Year : 2020
Mentors : Sachin Gajjar
Students involved : Sagar Maheshwari (17BEC091)
Project : Link
Abstract: I attempt to present novel input methods that helps enable byzantine free of hands interface through recognition of 3D Handwriting. As obsolete as physical input methods are becoming day by day, a new method of input was bound to be brought up. The motion is detected wirelessly by the use of the inertial measurement unit (IMU) of the Arduino 101 board. Two different approaches are discussed to tackle the continuous recognition problem. One approach is to use the Pattern Matching Engine (PME) of the Intel® CurieTM module on Arduino 101 mounted on the back of the hand. Second approach uses the IMU input to a well-structured Recurrent Neural Network. The spotting of handwriting segments is done by a support vector machine. The former approach, being indigent of memory, is not preferred over the latter. The Deep Learning approach can continuously recognize random sentences. The model was trained on 1000 freely definable vocabulary and was tested by only one person, achieving the lowest possible word error rate of 2%