American Hand Signs Dataset

This dataset consists of 17,600 labeled images of American Sign Language hand signs, including representations of the alphabets (A to Z) and the "I love you" gesture. The images are of size 300x300 pixels and contain various background and lighting conditions to ensure robustness. Each alphabet sign contains approximately 600 images. The dataset was generated using MediaPipe for hand gesture detection and was trained using TensorFlow and Keras, achieving high accuracy on the dataset.

The dataset is intended for use in the development and evaluation of machine learning models for hand gesture recognition. It is suitable for applications in sign language recognition, human-computer interaction, and other related fields. The variety in background and lighting makes it useful for real-world applications, ensuring that models trained on this dataset can generalize well to diverse environments.

Keywords: American Sign Language, Hand Gesture Recognition, MediaPipe, TensorFlow, Keras, Image Dataset, Machine Learning, Sign Language Recognition, Computer Vision.