Work

PalmPen: A Palmprint Positioning Pen

Year: 2025

Type: article

Abstract: Palm-based interaction offers unique advantages in tasks requiring minimal visual attention and low cognitive load, thanks to the sensitive tactile feedback of the palm and the body's proprioceptive abilities. However, current research in this field faces challenges like limited detection precision and complex equipment. This paper presents PalmPen, a novel pen-shaped camera device that relies on computer vision algorithms to enable absolute positioning and continuous tracking on the palm. We created a training dataset containing full and partial palmprints with corresponding positional data using cameras and an optical tracker. A deep learning network was created to predict the location of partial palmprints within a full palmprint. PalmPen achieved a mean positioning error of 2.74 mm in the experiments. A user study with 12 participants demonstrated that PalmPen offers superior positioning accuracy and input efficiency over other methods. Additionally, properties such as touch pressure and rotation angles can be inferred from palmprint sequences, extending PalmPen's application range.

Source: Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies

DOI: 10.1145/3749549

Authors: Jinyang Yu, Zhaoguo Wang, Zhiyu Pan, Jianjiang Feng, Jie Zhou

Institution: Tsinghua University

Language: English

Topic: Interactive and Immersive Displays

Subfield: Human-Computer Interaction

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Natural Science Foundation of China

Award: G2556395234