Other researchers, though using a 3D sensor, do not consider at all the third dimension in the features used to represent the hand postures. That is the case of [5], where the authors use a 3D depth camera but only consider the 2D outline of the hand segment in their recognition process. A 3D image describes better the hand posture than a 2D image. It provides less occlusion. The 2D image is the projection in a given plane of the 3D image. Two different 3D hand postures projected on a particular plane can provide exactly the same information in the 2D images which as a consequence cannot be used to differentiate them.The design of a rotation invariant system has not been successfully achieved so far. Indeed many researchers consider the principal component analysis to evaluate the orientation of the 2D hand image but, as acknowledged by [6], this method is not always accurate. Not only has the estimation of the rotation of a 2D hand segment not been successful so far but, furthermore, the evaluation of the orientation of a 3D hand segment is not considered in most existing approaches.To test their hand motion classification using a multi-channel surface electromyography sensor, [7] only consider five testing images per gesture. Contrary to most of the studies on this topic, a significant number of testing samples has been considered to validate the proposed algorithm. Indeed, testing more than 1,000 images per gesture in average instead of five provides more evidence on the robustness of the methodology.The objective of the current study is to design a range camera based system where a high number of postures taken from the alphabet of the Regorafenib IC50 American Sign Language can be recognized in real-time. Contrary to existing methods, the current one allows hand posture recognition independently of the orientation of the user’s hand. It makes use of a 3D signature, considers only one training image per posture and uses a significant number of testing images for its evaluation.The term ��gesture�� means that the character considered cannot be performed without a dynamic movement of the hand while ��posture�� refers to a character that can be fully described with a static position of the hand. In this paper ��Static gestures�� doesn’t mean that the user is not moving his hand. ��Static gestures�� or ��postures�� relate to the different characters of the American Sign Language Alphabet as shown in the paper except ��Z�� and ��J��. Once the user performs one of them, he can rotate and move his hand in whatever direction he wants to. The objective is to make the system recognize this posture no matter the position of the user’s hand.This paper is structured as follows: Section 2 reviews the literature on methods used for hand gesture recognition. Section 3 describes the set up of the experiment and Section 4, the segmentation process used. The methodologies considered for tracking the hand motion are provided in Section 5.