stgloorious / ocr_mnist_digits

Demonstration of simple handwritten digit recognition using a neural network in Python. Based on a book by Tariq Rashid. The neural network is able to decipher greyscale 28 x 28 pictures of numerical digits 0-9 with a very high success rate. It uses MNIST data for training and testing but can also be used with other similar data.

OCR_Mnist_Digits

Demonstration of handwritten digit recognition with a neural network. Uses Mnist data set.

Based on a book by Tariq Rashid "Neurale Netzwerke selbst programmieren" (Übersetzung Frank Langenau, O'Reilly).

Their Github can be found here.

The model is first trained with a dataset of 60'000 samples of labeled, handwritten digits. After that, it is tested with a labeled set containing 10'000 unseen samples. Some falsely identified digits are displayed and a performance rating is given. The trained network can also be stored in a file to save time and to be able to experiment with different testing data later in time.

Typical accuracy is up to 97.5 %. The data set is not included but can be found here: Training data, Testing data

Take a look at my data generating tool

Doxygen Docs