Related
I have the following table:
I want to write a script that creates lines based on the natural breakages on the table text. The result would look like this:
Is there an OpenCV implementation that makes drawing these lines possible? I looked at the answers to the questions here and here, but neither worked. What is the best approach to solving this problem?
Here is one way to get the horizontal lines in Python/OpenCV by counting the number of white pixels in each row of the image to find their center y values. The vertical lines can be added by a similar process.
Input:
import cv2
import numpy as np
# read image
img = cv2.imread("table.png")
hh, ww = img.shape[:2]
# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# threshold gray image
thresh = cv2.threshold(gray, 254, 255, cv2.THRESH_BINARY)[1]
# count number of non-zero pixels in each row
count = np.count_nonzero(thresh, axis=1)
# threshold count at ww (width of image)
count_thresh = count.copy()
count_thresh[count==ww] = 255
count_thresh[count<ww] = 0
count_thresh = count_thresh.astype(np.uint8)
# get contours
contours = cv2.findContours(count_thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# loop over contours and get bounding boxes and ycenter and draw horizontal line at ycenter
result = img.copy()
for cntr in contours:
x,y,w,h = cv2.boundingRect(cntr)
ycenter = y+h//2
cv2.line(result, (0,ycenter), (ww-1,ycenter), (0, 0, 0), 2)
# write results
cv2.imwrite("table_thresh.png", thresh)
cv2.imwrite("table_lines.png", result)
# display results
cv2.imshow("THRESHOLD", thresh)
cv2.imshow("RESULT", result)
cv2.waitKey(0)
Threshold Image:
Result with lines:
ADDITION
Here is an alternate method that is slightly simpler. It averages the image down to one column rather than counting white pixels.
import cv2
import numpy as np
# read image
img = cv2.imread("table.png")
hh, ww = img.shape[:2]
# convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# average gray image to one column
column = cv2.resize(gray, (1,hh), interpolation = cv2.INTER_AREA)
# threshold on white
thresh = cv2.threshold(column, 254, 255, cv2.THRESH_BINARY)[1]
# get contours
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# loop over contours and get bounding boxes and ycenter and draw horizontal line at ycenter
result = img.copy()
for cntr in contours:
x,y,w,h = cv2.boundingRect(cntr)
ycenter = y+h//2
cv2.line(result, (0,ycenter), (ww-1,ycenter), (0, 0, 0), 2)
# write results
cv2.imwrite("table_lines2.png", result)
# display results
cv2.imshow("RESULT", result)
cv2.waitKey(0)
Result:
I would like to get from the image in the groups that are on the image
I have managed to remove first contour (as described below), but issue is that when I try to read the text, I have some missing text, I expect that this is because of other contours that have stayed on the image, but while I try to remove them, I loose the grouping or part of text...
for i in range(len(contours)):
if 800 < cv2.contourArea(contours[i]) < 2000:
x, y, width, height = cv2.boundingRect(contours[i])
roi = img[y:y + height, x:x + width]
roi_h = roi.shape[0]
roi_w = roi.shape[1]
resize_roi = cv2.resize(roi,(int(roi_w*6),int(roi_h*6)), interpolation=cv2.INTER_LINEAR)
afterd = cv2.cvtColor(resize_roi, cv2.COLOR_BGR2GRAY)
retim, threshm = cv2.threshold(afterd, 210, 225, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
contoursm, hierarchym = cv2.findContours(threshm, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
mask = np.ones(resize_roi.shape[:2], dtype="uint8") * 255
for m in range(len(contoursm)):
if 10000 < cv2.contourArea(contoursm[m]) < 33000:
cv2.drawContours(mask, contoursm, m, 0, 7)
afterd = cv2.bitwise_not(afterd)
afterd = cv2.bitwise_and(afterd, afterd, mask=mask)
afterd = cv2.bitwise_not(afterd)
print(pytesseract.image_to_string(afterd, lang='eng', config='--psm 3'))
Instead of dealing with all the boxes, I suggest deleting them by finding connected components, and filling the large clusters with background color.
You may use the following stages:
Convert image to Grayscale, apply threshold, and invert polarity.
Delete all clusters having more than 100 pixels (assume letters are smaller).
Dilate thresh for uniting text areas to single "blocks".
Find contours on the dilated thresh image.
Find bounding rectangles, and apply OCR to the rectangle.
Here is the complete code sample:
import numpy as np
import cv2
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe' # I am using Windows
img = cv2.imread('img.png') # Read input image
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # Convert to Grayscale.
ret, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU) # Convert to binary and invert polarity
nlabel,labels,stats,centroids = cv2.connectedComponentsWithStats(thresh, connectivity=8)
thresh_size = 100
# Delete all lines by filling large clusters with zeros.
for i in range(1, nlabel):
if stats[i, cv2.CC_STAT_AREA] > thresh_size:
thresh[labels == i] = 0
# Dilate thresh for uniting text areas to single blocks.
dilated_thresh = cv2.dilate(thresh, np.ones((5,5)))
# Find contours on dilated thresh
contours, hierarchy = cv2.findContours(dilated_thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
# Iterate contours, find bounding rectangles
for c in contours:
# Get bounding rectangle
x, y, w, h = cv2.boundingRect(c)
# Draw green rectangle for testing
cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), thickness = 1)
# Get the slice with the text (slice with margins).
afterd = thresh[y-3:y+h+3, x-3:x+w+3]
# Show afterd as image for testing
# cv2.imshow('afterd', afterd)
# cv2.waitKey(100)
# The OCR works only when image is enlarged and black text?
resized_afterd = cv2.resize(afterd, (afterd.shape[1]*5, afterd.shape[0]*5), interpolation=cv2.INTER_LANCZOS4)
print(pytesseract.image_to_string(255 - resized_afterd, lang='eng', config='--psm 3'))
cv2.imshow('thresh', thresh)
cv2.imshow('img', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Result strings after OCR:
DF6DF645
RFFTW
2345
2277
AABBA
DF1267
ABCET5456
Input image with green boxes around the text:
Update:
Grouping contours:
For contours contours you may use the hierarchy result of cv2.findContours with cv2.RETR_TREE.
See Contours Hierarchy documentation.
You may use the parent-child relationship for grouping contours.
Here is an incomplete sample code for using the hierarchy:
img = cv2.imread('img.png') # Read input image
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # Convert to Grayscale.
ret, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU) # Convert to binary and invert polarity
nlabel,labels,stats,centroids = cv2.connectedComponentsWithStats(thresh, connectivity=8)
thresh_boxes = np.zeros_like(thresh)
thresh_size = 100
# Delete all lines by filling large clusters with zeros.
# Make new image that contains only boxes - without text
for i in range(1, nlabel):
if stats[i, cv2.CC_STAT_AREA] > thresh_size:
thresh[labels == i] = 0
thresh_boxes[labels == i] = 255
# Find contours on thresh_boxes, use cv2.RETR_TREE to build tree with hierarchy
contours, hierarchy = cv2.findContours(thresh_boxes, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
# Iterate contours, and hierarchy
for c, i in zip(contours, range(len(contours))):
h = hierarchy[0, i, :]
h_child = h[2]
# if contours has no child (last level)
if h_child == -1:
h_parent = h[3]
x, y, w, h = cv2.boundingRect(c)
cv2.putText(img, str(h_parent), (x+w//2-4, y+h//2+8), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=1, color=(0, 0, 255), thickness=2)
cv2.imshow('thresh', thresh)
cv2.imshow('img', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Result:
I can't seem to find a way to draw more than one contour of objects.
Input Image:
Code:
import cv2
import numpy as np
#import image
img = cv2.imread('img.png', 0)
#Thresh
ret, thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY)
#Finding the contours in the image
_, contours, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
#Convert img to RGB and draw contour
img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
cv2.drawContours(img, contours, 0, (0,0,255), 2)
#save output img
cv2.imwrite('output_img.png', img)
Output:
Only the larger object contour is drawn. How would I draw both contours?
Change the third parameter to -1(third argument is index of contours) in your drawContours which will draw all contours in your image:
cv2.drawContours(img, contours, -1, (0,0,255), 2)
If you want to draw only two contours and the first two contours are of the white objects use:
cnt1 = contours[0]
cnt2 = contours[1]
cv2.drawContours(img, [cnt1, cnt2], -1, (0,0,255), 2)
I'm trying to remove the square boxes(vertical and horizontal lines) using Hough transform in opencv (Python). The problem is none of the vertical lines are being detected. I've tried looking through contours and hierarchy but there are too many contours in this image and I'm confused how to use them.
