I want to calculate number of pixels per grid (i.e. pixels per 11 mm) of the checkerboard. I am doing this to validate that mm/pixel calculation I obtain using calibration matrix and formula (below) is same as what I will see when I open the image in MS Paint.
For the checkerboard image (1920x1080 resolution): 11 grid x 7 grid in size with each grid as 11x 11 mm, at a distance of 500 mm (picture below).
I compute a calibration matrix using code:
import cv2
import numpy as np
import pathlib
#from utils import *
import glob
from argparse import ArgumentParser
topview_image_path = 'checkerboard_top\*.png'
camera_orientation = 'topview'
if camera_orientation == 'topview':
image_path = topview_image_path
def calibrate_chessboard(folder):
# Defining the dimensions of checkerboard
CHECKERBOARD = (6,9)
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 0.001)
# Creating vector to store vectors of 3D points for each checkerboard image
objpoints = []
# Creating vector to store vectors of 2D points for each checkerboard image
imgpoints = []
# Defining the world coordinates for 3D points
objp = np.zeros((1, CHECKERBOARD[0] * CHECKERBOARD[1], 3), np.float32)
objp[0,:,:2] = np.mgrid[0:CHECKERBOARD[0], 0:CHECKERBOARD[1]].T.reshape(-1, 2)
prev_img_shape = None
# Extracting path of individual image stored in a given directory
print("image path:", image_path)
images = glob.glob(image_path)
#images = glob.glob(f'{folder}/*.png')
# if len(images) == 0:
# images = glob.glob(f'{folder}/*.jpg')
# print(images)
for fname in images:
img = cv2.imread(fname)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# Find the chess board corners
# If desired number of corners are found in the image then ret = true
ret, corners = cv2.findChessboardCorners(gray, CHECKERBOARD, cv2.CALIB_CB_ADAPTIVE_THRESH + cv2.CALIB_CB_FAST_CHECK + cv2.CALIB_CB_NORMALIZE_IMAGE)
"""
If desired number of corner are detected,
we refine the pixel coordinates and display
them on the images of checker board
"""
if ret == True:
objpoints.append(objp)
# refining pixel coordinates for given 2d points.
corners2 = cv2.cornerSubPix(gray, corners, (11,11),(-1,-1), criteria)
imgpoints.append(corners2)
# Draw and display the corners
img = cv2.drawChessboardCorners(img, CHECKERBOARD, corners2, ret)
cv2.imshow('img',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
h,w = img.shape[:2]
"""
Performing camera calibration by
passing the value of known 3D points (objpoints)
and corresponding pixel coordinates of the
detected corners (imgpoints)
"""
ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpoints, imgpoints, gray.shape[::-1], None, None)
return [ret, mtx, dist, rvecs, tvecs]
if __name__ == '__main__':
parser = ArgumentParser()
parser.add_argument('--type', dest='type',type=str, default='topview',help='is the image topview or sideview?')
parser.add_argument('--folder', dest='folder',type=str, default='cal_images/checkerboard_topview',help='is the image topview or sideview?')
args = parser.parse_args()
WIDTH = 6
HEIGHT = 9
# Calibrate
ret, mtx, dist, rvecs, tvecs = calibrate_chessboard(args.folder)
print(mtx)
print(dist)
mtx_list = ["calibration matrix:\n", str(mtx),
"\ndistortion matrix:", str(dist)]
txt_file = "matrix_" + camera_orientation +".txt"
with open(txt_file, mode='wt', encoding='utf-8') as myfile:
myfile.write('\n'.join(mtx_list))
and get the calibration matrix as:
M = [[2.86276094e+03 0.00000000e+00 8.23315889e+02]
[0.00000000e+00 2.86846709e+03 5.80987675e+02]
[0.00000000e+00 0.00000000e+00 1.00000000e+00]]
This gives me the focal length (f) in pixel units (M[0][0]) i.e. 2862.
I then calculate size in pixels (X_sizepx) of the checkerboard grid 11 mm (X_sizemm) object at distance Z (in my case 500mm) using formula:
X_sizepx = (f/Z) * X_sizemm
Substituting all the values: f = 2862, Z =500, X_sizemm = 11, I get 62.94. So as per opencv calibration and the formula, 11mm should ~63 pixels.
