in Pattern Recognition that has gained much attention in recent times is Gesture Recognition. Gesture may be described as the manner in which a person moves his body and limbs to express an idea or sentiment. People frequently use gestures to communicate in their day-to-day life. Therefore, gestures are a natural means of conveying information. This has motivated to use gestures for communicating with computers. Thus, gestures provide an attractive and user-friendly alternative to interface devices like keyboard, mouse and joysticks in human-computer interaction (HCI). Accordingly, the basic aim of gesture recognition research is to build a system which can identify/interpret specific human gestures automatically and use them to convey information.The main objective of this book is to study methods based on state-of-the-art techniques. The thesis addresses to the development of hand gesture recognition using Video Object Plane Generation Hand Segmentation, Modified Finite State Machine (MFSM), Modified Hidden Markov Model (MHMM) and Dynamic Time Warping (DTW).

Ключевые слова: Hand Gesture, segmentation, Finite State Machine, Hidden Markov Model, Dynamic time warping