get_digits.py

import os
from PIL import Image
import numpy as np

files = [f for f in os.listdir("handwriting/numbers/")]
files = ["handwriting/numbers/" + f for f in files]

STANDARD_SIZE = (50, 50)
def get_image_data(filename):
    img = Image.open(filename)
    img = img.getdata()
    img = img.resize(STANDARD_SIZE)
    img = map(list, img)
    img = np.array(img)
    s = img.shape[0] * img.shape[1]
    img_wide = img.reshape(1, s)
    return img_wide[0]

data = []
labels = []
print "extracting features..."
for f in files:
    data.append(get_image_data(f))
    labels.append(int(f.split(".")[0][-1]))
print "done."