I then open the checkerboard image in MS paint to see the pixel dimension of the square grid in pixels and it says 41 pixels (image below).
This is a big difference if I were to use camera calibration matrix and the the formula. Is there something I am doing wrong?
Note: Z can never be more than 530 mm if I were to assume that Z might be slightly off.
Context
My goal is to detect PV modules on the dataset of infrared images taken by a drone. I want to improve the edge detection so my algorithm performs better. Detected and labelled modules are then used to train a neural network.
Dataset
I have several hundred images taken at different times and from different altitudes. I guess their quality is not perfect - the environmental conditions could be better, e.g:
altitude - sometimes the edges between modules are not the images could be taken from a lower altitude so the edges are better visible.
capture time - sometimes the background (grass) is very hot. Most likely the images could be taken late morning/early afternoon.
However, I have to stick to what I have.
As you can see sometimes (e.g. image_3) the "middle line" is hardly visible.
Code
Preprocessing below is based on project I found on Github. Standard preprocessing and Canny Edge detection is used.
import cv2
import numpy as np
def detect_edges():
# image_path = "data/stackoverflow/TEMP_DJI_1_R (715).JPG"
# image_path = "data/stackoverflow/TEMP_DJI_6_R (720).JPG"
image_path = "data/stackoverflow/TEMP_DJI_5_R (657).JPG"
# read image
input_image = cv2.imread(image_path, cv2.IMREAD_COLOR)
cv2.imshow('input_image', input_image)
# scale image
image_scaling = 11.0
scaled_image_rgb = cv2.resize(src=input_image, dsize=(0, 0), fx=image_scaling, fy=image_scaling)
cv2.imshow('scaled_image', scaled_image_rgb)
# blur image
gaussian_blur = 7
blurred_image = cv2.blur(scaled_image_rgb, (gaussian_blur, gaussian_blur))
cv2.imshow('blurred_image', blurred_image)
# gray image
grayed_image = cv2.cvtColor(scaled_image_rgb, cv2.COLOR_BGR2GRAY)
cv2.imshow('grayed_image', grayed_image)
# red threshold
red_threshold = 120
red_channel = scaled_image_rgb[:, :, 2]
_, thresholded_image = cv2.threshold(red_channel, red_threshold, 255, 0, cv2.THRESH_BINARY)
# dilation and erosion
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 9))
closing = cv2.morphologyEx(thresholded_image, cv2.MORPH_CLOSE, kernel)
opening = cv2.morphologyEx(closing, cv2.MORPH_OPEN, kernel)
# min area
min_area = 250 * 200
contours, hierarchy = cv2.findContours(opening, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
areas = [cv2.contourArea(contour) for contour in contours]
discarded_contours = [area < min_area for area in areas]
contours = [contours[i] for i in range(len(contours)) if not discarded_contours[i]]
mask = np.zeros_like(grayed_image)
cv2.drawContours(mask, contours, -1, (255), cv2.FILLED)
mask = cv2.dilate(mask, kernel, iterations=5)
mask = cv2.blur(mask, (25, 25))
mask = mask.astype(np.float) / 255.
preprocessed_image = (grayed_image * mask).astype(np.uint8)
cv2.imshow('preprocessed_image', preprocessed_image)
hysteresis_min_thresh = 25
hysteresis_max_thresh = 40
# canny edge
canny_image = cv2.Canny(image=preprocessed_image, threshold1=hysteresis_min_thresh,
threshold2=hysteresis_max_thresh, apertureSize=3)
cv2.imshow('canny_image', canny_image)
cv2.waitKey()
Results
The results are not bad, however they must be improved before further processing.
What kind of operations would be best to distinguish panels from the background (grass)?
In the case of the images with hardly visible "middle" lines (image_3), are there any chances of finding that "internal" edge? Maybe for these images, I should rather focus on finding outer edges only and draw an artificial line in the middle to divide the whole panel into two?
I am currently working on a project, where the problem statement is to detect handwritten text from a image of a particular form. As a pre-processing step I have extracted texts in the form of bounding boxes, and I have around 1500 images of texts extracted from the image form, out of which 50 of them are handwritten.
The problem is how do I now use these extracted images to train a classifier model which will classify the images as printed or handwritten text. I have no prior knowledge of Deep learning. Any help will be appreciated. I am uploading the image and the extracted images, as well as the code to extract the texts from the images.
im_ns = cv.imread('~/Image processing/IMG_20180921_111952.png')
gray = cv.cvtColor(im_ns,cv.COLOR_BGR2GRAY)
blurred_g = cv.GaussianBlur(gray,(11,11),0)
ret, th1 = cv.threshold(blurred_g,127,255,cv.THRESH_BINARY)
th2 = cv.adaptiveThreshold(blurred_g,255,cv.ADAPTIVE_THRESH_MEAN_C,cv.THRESH_BINARY,11,2)
th3 = cv.adaptiveThreshold(blurred_g,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,11,2)
##Detecting horizontal Lines and removing them
th3_di1 = th3_di.copy()
hor = int(round(th3_di1.shape[1]/30,0))
hor_struc = cv.getStructuringElement(cv.MORPH_RECT,(hor,1))
bw_hor_er = cv.erode(th3_di1,hor_struc,iterations=1)
bw_hor_di = cv.dilate(th3_di1,hor_struc,iterations=1)
for i in range(0,bw_hor_di.shape[0]):
for j in range(0,bw_hor_di.shape[1]):
if bw_hor_di[i,j] == 0:
th3_di1[i,j] = 255
else:
th3_di1[i,j] = th3_di1[i,j]
plt.figure(figsize=(20,25))
plt.imshow(th3_di1,'gray')
# perform a connected component analysis on the thresholded
# image, then initialize a mask to store only the "large"
# components
labels = measure.label(th3_di1, neighbors=4, background=255)
mask = np.zeros(th3_di1.shape, dtype="uint8")
plt.figure(figsize=(30,25))
plt.imshow(labels)
# loop over the unique components
for lab in np.unique(labels):
# if this is the background label, ignore it
if lab == 0:
continue
# otherwise, construct the label mask and count the
# number of pixels
labelMask = np.zeros(th3_di.shape, dtype="uint8")
labelMask[labels == lab] = 255
numPixels = cv.countNonZero(labelMask)
# if the number of pixels in the component is sufficiently
# large, then add it to our mask of "large blobs"
if numPixels > 8:
mask = cv.add(mask, labelMask)
plt.figure(figsize=(30,24))
plt.imshow(mask,'gray')
# find the contours in the mask, then sort them from left to
# right
cnts = cv.findContours(mask.copy(), cv.RETR_EXTERNAL,
cv.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if imutils.is_cv2() else cnts[1]
cnts = contours.sort_contours(cnts)[0]
# loop over the contours to make rectangles for the th3 image with gassian thresholding
for (i, c) in enumerate(cnts):
# draw the bright spot on the image
(x,y,w,h) = cv.boundingRect(c)
#((cX, cY), radius) = cv.minEnclosingCircle(c)
cv.rectangle(th3,(x,y),(x+w,y+h),(0,255),2)
cv.putText(th3, "",(x+w+10,y+h),0,0.3,(0,255,0))
# show the output image
cv.imshow("Image", th3)
cv.waitKey(10000)
cv.destroyAllWindows()
##Extracting the bounding boxes
idx=0
for (i, c) in enumerate(cnts):
# draw the bright spot on the image
idx += 1
x,y,w,h = cv.boundingRect(c)
roi = im_ns[y:y+h,x:x+w]
#((cX, cY), radius) = cv.minEnclosingCircle(c)
#cv.rectangle(im_ns,(x,y),(x+w,y+h),(0,255),2)
cv.imwrite(str(idx)+'.jpg',roi)
Images:
Here is the image from which I want to take the text out.
How to remove the black border and reduce the image to only 50?
Approach I took:
I tried to use corner detectors (corner peak and corner harris) and pick the first 2 coordinates from the left and last 2 coordinates from the right.
With those 4 coordinates I cropped the image and I further reduced by 5 on all sides.
Certainly not efficient way of doing it. I also looked at few segmentation also. Not able to get it right. I am using scikit image for solving this.
