Digit Draw: Neural Network Digit Recognition
MrEconomical (2189)

Neural Network Recognition

Digit Draw is a program to recognize 28x28 pixel hand-drawn digits. It uses a neural network made with brain.js trained on MNIST data (a database of hand-drawn digits). It takes in an array of 28x28 for the darkness of each pixel and outputs an array of length 10 of the certainty for each digit. The neural network works fairly well and is able to predict the digit most of the time.


Input Size: 784
Hidden Layers: 1
Hidden Layer Neurons: 392
Activation Function: Sigmoid
Output Size: 10


brain.js - https://github.com/BrainJS
MNIST - http://yann.lecun.com/exdb/mnist/

You are viewing a single comment. View All
CProgrammer4 (0)

All the other digits work, though. Really good job, man! I don't know anything about NN or web design, so this is WAY better than I could do. I am not trying to poop on your parade or anything. Maybe you just need a larger variety of picture training data of crooked, sloppy, photoshopped/distorted, etc... numbers. You could probably draw more digits yourself, scan them in, and improve your little NN.

Don't give up, dude. This is pretty cool!