Salvato in:
Dettagli Bibliografici
Autore principale: Moreira, Jasmine
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.25863
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912984223186944
author Moreira, Jasmine
author_facet Moreira, Jasmine
contents This paper proposes a method for dynamic hand gesture recognition based on the composition of two models: the MediaPipe Hand Landmarker, responsible for extracting 21 skeletal keypoints of the hand, and a convolutional neural network (CNN) trained to classify gestures from a spatiotemporal matrix representation of dimensions 90 by 21 of those keypoints. The method is applied to the recognition of LIBRAS (Brazilian Sign Language) gestures for device control in a home automation system, covering 11 classes of static and dynamic gestures. For real-time inference, a sliding window with temporal frame triplication is used, enabling continuous recognition without recurrent networks. Tests achieved 95\% accuracy under low-light conditions and 92\% under normal lighting. The results indicate that the approach is effective, although systematic experiments with greater user diversity are needed for a more thorough evaluation of generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25863
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Dynamic LIBRAS Gesture Recognition via CNN over Spatiotemporal Matrix Representation
Moreira, Jasmine
Computer Vision and Pattern Recognition
Artificial Intelligence
This paper proposes a method for dynamic hand gesture recognition based on the composition of two models: the MediaPipe Hand Landmarker, responsible for extracting 21 skeletal keypoints of the hand, and a convolutional neural network (CNN) trained to classify gestures from a spatiotemporal matrix representation of dimensions 90 by 21 of those keypoints. The method is applied to the recognition of LIBRAS (Brazilian Sign Language) gestures for device control in a home automation system, covering 11 classes of static and dynamic gestures. For real-time inference, a sliding window with temporal frame triplication is used, enabling continuous recognition without recurrent networks. Tests achieved 95\% accuracy under low-light conditions and 92\% under normal lighting. The results indicate that the approach is effective, although systematic experiments with greater user diversity are needed for a more thorough evaluation of generalization.
title Dynamic LIBRAS Gesture Recognition via CNN over Spatiotemporal Matrix Representation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.25863