Using corners might not work since corner points can also be present in characters.
Here is what i tried with hough lines as described below:
1) First erode the image to minimize the gap between lines and characters
2) Use Hough line detection algorithm to detect and delete the lines
3) Dilate the image to get clear characters
4) Now we have characters and lines separated, so we can delete the lines by finding the connected components.
Here is the code implementation of the same in Python:
img = cv2.imread('D:\Image\st1.png',0)
ret, thresh = cv2.threshold(img, 150, 255, cv2.THRESH_BINARY_INV)
#dilate the image to reduce gap between characters and lines and get hough lines correctly
kernel = np.ones((3,3),np.uint8)
erosion = cv2.erode(thresh,kernel,iterations = 1)
#find canny edge image
canny = cv2.Canny(erosion,100,200)
minLineLength=img.shape[1]/4
lines = cv2.HoughLinesP(image=canny,rho=0.02,theta=np.pi/500, threshold=10,lines=np.array([]), minLineLength=minLineLength,maxLineGap=10)
a,b,c = lines.shape
# delete the lines
for i in range(a):
cv2.line(erosion, (lines[i][0][0], lines[i][0][1]), (lines[i][0][2], lines[i][0][3]), 0, 3, cv2.LINE_AA)
#erode the image
kernel = np.ones((3,3),np.uint8)
erosion = cv2.dilate(erosion, kernel, iterations=1)
# find connected components
connectivity = 4
nb_components, output, stats, centroids = cv2.connectedComponentsWithStats(erosion, connectivity, cv2.CV_32S)
sizes = stats[1:, -1]; nb_components = nb_components - 1
min_size = 250 #threshhold value for lines length
img2 = np.zeros((output.shape), np.uint8)
for i in range(0, nb_components):
if sizes[i] >= min_size:
img2[output == i + 1] = 255 #delete the line components
img = cv2.bitwise_not(img2)
Output image:
I´m trying to find the corners on a image, I don´t need the contours, only the 4 corners. I will change the perspective using 4 corners.
I´m using Opencv, but I need to know the steps to find the corners and what function I will use.
My images will be like this:(without red points, I will paint the points after)
EDITED:
After suggested steps, I writed the code: (Note: I´m not using pure OpenCv, I´m using javaCV, but the logic it´s the same).
// Load two images and allocate other structures (I´m using other image)
IplImage colored = cvLoadImage(
"res/scanteste.jpg",
CV_LOAD_IMAGE_UNCHANGED);
IplImage gray = cvCreateImage(cvGetSize(colored), IPL_DEPTH_8U, 1);
IplImage smooth = cvCreateImage(cvGetSize(colored), IPL_DEPTH_8U, 1);
//Step 1 - Convert from RGB to grayscale (cvCvtColor)
cvCvtColor(colored, gray, CV_RGB2GRAY);
//2 Smooth (cvSmooth)
cvSmooth( gray, smooth, CV_BLUR, 9, 9, 2, 2);
//3 - cvThreshold - What values?
cvThreshold(gray,gray, 155, 255, CV_THRESH_BINARY);
//4 - Detect edges (cvCanny) -What values?
int N = 7;
int aperature_size = N;
double lowThresh = 20;
double highThresh = 40;
cvCanny( gray, gray, lowThresh*N*N, highThresh*N*N, aperature_size );
//5 - Find contours (cvFindContours)
int total = 0;
CvSeq contour2 = new CvSeq(null);
CvMemStorage storage2 = cvCreateMemStorage(0);
CvMemStorage storageHull = cvCreateMemStorage(0);
total = cvFindContours(gray, storage2, contour2, Loader.sizeof(CvContour.class), CV_RETR_CCOMP, CV_CHAIN_APPROX_NONE);
if(total > 1){
while (contour2 != null && !contour2.isNull()) {
if (contour2.elem_size() > 0) {
//6 - Approximate contours with linear features (cvApproxPoly)
CvSeq points = cvApproxPoly(contour2,Loader.sizeof(CvContour.class), storage2, CV_POLY_APPROX_DP,cvContourPerimeter(contour2)*0.005, 0);
cvDrawContours(gray, points,CvScalar.BLUE, CvScalar.BLUE, -1, 1, CV_AA);
}
contour2 = contour2.h_next();
}
}
So, I want to find the cornes, but I don´t know how to use corners function like cvCornerHarris and others.
