CVAIMar 26

Dynamic LIBRAS Gesture Recognition via CNN over Spatiotemporal Matrix Representation

arXiv:2603.258630.3h-index: 1
Predicted impact top 97% in CV · last 90 daysOriginality Synthesis-oriented
AI Analysis

This work addresses gesture recognition for home automation control using LIBRAS, but it is incremental as it applies existing methods to a specific domain with limited user diversity.

The paper tackles dynamic hand gesture recognition for LIBRAS sign language by combining MediaPipe Hand Landmarker for keypoint extraction with a CNN on spatiotemporal matrices, achieving 95% accuracy in low-light and 92% in normal lighting conditions.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes