deskew_mnist.py

import cv2
import glob, tqdm

from scipy.ndimage import interpolation
import numpy as np

def moments(image):
    c0,c1 = np.mgrid[:image.shape[0],:image.shape[1]] # A trick in numPy to create a mesh grid
    totalImage = np.sum(image) #sum of pixels
    m0 = np.sum(c0*image)/totalImage #mu_x
    m1 = np.sum(c1*image)/totalImage #mu_y
    m00 = np.sum((c0-m0)**2*image)/totalImage #var(x)
    m11 = np.sum((c1-m1)**2*image)/totalImage #var(y)
    m01 = np.sum((c0-m0)*(c1-m1)*image)/totalImage #covariance(x,y)
    mu_vector = np.array([m0,m1]) # Notice that these are \mu_x, \mu_y respectively
    covariance_matrix = np.array([[m00,m01],[m01,m11]]) # Do you see a similarity between the covariance matrix
    return mu_vector, covariance_matrix


def deskew(image):
    c,v = moments(image)
    alpha = v[0,1]/v[0,0]
    affine = np.array([[1,0],[alpha,1]])
    ocenter = np.array(image.shape)/2.0
    offset = c-np.dot(affine,ocenter)
    return interpolation.affine_transform(image,affine,offset=offset)

import os, glob2
def process(dir):
    for cur in tqdm.tqdm(glob2.glob(dir + '/**/*.png')):
        im = cv2.imread(cur, 0)
        res = deskew(im)
        res = cv2.fastNlMeansDenoising(res)
        cv2.imwrite(cur, res)

process('data/mnist/trainset')
process('data/mnist/testset')