Related
I want to remove the text on the edged in the image
I have used the following code but it does not work it also remove the text in the center
Input:
Output:
import cv2
import matplotlib.pyplot as plt
import glob
import os
import numpy as np
def crop_buttom_text(img):
""" Remove the text from the bottom edge of img """
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
#blur = cv2.GaussianBlur(gray, (9,9), 0) # No need for blurring
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Create rectangular structuring element and dilate
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (30, 1)) # Use horizontal line as kernel - dilate horizontally.
dilate = cv2.dilate(thresh, kernel, iterations=1)
#kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (10,10))
#dilate = cv2.morphologyEx(dilate, cv2.MORPH_OPEN, kernel) # No need for opening
# Find contours and draw rectangle
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[-2] # [-2] indexing takes return value before last (due to OpenCV compatibility issues).
#cnts = cnts[0] if len(cnts) == 2 else cnts[1] # [-2] is shorter....
res_img = img.copy() # Copy img to res_img - in case there is no edges text.
for c in cnts:
x, y, w, h = cv2.boundingRect(c)
y2 = y + h # Bottom y coordinate of the bounding rectangle
if (y2 >= img.shape[0]):
# If the rectangle touches the bottom of the img
res_img = res_img[0:y-1, :].copy() # Crop rows from first row to row y-1
return res_img
def remove_lines(image_path,outdir):
image = cv2.imread(image_path)
img1 = crop_buttom_text(image)
img2 = crop_buttom_text(np.rot90(img1)) # Rotate by 90 degrees and crop.
img3 = crop_buttom_text(np.rot90(img2)) # Rotate by 90 degrees and crop.
img4 = crop_buttom_text(np.rot90(img3)) # Rotate by 90 degrees and crop.
output_img = np.rot90(img4)
cv2.imwrite(os.path.join(outdir,os.path.basename(image_path)), output_img)
for jpgfile in glob.glob(r'/content/Dataset/*'):
print(jpgfile)
remove_lines(jpgfile,r'/content/output')
How can i modify the above code to remove the text around the edge
How do you remove the text which is at the edge? Here is a rough way to attack the problem: remove every connected component which touches the border.
To solve this, you can add a 1 pixel border, extract the connected components and then use the one corresponding to the border as a binary mask.
The mask becomes
The result is
Notice how a 7 and few commas get removed as well.
from cv2 import cv2
import numpy as np
# Load original image
img = cv2.imread('kShDc.jpg', cv2.IMREAD_GRAYSCALE)
# Save original dimensions
h, w = img.shape[:2]
# Ensure only bilevel image with white as foreground
_, bimg = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY_INV)
# Add one pixel border
bimg = cv2.copyMakeBorder(bimg, 1, 1, 1, 1, cv2.BORDER_CONSTANT, None, 255)
# Extract connected components (Spaghetti is the fastest algorithm)
nlabels, label_image = cv2.connectedComponentsWithAlgorithm(bimg, 8, cv2.CV_32S, cv2.CCL_SPAGHETTI)
# Make a mask with the edge label (0 is background, 1 is the first encountered label, i.e. the border)
ccedge = np.uint8((label_image != 1)*255)
cv2.imwrite("mask.png", ccedge, [cv2.IMWRITE_PNG_BILEVEL, 1])
# Zero every pixel touching the border
bimg = cv2.bitwise_and(bimg, ccedge)
# Remove border and invert again
bimg = 255 - bimg[1:h+1, 1:w+1]
# Save result
cv2.imwrite("result.png", bimg, [cv2.IMWRITE_PNG_BILEVEL, 1])
I have an image like so,
By using the following code,
import numpy as np
import cv2
# load the image
image = cv2.imread("frame50.jpg", 1)
#color boundaries [B, G, R]
lower = [0, 3, 30]
upper = [30, 117, 253]
# 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, 50, 255, 0)
if (int(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:
# find the biggest countour (c) by the area
c = max(contours, key = cv2.contourArea)
x,y,w,h = cv2.boundingRect(c)
ROI = image[y:y+h, x:x+w]
cv2.imshow('ROI',ROI)
cv2.imwrite('ROI.png',ROI)
cv2.waitKey(0)
I get the following cropped image,
I would like to retain all data within the orange hand-drawn boundary including the boundary itself and blackout the rest.
In the image above the data outside the orange boundary is still there. I do not want that. How do i fill the mask which is like this now so that i can retain data inside the orange boundary,
I would still like to retain other properties like the rectangular bounding box. I don't want anything else to change. How do I go about this?
Thanks.
As you desire (in your comments to my previous answer) to have the outer region to be black rather than transparent, you can do that as follows in Python/OpenCV with a couple of lines changed to multiply the mask by the input rather than put the mask into the alpha channel.
