Convolutional Neural Network for Hand Gesture Recognition using 8 different Gestures

This paper describes the implementation of hand gesture recognition which uses deep learning algorithm as CNN. Therefore, proposed technique is hassle free as control is not based on joysticks or switches. There are eight conditions considered for hand gesture as up, stop , right, No ,Left ,Down, clockwise and anticlockwise. There are many researchers worked on this area using different sensors, machine learning algorithms and deep learning algorithms. Limitations of the state of art techniques are studied in this paper and designed a new modified convolutional neural network (CNN) for gesture recognition. Dataset is created which generates 1000 Gray scale images for each type of gesture. Training modified CNN model gives prediction accuracy of 98.4024 percent while random forest machine learning classifier gives prediction accuracy of 69 ppercent. It is observed that proposed model gives better accuracy compared to state of art technique for hand gesture recognition. Obtained hand gesture class can be send to controller for further controlling in future like home automation robotic car movement etc. Keywords: Robot Car Movement, Gesture Recognition, Random Forest, Deep Learning, CNN, layer modification. )