In the present scenario, vision based hand gesture recognition has become a highly emerging research area for the purpose of human computer interaction. Such recognition systems are deployed to serve as a replacement for the commonly used human-machine interactive devices such as keyboard, mouse, joystick etc. in real world situations. The major challenges faced by a vision based hand gesture recognition system include recognition in complex background, in dynamic background, in presence of multiple gestures in the background, under variable lighting condition, under different viewpoints etc. In the context of sign language recognition, which is a highly demanding application of hand gesture recognition system, coarticulation detection is a challenging task. The main objective of this chapter is to provide a general overview of vision based hand gesture recognition system as well as to bring into light some of the research works that have been done in this field.

Human Computer Interaction (HCI) has become very important in today's world. Existing HCI techniques like keyboard, mouse, joysticks etc. limit the speed and naturalness of our interaction. Hand gestures provide a more natural way of communicating with the computer. Hand segmentation is the most crucial step in every hand gesture recognition system. All subsequent steps greatly depend on the quality of segmentation. If data is lost due to improper segmentation, it can hardly be recovered in the later stages of gesture recognition process. In this paper, we present a robust and effective method of hand segmentation which overcomes problems such as skin color detection, complex background removal, complexity from multiple gesturers in front of the camera and variable lighting condition.

No abstract

Automatic sign language recognition (SLR) is a current area of research as this is meant to serve as a substitute for sign language interpreters. In this paper, we present the design of a continuous SLR system that can extract out the meaningful signs and consequently recognize them. Here, we have used height of the hand trajectory as a salient feature for separating out the meaningful signs from the movement epenthesis patterns. Further, we have incorporated a unique set of spatial and temporal features for efficient recognition of the signs encapsulated within the continuous sequence. The implementation of an efficient hand segmentation and hand tracking technique makes our system robust to complex background as well as background with multiple signers. Experiments have established that our proposed system can identify signs from a continuous sign stream with a 92.8% spotting rate.

No abstract