Perspective Transform OMR Sheet - OpenCV Python

Question

I am trying to make a perspective transformation with OpenCV in python. I want to align the image and find the coordinates of top left top right and bottom left and bottom right contours. here is my code so far where I can identify all the contours.

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(3,3),0)
edges = cv2.Canny(blur,50,100)
contours, hierarchy = cv2.findContours(edges,cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) #find contours
cv2.drawContours(img,contours,-1,(0,255,0),2)
cv2.imshow('Contours',img)
cv2.waitKey(0)

Here is an image of what I get.

I'd be very thankful if you could try to help me solve this problem!

Original Image
Demo Inputs:
Demo Inputs Demo Input 1:
Demo Input 1
Demo Input 2:
Demo Input 2
Demo Input 3:
Demo Input 3
Demo Input 4:
Demo Input 4
Desired Output:
Desired Output

Please post your original input and explain better. I am sorry, I do not fully understand. Do you simply want to get the 4 corners of the page within the background of the input file? What else do you want to do with those corners? — fmw42, May 28 '22 at 21:11
the original image is the same except the green rectangles around the contours. i want to scan images with boundary rectangles like above. after scanning i want to transform the image to make it straight and find the external corners of the rectangles. [TL,TR,BL,BR] and crop the image on those 4 points. — rnative, May 29 '22 at 04:56
I have added a complete Input list and the desired output. Kindly help me achieve it. — rnative, May 29 '22 at 12:19

score 2 · Answer 1 · answered May 29 '22 at 16:18

Here is one way to do that in Python/OpenCV.

Read the input
Read the template (for its dimension)
Convert the input to gray and threshold
Pad the threshold (to preserve the corners when apply morphology)
Apply morphology close
Remove the padding
Get the largest external contour
Get its perimeter and approximate to 4 corners as the input corners for the warping
Get the output corners for the warping from the dimensions of the template
Get the perspective transformation matrix
Warp the input to match the template
Save the results

Input:

Template:

import cv2
import numpy as np

# read image
img = cv2.imread("omr_test.jpg")
hh, ww = img.shape[:2]

# read template
template = cv2.imread("omr_template.jpg")
ht, wd = template.shape[:2]

# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# do otsu threshold on gray image
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]

# pad thresh with black to preserve corners when apply morphology
pad = cv2.copyMakeBorder(thresh, 20, 20, 20, 20, borderType=cv2.BORDER_CONSTANT, value=0)

# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
morph = cv2.morphologyEx(pad, cv2.MORPH_CLOSE, kernel)

# remove padding
morph = morph[20:hh+20, 20:ww+20]

# get largest external contour
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)

# get perimeter and approximate a polygon
peri = cv2.arcLength(big_contour, True)
corners = cv2.approxPolyDP(big_contour, 0.04 * peri, True)

# draw polygon on input image from detected corners
polygon = img.copy()
cv2.polylines(polygon, [corners], True, (0,255,0), 2, cv2.LINE_AA)
# Alternate: cv2.drawContours(page,[corners],0,(0,0,255),1)

# print the number of found corners and the corner coordinates
# They seem to be listed counter-clockwise from the top most corner
print(len(corners))
print(corners)

# reformat input corners to x,y list
icorners = []
for corner in corners:
    pt = [ corner[0][0],corner[0][1] ]
    icorners.append(pt)
icorners = np.float32(icorners)

# get corresponding output corners form width and height
ocorners = [ [0,0], [0,ht], [wd,ht], [wd,0] ]
ocorners = np.float32(ocorners)

# get perspective tranformation matrix
M = cv2.getPerspectiveTransform(icorners, ocorners)

# do perspective 
warped = cv2.warpPerspective(img, M, (wd, ht))

# write results
cv2.imwrite("omr_test_thresh.jpg", thresh)
cv2.imwrite("omr_test_morph.jpg", morph)
cv2.imwrite("omr_test_polygon.jpg", polygon)
cv2.imwrite("omr_test_warped.jpg", warped)

# display it
cv2.imshow("thresh", thresh)
cv2.imshow("pad", pad)
cv2.imshow("morph", morph)
cv2.imshow("polygon", polygon)
cv2.imshow("warped", warped)
cv2.waitKey(0)

Threshold Image:

Morphology Image:

Polygon Image:

Warped Input:

Dear Fred. Thank you so very much for your kind answer. this answer for sure helped me move in a positive direction. what can we do if the input image is tilted counter clockwise? because the transformation isn't working correctly. — rnative, May 29 '22 at 19:21

fmw42 · Accepted Answer · 2022-05-30T04:09:35.727

Here is a correction that solves whether the input image is rotated cw or ccw in Python/OpenCV.