Input:
import numpy as np
import cv2
# load the image
image = cv2.imread("frame50.jpg")
#color boundaries [B, G, R]
lower = (0, 70, 210)
upper = (50, 130, 255)
# threshold on orange color
thresh = cv2.inRange(image, lower, upper)
# get largest contour
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
x,y,w,h = cv2.boundingRect(big_contour)
# draw filled contour on black background
mask = np.zeros_like(image)
cv2.drawContours(mask, [big_contour], 0, (255,255,255), -1)
# apply mask to input image
new_image = cv2.bitwise_and(image, mask)
# crop
ROI = new_image[y:y+h, x:x+w]
# save result
cv2.imwrite('frame50_thresh.jpg',thresh)
cv2.imwrite('frame50_mask.jpg',mask)
cv2.imwrite('frame50_new_image2.jpg',new_image)
cv2.imwrite('frame50_roi2.jpg',ROI)
# show images
cv2.imshow('thresh',thresh)
cv2.imshow('mask',mask)
cv2.imshow('new_image',new_image)
cv2.imshow('ROI',ROI)
cv2.waitKey(0)
new_image after applying the mask:
cropped roi image:
Here is one way to do that in Python/OpenCV.
Read the input
Threshold on the orange color
Find the (largest) contour and get its bounding box
Draw a white filled contour on a black background as a mask
Create a copy of the input with an alpha channel
Copy the mask into the alpha channel
Crop the ROI
Save the results
Input:
import numpy as np
import cv2
# load the image
image = cv2.imread("frame50.jpg")
#color boundaries [B, G, R]
lower = (0, 70, 210)
upper = (50, 130, 255)
# threshold on orange color
thresh = cv2.inRange(image, lower, upper)
# get largest contour
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
x,y,w,h = cv2.boundingRect(big_contour)
# draw filled contour on black background
mask = np.zeros_like(image)
cv2.drawContours(mask, [big_contour], 0, (255,255,255), -1)
# put mask into alpha channel of input
new_image = cv2.cvtColor(image, cv2.COLOR_BGR2BGRA)
new_image[:,:,3] = mask[:,:,0]
# crop
ROI = new_image[y:y+h, x:x+w]
# save result
cv2.imwrite('frame50_thresh.jpg',thresh)
cv2.imwrite('frame50_mask.jpg',mask)
cv2.imwrite('frame50_new_image.jpg',new_image)
cv2.imwrite('frame50_roi.png',ROI)
# show images
cv2.imshow('thresh',thresh)
cv2.imshow('mask',mask)
cv2.imshow('new_image',new_image)
cv2.imshow('ROI',ROI)
cv2.waitKey(0)
Threshold image:
Mask Image:
New image with mask in alpha channel:
Cropped ROI
Need your help. Now I'm writing python script to recognize text in a shape. This shape can be captured from RTSP (IP Camera) at any angle.
For the example see attached file. My code is here, but coords to crop rotated shape is sets manually
import cv2
import numpy as np
def main():
fn = cv2.VideoCapture("rtsp://admin:Admin123-#172.16.10.254")
flag, img = fn.read()
cnt = np.array([
[[64, 49]],
[[122, 11]],
[[391, 326]],
[[308, 373]]
])
print("shape of cnt: {}".format(cnt.shape))
rect = cv2.minAreaRect(cnt)
print("rect: {}".format(rect))
box = cv2.boxPoints(rect)
box = np.int0(box)
print("bounding box: {}".format(box))
cv2.drawContours(img, [box], 0, (0, 255, 0), 2)
img_crop, img_rot = crop_rect(img, rect)
print("size of original img: {}".format(img.shape))
print("size of rotated img: {}".format(img_rot.shape))
print("size of cropped img: {}".format(img_crop.shape))
new_size = (int(img_rot.shape[1]/2), int(img_rot.shape[0]/2))
img_rot_resized = cv2.resize(img_rot, new_size)
new_size = (int(img.shape[1]/2)), int(img.shape[0]/2)
img_resized = cv2.resize(img, new_size)
cv2.imshow("original contour", img_resized)
cv2.imshow("rotated image", img_rot_resized)
cv2.imshow("cropped_box", img_crop)
# cv2.imwrite("crop_img1.jpg", img_crop)
cv2.waitKey(0)
def crop_rect(img, rect):
# get the parameter of the small rectangle
center = rect[0]
size = rect[1]
angle = rect[2]
center, size = tuple(map(int, center)), tuple(map(int, size))
# get row and col num in img
height, width = img.shape[0], img.shape[1]
print("width: {}, height: {}".format(width, height))
M = cv2.getRotationMatrix2D(center, angle, 1)
img_rot = cv2.warpAffine(img, M, (width, height))
img_crop = cv2.getRectSubPix(img_rot, size, center)
return img_crop, img_rot
if __name__ == "__main__":
main()
example pic
You may start with the example in the following post.
The code sample detects the license plate, and it also detects your "shape" with text.
After detecting the "shape" with the text, you may use the following stages:
Apply threshold the cropped area.
Find contours, and find the contour with maximum area.
Build a mask, and mask area outside the contour (like in the license plate example).
Use minAreaRect (as fmw42 commented), and get the angle of the rectangle.
Rotate the cropped area (by angle+90 degrees).
Apply OCR using pytesseract.image_to_string.
