The dataset was built by capturing the static gestures of the American Sign Language (ASL) alphabet, from 8 people, except for the letters J and Z, since they are dynamic gestures. To capture the images, we used a Logitech Brio webcam, with a resolution of 1920 × 1080 pixels, in a university laboratory with artificial lighting. By extracting only the hand region, we defined an area of 400 × 400 pixels for the final image of our dataset.