Read the input
Read the template (for its dimensions)
Convert the input to gray and threshold
Pad the threshold (to preserve the corners when applying morphology)
Apply morphology close
Remove the padding
Get the largest external contour
Get its perimeter and approximate to 4 corners as the input corners for the warping
Sort the corners by Y and test the first two sorted corners for X. If diff=X2-X1 is negative, then the output corners need to be list in a slightly differently order.
Get the output corners for the warping from the dimensions of the template and the diff of the sorted corners.
Get the perspective transformation matrix
Warp the input to match the template
Save the results

Input 1 (cw rotated):

:

Input 2 (ccw rotated):

import cv2
import numpy as np

# read image
#img = cv2.imread("omr_test.jpg")
img = cv2.imread("omr_test2.jpg")
hh, ww = img.shape[:2]

# read template
template = cv2.imread("omr_template.jpg")
ht, wd = template.shape[:2]

# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# do otsu threshold on gray image
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]

# pad thresh with black to preserve corners when apply morphology
pad = cv2.copyMakeBorder(thresh, 20, 20, 20, 20, borderType=cv2.BORDER_CONSTANT, value=0)

# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
morph = cv2.morphologyEx(pad, cv2.MORPH_CLOSE, kernel)

# remove padding
morph = morph[20:hh+20, 20:ww+20]

# get largest external contour
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)

# get perimeter and approximate a polygon
peri = cv2.arcLength(big_contour, True)
corners = cv2.approxPolyDP(big_contour, 0.04 * peri, True)

# draw polygon on input image from detected corners
polygon = img.copy()
cv2.polylines(polygon, [corners], True, (0,255,0), 2, cv2.LINE_AA)

# print the number of found corners and the corner coordinates
# They seem to be listed counter-clockwise from the top most corner
print(len(corners))
print(corners)

# reformat input corners to x,y list
sortcorners = []
for corner in corners:
    pt = [ corner[0][0],corner[0][1] ]
    sortcorners.append(pt)
icorners = np.float32(sortcorners)

# sort corners on y
def takeSecond(elem):
    return elem[1]
sortcorners.sort(key=takeSecond)

# check if second corner x is left or right of first corner x
x1 = sortcorners[0][0]
x2 = sortcorners[1][0]
diff = x2 - x1
print(x1, x2)

# get corresponding output corners from width and height
if diff >= 0:
    ocorners = [ [0,0], [0,ht], [wd,ht], [wd,0] ]
else:
    ocorners = [ [wd,0], [0,0], [0,ht], [wd,ht]]
ocorners = np.float32(ocorners)

# get perspective tranformation matrix
M = cv2.getPerspectiveTransform(icorners, ocorners)

# do perspective 
warped = cv2.warpPerspective(img, M, (wd, ht))

# write results
cv2.imwrite("omr_test2_thresh.jpg", thresh)
cv2.imwrite("omr_test2_morph.jpg", morph)
cv2.imwrite("omr_test2_polygon.jpg", polygon)
cv2.imwrite("omr_test2_warped.jpg", warped)

# display it
cv2.imshow("thresh", thresh)
cv2.imshow("pad", pad)
cv2.imshow("morph", morph)
cv2.imshow("polygon", polygon)
cv2.imshow("warped", warped)
cv2.waitKey(0)

Result for first input (cw rotated):

Result for second input (ccw rotated):

Thank you Fred. you just made my day twice in a row!! – rnative May 29 '22 at 21:17 — rnative, May 29 '22 at 21:17

Perspective Transform OMR Sheet - OpenCV Python

2 Answers2