Hand Posture and Gesture Recognition Technology This section explains the requirements for hand posture and gesture recognition. It describes the two main solutions for collecting the data required to perform recognition, the glove-based solution and the camera- or vision-based solution, and examines the advantages and disadvantages of each. Collecting Data for Postures and Hand Gestures The first step in using posture and hand gestures in computer applications is collecting raw data. This raw data is then analyzed using various recognition algorithms (see Section 3) to extract meaning or context from the data in order to perform tasks in the application. Raw data is collected in three ways. The first is to use user-worn input devices. This setup usually consists of one or two instrumented gloves that measure various joint angles of the hand and a six-degree-of-freedom (6DOF) tracking device that collects data on the position and orientation of the hand. The second way to collect raw hand data is to use a computer vision approach whereby one or more cameras collect images of the user's hands. The cameras capture an arbitrary number of images per second and send them to image processing routines to perform posture and gesture recognition, as well as 3D triangulation to find the position of the hands in space. The third way to collect raw data is to combine the previous two methods in a hybrid approach with the hope of achieving a more accurate level of recognition by using the two data streams to reduce mutual error. Very little work has been done on hybrid tracking for hand posture and gesture recognition, but this type of tracking has been successful in augmented reality systems such as Auer[7] and State[98], and may well be... medium of paper ......sizes the voltage output of each sensor and then changes the value using a linear calibration function. This function uses gain and offset values ​​to represent the slope and y-intercept of the linear equation. This equation allows for software calibration of the glove and therefore makes it more robust for a variety of hand sizes. The author's personal experience and an evaluation by Kessler et al. [50] suggest that the CyberGlove has an accuracy within one degree of flexion. It works well for recognizing both simple and complex postures and gestures (Wexelblat[116] and Fels[35] verify this claim). The only downside about the CyberGlove is its price; the 18-sensor model is available for $9800 and the 22-sensor model for $14,500. But even though the glove is expensive, it is the best glove-based technology available for accurate and robust hand posture and gesture recognition.