ISL Fingerspelling Image Dataset

This dataset consists of high-resolution images of static hand gestures representing Indian Sign Language (ISL) fingerspelling for alphabets (A\u2013Z) and numbers (1\u20139). It includes approximately 400 images per class, covering a total of 35 classes, resulting in over 14,000 labeled images. The gestures were performed by 3 different individuals to introduce inter-subject variability and enhance model generalization. All images were captured against two distinct backgrounds under varied lighting conditions to simulate real-world scenarios. This dataset is ideal for developing and evaluating computer vision and deep learning models for ISL recognition, hand gesture classification, and gesture-based human-computer interaction (HCI). It serves as a valuable resource for researchers working on sign language recognition and accessibility technologies.