Index Finger Motion Recognition Using Self-Advise Support Vector Machine

Because of the functionality of an index finger, the disability of its motion in the modern age can decrease the person’s quality of life. As a part of rehabilitation therapy, the recognition of the index finger motion for rehabilitation purposes should be done properly. This paper proposes a novel recognition system of the index finger motion suing a cutting-edge method and its improvements. The proposed system consists of combination of feature extraction method, a dimensionality reduction and well-known classifier, Support Vector Machine (SVM). An improvement of SVM, Self-advise SVM (SA-SVM), is tested to evaluate and compare its performance with the original one. The experimental result shows that SA-SVM improves the classification performance by on average 0.63 %.