Created
April 3, 2023 10:48
-
-
Save addam/0b30e1edc767dccb2306c35bfa2536b9 to your computer and use it in GitHub Desktop.
robust fit 2D polynomial to an image. Given a photo of a paper, makes it perfectly white.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sys import argv | |
import cv2 | |
import numpy as np | |
import scipy | |
iterations = 2 | |
def grid(shape): | |
y = np.linspace(0, 1, shape[0]) | |
x = np.linspace(0, 1, shape[1]) | |
xx, yy = np.meshgrid(x, y) | |
return np.dstack([xx**0, xx, yy, xx**2, xx*yy, yy**2]) | |
def solve(mat, b): | |
x, res, rank, sing = np.linalg.lstsq(mat, b, rcond=None) | |
return x | |
def paint(params, shape): | |
mat = grid(shape) | |
return (mat.reshape((-1, 6)) @ params.reshape((6, 1))).reshape(shape) | |
def fit(img, mask): | |
vmask = mask | |
mat = grid(mask.shape)[vmask] | |
b = img[vmask] | |
return solve(mat, b) | |
def background(color_img, quantile=0.9): | |
result = list() | |
for c in range(color_img.shape[2]): | |
img = color_img[..., c] | |
bg = cv2.dilate(img, None) | |
for i in range(iterations): | |
diff = np.abs(img - bg) | |
mask = diff <= np.quantile(diff, quantile) | |
params = fit(img, mask) | |
bg = paint(params, img.shape[:2]) | |
result.append(paint(params, img.shape[:2])) | |
return np.dstack(result) | |
def augment(img, quantile=0.9): | |
mask = np.random.uniform(0, 1, img.shape) > quantile | |
img[mask] = 0 | |
def normalize(img, bg, black=0.05, white=0.5): | |
result = img - bg | |
low = np.quantile(result, black) | |
high = np.quantile(result, white) | |
return (result - low) / (high - low) | |
is_visual = False | |
if __name__ == "__main__": | |
if len(argv) > 1: | |
for filename in argv[1:]: | |
img = cv2.imread(filename) / 255.0 | |
cv2.imshow("img", img) | |
bg = background(img, 0.5) | |
if is_visual: | |
cv2.imshow("background", bg) | |
cv2.waitKey() | |
else: | |
result = normalize(img, bg) | |
cv2.imwrite(f"{filename[:-4]}.norm.jpg", result * 255.0) | |
else: | |
params = np.array([1, 0, 0, -1, 2, -1]) | |
img = paint(params, (300, 200)) | |
augment(img, 0.5) | |
if is_visual: | |
cv2.imshow("img", img) | |
cv2.waitKey() | |
else: | |
cv2.imwrite("normalize_background.png", img * 255.0) | |
print(params) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment