A Unified Learning Approach for Hand Gesture Recognition and Fingertip Detection

Thumbnail Image

Files

2101.02047.pdf (1.79 MB)

Links to Files

https://arxiv.org/abs/2101.02047

Permanent Link

http://hdl.handle.net/11603/20970

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Student Collection

Author/Creator

Author/Creator ORCID

Date

Type of Work

journal articles preprints
Text

Department

Program

Citation of Original Publication

Mohammad Mahmudul Alam, Mohammad Tariqul Islam and S. M. Mahbubur Rahman,A Unified Learning Approach for Hand Gesture Recognition and Fingertip Detection, https://arxiv.org/abs/2101.02047

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Attribution 4.0 International

Subjects

Abstract

In human-computer interaction or sign language interpretation, recognizing hand gestures and detecting fingertips become ubiquitous in computer vision research. In this paper, a unified approach of convolutional neural network for both hand gesture recognition and fingertip detection is introduced. The proposed algorithm uses a single network to predict the probabilities of finger class and positions of fingertips in one forward propagation of the network. Instead of directly regressing the positions of fingertips from the fully connected layer, the ensemble of the position of fingertips is regressed from the fully convolutional network. Subsequently, the ensemble average is taken to regress the final position of fingertips. Since the whole pipeline uses a single network, it is significantly fast in computation. The proposed method results in remarkably less pixel error as compared to that in the direct regression approach and it outperforms the existing fingertip detection approaches including the Heatmap-based framework.