Virtual Handwritten Recognition for Advanced Smart Learning Process

This paper proposes an idea for advanced learning system to school children using virtual character recognition for smart class rooms. The proposed technique has two phases, the first phase involves in creating numerals or character input virtually. The virtual input is obtained by tracking the movement of colored blob in front of the webcam. The blob can be detected with the help of Region of Interest (ROI), and ROI can be determined by color, size, and compactness of blob. The second phase involves in recognizing the numeral or character using Support Vector Machines (SVM), since SVM is one of the most optimized techniques for an efficient learning method for recognition. The features for recognition are obtained using object representation, region representation and boundary representation. Thus the proposed system can improve the standard of smart learning system by improving the way of teaching system. IndexTerms-Blob,Boundary recognition, Object representation, Region of Interest, Region representation, Support Vector Machines.