Hand Gesture Recognition Using Multivariate Fuzzy Decision Tree and User Adaptation

Abstract

As an emerging human-computer interaction (HCI) technology, recognition of human hand gesture is considered a very powerful means for human intention reading. To construct a system with a reliable and robust hand gesture recognition algorithm, it is necessary to resolve several major difficulties of hand gesture recognition, such as inter-person variation, intra-person variation, and false positive error caused by meaningless hand gestures. This paper proposes a learning algorithm and also a classification technique, based on multivariate fuzzy decision tree (MFDT). Efficient control of a fuzzified decision boundary in the MFDT leads to reduction of intra-person variation, while proper selection of a user dependent (UD) recognition model contributes to minimization of inter-person variation. The proposed method is tested first by using two benchmark data sets in UCI Machine Learning Repository and then by a hand gesture data set obtained from 10 people for 15 days. The experimental results show a discernibly enhanced classification performance as well as user adaptation capability of the proposed algorithm.

Tracking and replication of hand movements by teleguided intelligent manipulator robot

“…A large amount of research work has been performed on hand gesture recognition. Some of the most recent achievements include the work by Moon-Jin Jeon Bien, 14 who constructed a system with a reliable and robust hand gesture recognition algorithm that used an efficient control-based fuzzified decision making technique but faced difficulties when using a multivariate fuzzy decision tree. George Caridakis's 15 recognition scheme for hand gestures utilizes self-organization feature maps to model information extracted through image processing.…”

“…The morphological opening is accomplished by first scanning through all the pixels in the image and recording those that are non-zero. This is followed by the use of a union-find connected components algorithm 14 to identify those pixels that belong to each of the objects in the image. After all the objects in an image have been identified, their areas are calculated by simply counting the number of pixels in each.…”

Bangla User Adaptive Word Speech Recognition

“…Thus, the final challenge for any humancomputer interface is the user adaptability and which is what our research stresses on. Jeon, Lee and Bien (2011) stressed on this property of intelligent systems by stating that, the intra-person variation problem in any paradigm of human-computer interaction can be tackled by using fuzzy logic owing to its robustness property against uncertainty and ambiguity. This certainly put solid foundation on the justification of the application of fuzzy logic over HMM techniques in speech recognition.…”