First, check out /samples/c/squares.c in your OpenCV distribution. This example provides a square detector, and it should be a pretty good start on how to detect corner-like features. Then, take a look at OpenCV's feature-oriented functions like cvCornerHarris() and cvGoodFeaturesToTrack().
The above methods can return many corner-like features - most will not be the "true corners" you are looking for. In my application, I had to detect squares that had been rotated or skewed (due to perspective). My detection pipeline consisted of:
Convert from RGB to grayscale (cvCvtColor)
Smooth (cvSmooth)
Threshold (cvThreshold)
Detect edges (cvCanny)
Find contours (cvFindContours)
Approximate contours with linear features (cvApproxPoly)
Find "rectangles" which were structures that: had polygonalized contours possessing 4 points, were of sufficient area, had adjacent edges were ~90 degrees, had distance between "opposite" vertices was of sufficient size, etc.
Step 7 was necessary because a slightly noisy image can yield many structures that appear rectangular after polygonalization. In my application, I also had to deal with square-like structures that appeared within, or overlapped the desired square. I found the contour's area property and center of gravity to be helpful in discerning the proper rectangle.
At a first glance, for a human eye there are 4 corners. But in computer vision, a corner is considered to be a point that has large gradient change in intensity across its neighborhood. The neighborhood can be a 4 pixel neighborhood or an 8 pixel neighborhood.
In the equation provided to find the gradient of intensity, it has been considered for 4-pixel neighborhood SEE DOCUMENTATION.
Here is my approach for the image in question. I have the code in python as well:
path = r'C:\Users\selwyn77\Desktop\Stack\corner'
filename = 'env.jpg'
img = cv2.imread(os.path.join(path, filename))
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) #--- convert to grayscale
It is a good choice to always blur the image to remove less possible gradient changes and preserve the more intense ones. I opted to choose the bilateral filter which unlike the Gaussian filter doesn't blur all the pixels in the neighborhood. It rather blurs pixels which has similar pixel intensity to that of the central pixel. In short it preserves edges/corners of high gradient change but blurs regions that have minimal gradient changes.
bi = cv2.bilateralFilter(gray, 5, 75, 75)
cv2.imshow('bi',bi)
To a human it is not so much of a difference compared to the original image. But it does matter. Now finding possible corners:
dst = cv2.cornerHarris(bi, 2, 3, 0.04)
dst returns an array (the same 2D shape of the image) with eigen values obtained from the final equation mentioned HERE.
Now a threshold has to be applied to select those corners beyond a certain value. I will use the one in the documentation:
#--- create a black image to see where those corners occur ---
mask = np.zeros_like(gray)
#--- applying a threshold and turning those pixels above the threshold to white ---
mask[dst>0.01*dst.max()] = 255
cv2.imshow('mask', mask)
The white pixels are regions of possible corners. You can find many corners neighboring each other.
To draw the selected corners on the image:
img[dst > 0.01 * dst.max()] = [0, 0, 255] #--- [0, 0, 255] --> Red ---
cv2.imshow('dst', img)
(Red colored pixels are the corners, not so visible)
In order to get an array of all pixels with corners:
coordinates = np.argwhere(mask)
UPDATE
Variable coor is an array of arrays. Converting it to list of lists
coor_list = [l.tolist() for l in list(coor)]
Converting the above to list of tuples
coor_tuples = [tuple(l) for l in coor_list]
I have an easy and rather naive way to find the 4 corners. I simply calculated the distance of each corner to every other corner. I preserved those corners whose distance exceeded a certain threshold.