Here is the complete code:
import cv2
import numpy as np
import imutils
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe' # I am using Windows
# Read the input image
img = cv2.imread('Admin123.jpg')
# Reused code:
# https://stackoverflow.com/questions/60977964/pytesseract-not-recognizing-text-as-expected/60979089#60979089
################################################################################
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #convert to grey scale
gray = cv2.bilateralFilter(gray, 11, 17, 17)
edged = cv2.Canny(gray, 30, 200) #Perform Edge detection
cnts = cv2.findContours(edged.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:10]
screenCnt = None
# loop over our contours
for c in cnts:
# approximate the contour
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.018 * peri, True)
# if our approximated contour has four points, then
# we can assume that we have found our screen
if len(approx) == 4:
screenCnt = approx
break
# Masking the part other than the "shape"
mask = np.zeros(gray.shape,np.uint8)
new_image = cv2.drawContours(mask,[screenCnt],0,255,-1,)
new_image = cv2.bitwise_and(img,img,mask=mask)
# Now crop
(x, y) = np.where(mask == 255)
(topx, topy) = (np.min(x), np.min(y))
(bottomx, bottomy) = (np.max(x), np.max(y))
cropped = gray[topx:bottomx+1, topy:bottomy+1]
################################################################################
# Apply threshold the cropped area
_, thresh = cv2.threshold(cropped, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
# Find contours
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
cnts = imutils.grab_contours(cnts)
# Get contour with maximum area
c = max(cnts, key=cv2.contourArea)
# Build a mask (same as the code above)
mask = np.zeros(cropped.shape, np.uint8)
new_cropped = cv2.drawContours(mask, [c], 0, 255, -1)
new_cropped = cv2.bitwise_and(cropped, cropped, mask=mask)
# Draw green rectangle for testing
test = cv2.cvtColor(new_cropped, cv2.COLOR_GRAY2BGR)
cv2.drawContours(test, [c], -1, (0, 255, 0), thickness=2)
# Use minAreaRect as fmw42 commented
rect = cv2.minAreaRect(c)
angle = rect[2] # Get angle of the rectangle
# Rotate the cropped rectangle.
rotated_cropped = imutils.rotate(new_cropped, angle + 90)
# Read the text in the "shape"
text = pytesseract.image_to_string(rotated_cropped, config='--psm 3')
print("Extracted text is:\n\n", text)
# Show images for testing:
cv2.imshow('cropped', cropped)
cv2.imshow('thresh', thresh)
cv2.imshow('test', test)
cv2.imshow('rotated_cropped', rotated_cropped)
cv2.waitKey(0)
cv2.destroyAllWindows()
OCR output result:
AB12345
DEPARTMENT OF
INFORMATION
COMMUNICATION
TECHNOLOGY
cropped:
thresh:
test:
rotated_cropped:
Good day,
I have used cv2.findContours on an image. After that, I have extracted the contour and hierarchy information. From there, how do I filter and draw only contours without child (which from my understanding has a value of -1 in the 3rd column in the hierarchy array)?
below is my code:my image
from imutils import perspective
from imutils import contours
import numpy as np
import imutils
import cv2
img = cv2.imread('TESTING.png')
imgs = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edged = imgs
cnts = cv2.findContours(edged,cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
hierarchy = cnts[2]
ChildContour = hierarchy [0, :,2]
WithoutChildContour = (ChildContour==-1).nonzero()[0]
cntsA = cnts[0] if imutils.is_cv2() else cnts[1]
if not cntsA:
print ("no contours")
(cntsB, _) = contours.sort_contours(cntsA)
orig = cv2.imread('TESTING.png')
for c in cntsB:
if cv2.contourArea(c) < 100:
continue
box = cv2.minAreaRect(c)
box = cv2.boxPoints(box) if imutils.is_cv2() else cv2.boxPoints(box)
box = np.array(box, dtype="int")
box = perspective.order_points(box)
cv2.drawContours(orig, [box.astype("int")], -1, (0, 255, 0), 2)
screen_res = 972, 648
scale_width = screen_res[0] / img.shape[1]
scale_height = screen_res[1] / img.shape[0]
scale = min(scale_width, scale_height)
window_width = int(img.shape[1] * scale)
window_height = int(img.shape[0] * scale)
cv2.namedWindow('Image', cv2.WINDOW_NORMAL)
cv2.resizeWindow('Image', window_width, window_height)
cv2.imshow("Image", orig)
cv2.waitKey(0)
cv2.destroyAllWindows()
The hierarchy returned by findContours has four columns : [Next, Previous, First_Child, Parent]. As you pointed out, we are interested in index 2 i.e. First_Child. To filter and draw only contours without child, you can loop on indices present in WithoutChildContour.
cntsA=[ cntsA[i] for i in WithoutChildContour]
Here's the corresponding snippet:
Note: Since opencv 4.0, findContours returns only 2 values (cnts and hierarchy).
# ...
hierarchy = cnts[1] #changed index
ChildContour = hierarchy [0, :,2]
WithoutChildContour = (ChildContour==-1).nonzero()[0]
cntsA = cnts[0]
# get contours from indices
cntsA=[ cntsA[i] for i in WithoutChildContour]
# ...
Running on your sample image:
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)