After looking through related posts, I've played with the threshold and rho parameters but that didn't help.
I've attached the code for more details. Why does Hough transform not find the vertical lines in the image?. Any suggestions in solving this task are welcome. Thanks.
Input Image :
Hough transformed Image:
Drawing contours:
import cv2
import numpy as np
import pdb
img = cv2.imread('/home/user/Downloads/cropped/robust_blaze_cpp-300-0000046A-02-HW.jpg')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 140, 255, 0)
im2, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(img, contours, -1, (0,0,255), 2)
edges = cv2.Canny(gray,50,150,apertureSize = 3)
minLineLength = 5
maxLineGap = 100
lines = cv2.HoughLinesP(edges,rho=1,theta=np.pi/180,threshold=100,minLineLength=minLineLength,maxLineGap=maxLineGap)
for x1,y1,x2,y2 in lines[0]:
cv2.line(img,(x1,y1),(x2,y2),(0,255,0),2)
cv2.imwrite('probHough.jpg',img)
To be honest, rather than looking for the lines, I'd instead look for the white boxes.
Preparation
import cv2
import numpy as np
Load the image
img = cv2.imread("digitbox.jpg", 0)
Binarize it, so that both the boxes and the digits are black, rest is white
_, thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY)
cv2.imwrite('digitbox_step1.png', thresh)
Find contours. In this example image, it's fine to just look for external contours.
_, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
Process the contours, filtering out any with too small an area. Find convex hull of each contour, create a mask of all areas outside the contour. Store the bounding boxes of each found contour, sorted by x coordinate.
mask = np.ones_like(img) * 255
boxes = []
for contour in contours:
if cv2.contourArea(contour) > 100:
hull = cv2.convexHull(contour)
cv2.drawContours(mask, [hull], -1, 0, -1)
x,y,w,h = cv2.boundingRect(contour)
boxes.append((x,y,w,h))
boxes = sorted(boxes, key=lambda box: box[0])
cv2.imwrite('digitbox_step2.png', mask)
Dilate the mask (to shrink the black parts), to clip off any remains the the gray frames.
mask = cv2.dilate(mask, np.ones((5,5),np.uint8))
cv2.imwrite('digitbox_step3.png', mask)
Fill all the masked pixels with white, to erase the frames.
img[mask != 0] = 255
cv2.imwrite('digitbox_step4.png', img)
Process the digits as you desire -- i'll just draw the bounding boxes.
result = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
for n,box in enumerate(boxes):
x,y,w,h = box
cv2.rectangle(result,(x,y),(x+w,y+h),(255,0,0),2)
cv2.putText(result, str(n),(x+5,y+17), cv2.FONT_HERSHEY_SIMPLEX, 0.6,(255,0,0),2,cv2.LINE_AA)
cv2.imwrite('digitbox_step5.png', result)
The whole script in one piece:
import cv2
import numpy as np
img = cv2.imread("digitbox.jpg", 0)
_, thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY)
_, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
mask = np.ones_like(img) * 255
boxes = []
for contour in contours:
if cv2.contourArea(contour) > 100:
hull = cv2.convexHull(contour)
cv2.drawContours(mask, [hull], -1, 0, -1)
x,y,w,h = cv2.boundingRect(contour)
boxes.append((x,y,w,h))
boxes = sorted(boxes, key=lambda box: box[0])
mask = cv2.dilate(mask, np.ones((5,5),np.uint8))
img[mask != 0] = 255
result = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
for n,box in enumerate(boxes):
x,y,w,h = box
cv2.rectangle(result,(x,y),(x+w,y+h),(255,0,0),2)
cv2.putText(result, str(n),(x+5,y+17), cv2.FONT_HERSHEY_SIMPLEX, 0.6,(255,0,0),2,cv2.LINE_AA)
cv2.imwrite('digitbox_result.png', result)
Im trying to get the largest contour of a red book.
