American Sign Language Image Dataset (figerspelling original + keypoints + evaluation)

The dataset consists of four folders: (1) Dataset Original, (2) Dataset Keypoints, (3) Dataset Black Background, and (4) Controlled Evaluation Dataset. Each folder contains image data, dimension 192 x 192, for each alphabet letter (static only) in American Sign Language (ASL). Under CC BY 4.0 license, researchers can re-use this dataset for ASL fingerspelling recognition and translation, as long as you give appropriate credit by citing the dataset.