Towards an Intelligent Framework for Pressure-based 3D Curve Drawing

TL;DR

This paper presents a novel framework that uses neural network classification and tailored signal processing techniques to improve pressure-based 3D curve drawing, making digital pressure control more natural and accurate.

Contribution

It introduces a pressure-sensitive 3D curve drawing framework that adapts signal processing techniques based on curve type using neural network classification.

Findings

Framework demonstrates improved pressure control accuracy.

Neural network effectively classifies curve types.

Customized signal processing enhances drawing naturalness.

Abstract

Pen pressure is an input channel typically available in tablet pen device. To date, little attention has been paid to the use of pressure in the domain of graphical interaction, its usage largely limited to drawing and painting program, typically for varying brush characteristic such as stroke width, opacity and color. In this paper, we explore the use of pressure in 3D curve drawing. The act of controlling pressure using pen, pencil and brush in real life appears effortless, but to mimic this natural ability to control pressure using a pressure sensitive pen in the realm of electronic medium is difficult. Previous pressure based interaction work have proposed various signal processing techniques to improve the accuracy in pressure control, but a one-for-all signal processing solution tend not to work for different curve types. We propose instead a framework which applies signal processing techniques tuned to individual curve type. A neural network classifier is used as a curve classifier. Based on the classification, a custom combination of signal processing techniques is then applied. Results obtained point to the feasibility and advantage of the approach.