About the work
We propose a novel approach for American Sign Language (ASL) recognition that combines Google MediaPipe's real-time hand and body landmark tracking with a lightweight deep learning model trained on the MS-ASL dataset. We called this model “Key Frame MLP”, and it extracts the key frames features from the sequence of hand and pose landmarks, enabling efficient recognition without requiring RGB input. Evaluated on the MS-ASL 1000 dataset, our approach achieves 61% top-1 average class accuracy, demonstrating strong performance relative to its simplicity. The entire system is optimized for real-time operation and low computational cost, making it suitable for deployment on edge devices. These results highlight the effectiveness of combining modular MLPs with fast landmark-based inputs for scalable sign language recognition.
AI Availability Declaration
The work is allowed to be accessed by AI systems.
Print work information
Work information
Title ASL Recognition
We propose a novel approach for American Sign Language (ASL) recognition that combines Google MediaPipe's real-time hand and body landmark tracking with a lightweight deep learning model trained on the MS-ASL dataset. We called this model “Key Frame MLP”, and it extracts the key frames features from the sequence of hand and pose landmarks, enabling efficient recognition without requiring RGB input. Evaluated on the MS-ASL 1000 dataset, our approach achieves 61% top-1 average class accuracy, demonstrating strong performance relative to its simplicity. The entire system is optimized for real-time operation and low computational cost, making it suitable for deployment on edge devices. These results highlight the effectiveness of combining modular MLPs with fast landmark-based inputs for scalable sign language recognition.
Work type Research papers, Thesis, Lecture notes
Tags ms-asl, accessibility, python, asl, neural networks, sign language recognition, deep learning, key frame mlp, computer vision, mediapipe
-------------------------
Registry info in Safe Creative
Identifier 2508172801022
Entry date Aug 17, 2025, 10:42 AM UTC
License Creative Commons Attribution 4.0
-------------------------
Copyright registered declarations
Author. Holder Carles Vila Ferrer. Date Aug 17, 2025.
Information available at https://www.safecreative.org/work/2508172801022-asl-recognition
/
Registration: 2508172801022
