A Review On An Inertial Pen for Handwriting and Gesture Recognition Using Adaptive DTW Algorithm

ELECTRONIC ENGINEERING

In this review paper we are going to discuss a systematic adaptive dynamic time wrapping algorithm framework that can construct effective classifier for hand writing & gesture recognition. Review of digital pen for handwritten digit and gesture recognition using adaptive DTW algorithm based on accelerometer is discuss for the identification of 2-d handwriting and 3-d gesture. For this implementation we are going to use tri-axial accelerometer, tri-axial magnetometer, gyroscope, microcontroller, and RF wireless transmition module for sensing and collecting acceleration of handwriting and gesture. The proposed adaptive dynamic time wrapping algorithm includes the procedure of inertial signal acquisition, single pre-processing, motion detection, template selection and recognition. We integrate signals collected from accelerometer, a gyroscope, which might reduce the accuracy of the orientation estimation. We also have developed minimal inter-class to maximal inter-class based template selection method for ADTW recognizer to obtain a superior class separation for improved recognition.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.