Modelpublic

sid220/asl-now-fingerspelling

sourceHugging Facemitupdated 3y agoView on Hugging Face

0likes4downloads

Model Card

ASLNow!

ASLNow! is a web app designed to make learning ASL fingerspelling easy and fun! You can try it live at asl-now.vercel.app.

Demo: https://www.youtube.com/watch?v=Wi5tAxVasq8

Model

This model, trained on the isolated fingerspelling dataset is licensed under the MIT License. It will be updated frequently as more data is collected.

Format

[image]

Input

21 hand landmarks, each composed of x, y and z coordinates. The x and y coordinates are normalized to [0.0, 1.0] by the image width and height, respectively. The z coordinate represents the landmark depth, with the depth at the wrist being the origin. The smaller the value, the closer the landmark is to the camera. The magnitude of z uses roughly the same scale as x.

Hand Landmarks From: https://developers.google.com/mediapipe/solutions/vision/hand_landmarker

Example:

[
  # Landmark 1
  [x, y, z],
  # Landmark 2
  [x, y, z],
  ...
  # Landmark 20
  [x, y, z]
  # Landmark 21
  [x, y, z]
]

Output

The probability of each class, where classes are defined as such:

json

{
    "A": 0,
    "B": 1,
    "C": 2,
    "D": 3,
    "E": 4,
    "F": 5,
    "G": 6,
    "H": 7,
    "I": 8,
    "J": 9,
    "K": 10,
    "L": 11,
    "M": 12,
    "N": 13,
    "O": 14,
    "P": 15,
    "Q": 16,
    "R": 17,
    "S": 18,
    "T": 19,
    "U": 20,
    "V": 21,
    "W": 22,
    "X": 23,
    "Y": 24,
    "Z": 25
}