A REVIEW PAPER ON INERTIAL SENSOR BASED ALPHABET RECOGNITION USING CLASSIFIERS

Abstract

In today’s computer world human computer interface is important part. Pen with inbuilt inertial sensors” are new instruments in industry that may completely replace the computer keyboard. These devices aim to capture human handwriting or drawing motions in 3D space in real-time and use the sensor data for recognition or information retrieval at a later time. The proposed An inertial sensor based “Inertial pen” for handwritten character and gesture trajectory recognition consist of a microcontroller, and an RF wireless transmission module for sensing and collecting inertial sensor data of handwritten alphabets. Trajectory recognition algorithm composes of the procedures of sensor data acquisition, signal pre-processing, feature generation, feature selection, and feature extraction. Users can use the pen with inertial sensors to write alphabets, data is wirelessly transmitted to a computer for online trajectory recognition. The algorithm is capable of translating time-series sensor signals into important feature vectors. These vectors are used as input to classifiers.