Here is the code:
thresh = 50
def distance(pt1, pt2):
(x1, y1), (x2, y2) = pt1, pt2
dist = math.sqrt( (x2 - x1)**2 + (y2 - y1)**2 )
return dist
coor_tuples_copy = coor_tuples
i = 1
for pt1 in coor_tuples:
print(' I :', i)
for pt2 in coor_tuples[i::1]:
print(pt1, pt2)
print('Distance :', distance(pt1, pt2))
if(distance(pt1, pt2) < thresh):
coor_tuples_copy.remove(pt2)
i+=1
Prior to running the snippet above coor_tuples had all corner points:
[(4, 42),
(4, 43),
(5, 43),
(5, 44),
(6, 44),
(7, 219),
(133, 36),
(133, 37),
(133, 38),
(134, 37),
(135, 224),
(135, 225),
(136, 225),
(136, 226),
(137, 225),
(137, 226),
(137, 227),
(138, 226)]
After running the snippet I was left with 4 corners:
[(4, 42), (7, 219), (133, 36), (135, 224)]
UPDATE 2
Now all you have to do is just mark these 4 points on a copy of the original image.
img2 = img.copy()
for pt in coor_tuples:
cv2.circle(img2, tuple(reversed(pt)), 3, (0, 0, 255), -1)
cv2.imshow('Image with 4 corners', img2)
Here's an implementation using cv2.goodFeaturesToTrack() to detect corners. The approach is
Convert image to grayscale
Perform canny edge detection
Detect corners
Optionally perform 4-point perspective transform to get top-down view of image
Using this starting image,
After converting to grayscale, we perform canny edge detection
Now that we have a decent binary image, we can use cv2.goodFeaturesToTrack()
corners = cv2.goodFeaturesToTrack(canny, 4, 0.5, 50)
For the parameters, we give it the canny image, set the maximum number of corners to 4 (maxCorners), use a minimum accepted quality of 0.5 (qualityLevel), and set the minimum possible Euclidean distance between the returned corners to 50 (minDistance). Here's the result
Now that we have identified the corners, we can perform a 4-point perspective transform to obtain a top-down view of the object. We first order the points clockwise then draw the result onto a mask.
Note: We could have just found contours on the Canny image instead of doing this step to create the mask, but pretend we only had the 4 corner points to work with
Next we find contours on this mask and filter using cv2.arcLength() and cv2.approxPolyDP(). The idea is that if the contour has 4 points, then it must be our object. Once we have this contour, we perform a perspective transform
Finally we rotate the image depending on the desired orientation. Here's the result
Code for only detecting corners
import cv2
image = cv2.imread('1.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
canny = cv2.Canny(gray, 120, 255, 1)
corners = cv2.goodFeaturesToTrack(canny,4,0.5,50)
for corner in corners:
x,y = corner.ravel()
cv2.circle(image,(x,y),5,(36,255,12),-1)
cv2.imshow('canny', canny)
cv2.imshow('image', image)
cv2.waitKey()
Code for detecting corners and performing perspective transform
import cv2
import numpy as np
def rotate_image(image, angle):
# Grab the dimensions of the image and then determine the center
(h, w) = image.shape[:2]
(cX, cY) = (w / 2, h / 2)
# grab the rotation matrix (applying the negative of the
# angle to rotate clockwise), then grab the sine and cosine
# (i.e., the rotation components of the matrix)
M = cv2.getRotationMatrix2D((cX, cY), -angle, 1.0)
cos = np.abs(M[0, 0])
sin = np.abs(M[0, 1])
# Compute the new bounding dimensions of the image
nW = int((h * sin) + (w * cos))
nH = int((h * cos) + (w * sin))
# Adjust the rotation matrix to take into account translation
M[0, 2] += (nW / 2) - cX
M[1, 2] += (nH / 2) - cY
# Perform the actual rotation and return the image
return cv2.warpAffine(image, M, (nW, nH))
def order_points_clockwise(pts):
# sort the points based on their x-coordinates
xSorted = pts[np.argsort(pts[:, 0]), :]
# grab the left-most and right-most points from the sorted
# x-roodinate points
leftMost = xSorted[:2, :]
rightMost = xSorted[2:, :]
# now, sort the left-most coordinates according to their
# y-coordinates so we can grab the top-left and bottom-left
# points, respectively
leftMost = leftMost[np.argsort(leftMost[:, 1]), :]
