Digitizing Handwriting with a Sensor Pen: A Writer-Independent Recognizer

TL;DR

This paper introduces a writer-independent online handwriting recognition system using a sensor-equipped pen that captures multiple signals, enabling real-time recognition of Latin alphabets on plain paper without user-specific training.

Contribution

It presents a novel sensor-based pen system and a CNN model for writer-independent handwriting recognition on normal paper, addressing previous limitations of sensor-based approaches.

Findings

Achieved promising recognition accuracy with CNN on collected dataset.

System operates in real-time without user-specific training.

Demonstrated practicality for real-world handwriting recognition.

Abstract

Online handwriting recognition has been studied for a long time with only few practicable results when writing on normal paper. Previous approaches using sensor-based devices encountered problems that limited the usage of the developed systems in real-world applications. This paper presents a writer-independent system that recognizes characters written on plain paper with the use of a sensor-equipped pen. This system is applicable in real-world applications and requires no user-specific training for recognition. The pen provides linear acceleration, angular velocity, magnetic field, and force applied by the user, and acts as a digitizer that transforms the analogue signals of the sensors into timeseries data while writing on regular paper. The dataset we collected with this pen consists of Latin lower-case and upper-case alphabets. We present the results of a convolutional neural network model for letter classification and show that this approach is practical and achieves promising results for writer-independent character recognition. This work aims at providing a realtime handwriting recognition system to be used for writing on normal paper.