In this paper, we propose a real time 3D gesture recognition system that relies on the state based approach. The novelty of this work is the introduction of probabilistic neural networks (PNNs) to characterize the uncertain boundaries of each state. The 3D gestures are modeled as a sequence of states in a configuration space; the number of states and their spatial parameters are calculated by dynamic k-means clustering on the training data of the gesture without temporal information. Gesture recognition is performed using a simple Finite State Machine (FSM), where, each state transition depends only on the output of its corresponding PNN and optionally on its time restrictions (minimum and maximum time permitted in the state). If a recognizer reaches its final state, then it could be said that a gesture is recognized. The approach is illustrated with the implementation of a real time system that recognizes the semantic meaning of seven basic gestures of the Indian Dance, the description of the system and the technologies used, it will be described in detail in the paper.

This work presents a study of performance improvement of unskilled people to drawn simple sketches. We have assisted the unskilled people when drawn using a haptic interface which acts as a virtual guide taking advantage of its force feedback capabilities. In the first part of the study, an application has been developed to extract fixed templates from image files; the application extract the principal edges in the images to build output trajectories (templates) that are used by haptic interface controller, after that, the user can "fill" the virtual templates with the assistance of the force feedback capabilities of the interface. Based on the obtained results for fixed templates, a second application was developed; the user can generate interactive templates indicating where he/she desires to put a geometrical template (circle, line or arc) inside the haptic interface's workplace; once that the position of the template is defined, the interface shows its position graphically and then user can fill it assisted by the haptic interface force feedback.

In this paper the design and construction of a novel wireless Dataglove based on new flexible goniometric sensor technology is described. The device is characterized by a low cost and rugged construction and no requires calibration before its use. Indeed, the sensors used are purely goniometric, so they are not sensible to dimensions of the user's hand. The Dataglove can measure the angular displacement of the fingers hand using 11 sensors, each sensor has a resolution of 0.2 degrees, with 3 degree of accuracy in the worst case. The communication between the Dataglove and its computer Host is carried out using a 2,4 gigahertz wireless Bluetooth radio protocol, in a guaranteed range up to 10 meters with a refresh rate of 100 Hz.

Achieving realistic rendering of thin and spatially sharp objects (needles, for example) is an important open problem in computer haptics. Intrinsic mechanical properties of users, such as limb inertia, as well as mechanical and bandwidth limitations in haptic interfaces make this a very challenging problem. A successful rendering algorithm should also provide stable contact with a haptic virtual object. Here, perceptual illusions have been used to overcome some of these limitations to render objects with perceived sharp features. The feasibility of the approach was tested using a haptics-to-vision matching task. Results suggest that lateral-force-based illusory shapes can be used to render sharp objects, while also providing stable contact during virtual object exploration