(tl, bl) = leftMost
# now, sort the right-most coordinates according to their
# y-coordinates so we can grab the top-right and bottom-right
# points, respectively
rightMost = rightMost[np.argsort(rightMost[:, 1]), :]
(tr, br) = rightMost
# return the coordinates in top-left, top-right,
# bottom-right, and bottom-left order
return np.array([tl, tr, br, bl], dtype="int32")
def perspective_transform(image, corners):
def order_corner_points(corners):
# Separate corners into individual points
# Index 0 - top-right
# 1 - top-left
# 2 - bottom-left
# 3 - bottom-right
corners = [(corner[0][0], corner[0][1]) for corner in corners]
top_r, top_l, bottom_l, bottom_r = corners[0], corners[1], corners[2], corners[3]
return (top_l, top_r, bottom_r, bottom_l)
# Order points in clockwise order
ordered_corners = order_corner_points(corners)
top_l, top_r, bottom_r, bottom_l = ordered_corners
# Determine width of new image which is the max distance between
# (bottom right and bottom left) or (top right and top left) x-coordinates
width_A = np.sqrt(((bottom_r[0] - bottom_l[0]) ** 2) + ((bottom_r[1] - bottom_l[1]) ** 2))
width_B = np.sqrt(((top_r[0] - top_l[0]) ** 2) + ((top_r[1] - top_l[1]) ** 2))
width = max(int(width_A), int(width_B))
# Determine height of new image which is the max distance between
# (top right and bottom right) or (top left and bottom left) y-coordinates
height_A = np.sqrt(((top_r[0] - bottom_r[0]) ** 2) + ((top_r[1] - bottom_r[1]) ** 2))
height_B = np.sqrt(((top_l[0] - bottom_l[0]) ** 2) + ((top_l[1] - bottom_l[1]) ** 2))
height = max(int(height_A), int(height_B))
# Construct new points to obtain top-down view of image in
# top_r, top_l, bottom_l, bottom_r order
dimensions = np.array([[0, 0], [width - 1, 0], [width - 1, height - 1],
[0, height - 1]], dtype = "float32")
# Convert to Numpy format
ordered_corners = np.array(ordered_corners, dtype="float32")
# Find perspective transform matrix
matrix = cv2.getPerspectiveTransform(ordered_corners, dimensions)
# Return the transformed image
return cv2.warpPerspective(image, matrix, (width, height))
image = cv2.imread('1.png')
original = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
canny = cv2.Canny(gray, 120, 255, 1)
corners = cv2.goodFeaturesToTrack(canny,4,0.5,50)
c_list = []
for corner in corners:
x,y = corner.ravel()
c_list.append([int(x), int(y)])
cv2.circle(image,(x,y),5,(36,255,12),-1)
corner_points = np.array([c_list[0], c_list[1], c_list[2], c_list[3]])
ordered_corner_points = order_points_clockwise(corner_points)
mask = np.zeros(image.shape, dtype=np.uint8)
cv2.fillPoly(mask, [ordered_corner_points], (255,255,255))
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
cnts = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.015 * peri, True)
if len(approx) == 4:
transformed = perspective_transform(original, approx)
result = rotate_image(transformed, -90)
cv2.imshow('canny', canny)
cv2.imshow('image', image)
cv2.imshow('mask', mask)
cv2.imshow('transformed', transformed)
cv2.imshow('result', result)
cv2.waitKey()
find contours with RETR_EXTERNAL option.(gray -> gaussian filter -> canny edge -> find contour)
find the largest size contour -> this will be the edge of the rectangle
find corners with little calculation
Mat m;//image file
findContours(m, contours_, hierachy_, RETR_EXTERNAL);
auto it = max_element(contours_.begin(), contours_.end(),
[](const vector<Point> &a, const vector<Point> &b) {
return a.size() < b.size(); });
Point2f xy[4] = {{9000,9000}, {0, 1000}, {1000, 0}, {0,0}};
for(auto &[x, y] : *it) {
if(x + y < xy[0].x + xy[0].y) xy[0] = {x, y};
if(x - y > xy[1].x - xy[1].y) xy[1] = {x, y};
if(y - x > xy[2].y - xy[2].x) xy[2] = {x, y};
if(x + y > xy[3].x + xy[3].y) xy[3] = {x, y};
}
xy[4] will be the four corners.
I was able to extract four corners this way.
Apply houghlines to the canny image - you will get a list of points
apply convex hull to this set of points