Recognition of sign language hand gestures using leap motion sensor based on threshold and ANN models

Abstract

Hand gesture recognition is a topic that is still investigated by many scientists for numerous useful aspects. This research investigated hand gestures for sign language number zero to nine. The hand gesture recognition was based on finger direction patterns. The finger directions were detected by a Leap Motion Controller. Finger direction pattern modeling was based on two methods: threshold and artificial neural network. Threshold model 1 contained 15 rules based on the range of finger directions on each axis. Threshold model 2 was developed from model 1 based on the behavior of finger movements when the subject performed hand gestures. The ANN model of the system was designed with four neurons at the output layer, 15 neurons at the input layer, seven neurons at the first hidden layer and 5 neurons at the second hidden layer. The artificial neural network used the logsig as the activation function. The result shows that the first threshold model has the lowest accuracy because the rule is too complicated and rigid. The threshold model 2 can improve the threshold model, but it still needs development to reach better accuracy. The ANN model gave the best result among the developed model with 98% accuracy. LMC produces useful biometric data for hand gesture recognition.

Virtual reality's effects on air crash accident investigation learning interaction

“…The Real time visualisation connected with the modified programmable universal machine was also highlighted by other studies [28], [29]. Another example of the application of visualisation may be seen in the interpretation of sign language through the use of hand movements [30]. In a similar vein, Chae et al [31] proposed a VR based hand gesture identification system that used a density based CNN.…”

Electric Wheelchair Control Using Wrist Rotation Based on Analysis of Muscle Fatigue

“…3. The LMC is positioned at approximately 25 cm under the right armrest, to provide maximum accuracy [37].…”

Control and Implementation of Positioning System with Symmetrical Topology for Precision Manufacturing

“…us, the CAN-based motion control system achieves desired control performance even under lower transmission rate or heavier message loading on the bus. B. Chen et al [15,16] introduced three configurations of the networked synchronized motion control systems. In a networked synchronized motion control system, short communication cycle is needed in order to upgrade the synchronization accuracy.…”