I've got a little problem with the code because its getting the contours of the smallest objects (blobs) instead of the largest one and I can't seem to figure out why this is happening
The code I use:
camera = cv2.VideoCapture(0)
kernel = np.ones((2,2),np.uint8)
while True:
#Loading Camera
ret, frame = camera.read()
blurred = cv2.pyrMeanShiftFiltering(frame, 3, 3)
hsv = cv2.cvtColor(blurred, cv2.COLOR_BGR2HSV)
lower_range = np.array([150, 10, 10])
upper_range = np.array([180, 255, 255])
mask = cv2.inRange(hsv, lower_range, upper_range)
dilation = cv2.dilate(mask,kernel,iterations = 1)
closing = cv2.morphologyEx(dilation, cv2.MORPH_GRADIENT, kernel)
closing = cv2.morphologyEx(dilation, cv2.MORPH_CLOSE, kernel)
#Getting the edge of morphology
edge = cv2.Canny(closing, 175, 175)
_, contours,hierarchy = cv2.findContours(edge, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# Find the index of the largest contour
areas = [cv2.contourArea(c) for c in contours]
max_index = np.argmax(areas)
cnt=contours[max_index]
x,y,w,h = cv2.boundingRect(cnt)
cv2.rectangle(frame,(x,y),(x+w,y+h),(0,255,0),2)
cv2.imshow('threshold', frame)
cv2.imshow('edge', edge)
if cv2.waitKey(1) == 27:
break
camera.release()
cv2.destroyAllWindows()
As you can see on this picture
Hopefully there is someone who can help
You can start by defining a mask in the range of the red tones of the book you are looking for.
Then you can just find the contour with the biggest area and draw the rectangular shape of the book.
import numpy as np
import cv2
# load the image
image = cv2.imread("path_to_your_image.png", 1)
# red color boundaries [B, G, R]
lower = [1, 0, 20]
upper = [60, 40, 220]
# create NumPy arrays from the boundaries
lower = np.array(lower, dtype="uint8")
upper = np.array(upper, dtype="uint8")
# find the colors within the specified boundaries and apply
# the mask
mask = cv2.inRange(image, lower, upper)
output = cv2.bitwise_and(image, image, mask=mask)
ret,thresh = cv2.threshold(mask, 40, 255, 0)
if (cv2.__version__[0] > 3):
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
else:
im2, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
if len(contours) != 0:
# draw in blue the contours that were founded
cv2.drawContours(output, contours, -1, 255, 3)
# find the biggest countour (c) by the area
c = max(contours, key = cv2.contourArea)
x,y,w,h = cv2.boundingRect(c)
# draw the biggest contour (c) in green
cv2.rectangle(output,(x,y),(x+w,y+h),(0,255,0),2)
# show the images
cv2.imshow("Result", np.hstack([image, output]))
cv2.waitKey(0)
Using your image:
If you want the book to rotate you can use rect = cv2.minAreaRect(cnt) as you can find it here.
Edit:
You should also consider other colour spaces beside the RGB, as the HSV or HLS. Usually, people use the HSV since the H channel stays fairly consistent in shadow or excessive brightness. In other words, you should get better results if you use the HSV colourspace.
In specific, in OpenCV the Hue range is [0,179]. In the following figure (made by #Knight), you can find a 2D slice of that cylinder, in V = 255, where the horizontal axis is the H and the vertical axis the S. As you can see from that figure to capture the red you need both to include the lower (e.g., H=0 to H=10) and upper region (e.g., H=170 to H=179) of the Hue values.
Use this to convert Grayscale masks to Rectangles
def mask_to_rect(image):
'''
Give rectangle cordinates according to the mask image
Params: image : (numpy.array) Gray Scale Image
Returns: Cordinates : (list) List of cordinates [x, y, w h]
'''
# Getting the Thresholds and ret
ret,thresh = cv2.threshold(image, 0, 1, 0)
# Checking the version of open cv I tried for (version 4)
# Getting contours on the bases of thresh
if (int(cv2.__version__[0]) > 3):
contours, hierarchy = cv2.findContours(thresh.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
else:
im2, contours, hierarchy = cv2.findContours(thresh.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
# Getting the biggest contour
if len(contours) != 0:
# draw in blue the contours that were founded
cv2.drawContours(output, contours, -1, 255, 3)
# find the biggest countour (c) by the area
c = max(contours, key = cv2.contourArea)
x,y,w,h = cv2.boundingRect(c)
return [x, y, w, h]
Result