A supervised classification model, which predicts the labels of a Modified MNIST dataset. 1st place in Kaggle competition (https://www.kaggle.com/c/modified-mnist/overview)
0
stars
0
forks
source link
Create a system to extract numbers fro the training images #2
Each training image contains three numbers. We want to extract each number to make it look like a sample from the original MNIST training dataset.
Probably should use openCV to get the contours and thresholding etc...
Example:
We want to extract the 8, 5 and 2 to look like this: