عنوان مقاله [English]
Gesture recognition is an important task in areas such as human computer interaction, sign language recognition and robotics.This paper presents a Gesture reconition algorithm for recognizing American Sin Lanuage. In this article propose a highly precise method to recognize static gestures from a depth image and fuzzy decision tree. At first, article uses of depth images to derive rotation-, translation- and scale- invariant features. Then, by using of a fuzzy multi-layered random forest, trains to classify the feature vectors, which yields to the reconition of the hand signs. For improve classifing, uses flexibility of fuzzy logic and the fuzzy sets. This approach combines the robustness of multiple classifier systems, the power of the randomness to increase the diversity of the trees, and the flexibility of fuzzy logic and fuzzy sets for imperfect data management.