# A comprehensive image dataset of American Sign Language hand gestures

## TL;DR

This paper introduces ASL-HG, a new dataset of American Sign Language gestures to improve gesture recognition and assistive technologies.

## Contribution

ASL-HG distinguishes between the letter 'O' and digit '0' using a two-handed sign and provides preprocessed versions for immediate use.

## Key findings

- ASL-HG contains 36,000 images across 36 classes with balanced distribution across participants, genders, and skin tones.
- The dataset includes both raw images and a MediaPipe-processed version with predefined train–test splits.
- ASL-HG aims to support robust and fair ASL recognition systems and reduce communication barriers for deaf and speech-impaired users.

## Abstract

We present ASL-HG, a comprehensive American Sign Language (ASL) image dataset designed to advance gesture recognition and assistive technologies. The collection contains 36,000 static images across 36 classes, covering the full English alphabet (A–Z) and digits (0–9). Data were captured from 10 volunteers in Mirpur, Dhaka, Bangladesh, with each participant contributing 100 samples per class, ensuring a balanced distribution across subjects, genders, and skin tones. Unlike many existing ASL datasets, ASL-HG explicitly distinguishes between the letter “O” and the digit “0″ by including the standard two-handed ASL “zero” sign used in practical alphanumeric communication. The dataset is released in two complementary forms: raw images with natural indoor and outdoor backgrounds, and a MediaPipe-processed version with hand-segmented crops and predefined 80–20 train–test splits. This design supports both custom pre-processing and immediate model training. ASL-HG is intended to serve as a benchmark resource for developing robust and fair ASL recognition systems, reducing communication barriers for deaf and speech-impaired users, and enabling broader research in gesture-based human–computer interaction.