I am trying to detect the black tape on the floor, but whenever I try to increase the threshold to stop it from detecting the ground all it does is stop detecting the tape.
from cv2 import cv2
import numpy as np
img = cv2.imread('tape4.jpeg', cv2.IMREAD_UNCHANGED)
#convert img to grey
img_grey = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#set a thresh
thresh = 100
#get threshold image
ret,thresh_img = cv2.threshold(img_grey, thresh, 255, cv2.THRESH_BINARY)
#find contours
contours, hierarchy = cv2.findContours(thresh_img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
#create an empty image for contours
img_contours = np.zeros(img.shape)
# draw the contours on the empty image
cv2.drawContours(img_contours, contours, -1, (0,255,0), 3)
#save image
cv2.imwrite('contours.png',img_contours)
You may use Use cv2.THRESH_BINARY_INV instead of cv2.THRESH_BINARY for finding pixels below thresh instead of pixels above thresh.
The reason you are detecting the floor, is that cv2.threshold marks (with 255 value), the pixels above thresh.
You want to mark the dark pixels below thresh.
You can compute: thresh_img = 255 - thresh_img, or use cv2.THRESH_BINARY_INV (result is the same).
I also recommend using closing morphological operation, for removing clutter.
Code for finding the tape:
import cv2
import numpy as np
img = cv2.imread('tape4.jpeg', cv2.IMREAD_UNCHANGED)
#convert img to grey
img_grey = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#set a thresh
thresh = 20 # Set thresh to very low value (the tape is almost black).
#get threshold image
# Use cv2.THRESH_BINARY_INV instead of cv2.THRESH_BINARY for finding pixels below thresh instead of pixels above thresh
ret,thresh_img = cv2.threshold(img_grey, thresh, 255, cv2.THRESH_BINARY_INV)
# Apply closing morphological operation
thresh_img = cv2.morphologyEx(thresh_img, cv2.MORPH_CLOSE, cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (21,21)));
#find contours
contours, hierarchy = cv2.findContours(thresh_img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
#create an empty image for contours
img_contours = np.zeros(img.shape)
# draw the contours on the empty image
cv2.drawContours(img_contours, contours, -1, (0,255,0), 3)
#save image
cv2.imwrite('contours.png',img_contours)
Result:
For finding the tape, you can look for the largest contour within contours:
# Get contour with maximum area
c = max(contours, key=cv2.contourArea)
img_contours = np.zeros(img.shape)
cv2.drawContours(img_contours, [c], -1, (0,255,0), 3)
Result:
Related
I am trying to remove the backgrounds of a set of tea leaf images.
I tried these codes in StackOverflow itself but they don't work with my images.
How to remove the background from a picture in OpenCV python
how to remove background of images in python
How can I delete the whole background around the leaf and keep only the single leaf.
This is a one-sample of the image set.
# Read image
img = cv2.imread('leaf.jpg')
# Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Find edges
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU + cv2.THRESH_BINARY)[1]
# Find contour
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# Sort contour by area
contours = sorted(contours, key=cv2.contourArea, reverse=True)
# Find the bounding box and crop image to get ROI
for cnt in contours:
x,y,w,h = cv2.boundingRect(cnt)
ROI = img[y:y+h, x:x+w]
break
# Define lower and upper threshold for background
lower = np.array([128, 128, 128])
upper = np.array([255, 255, 255])
# Create mask to only select black
thresh = cv2.inRange(ROI, lower, upper)
# Apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3,3))
morph = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
# invert morph image to get background as black
mask = 255 - morph
# apply mask to image
result = cv2.bitwise_and(ROI, ROI, mask=mask)
plt.imshow(result)
I have been at this all day, how to we remove the small back noise in the red circle? I would need it to work on other samples of pictures like this.
The idea I used is to findContours and then add a mask with all the small black noise that is less than a certain area (trial and error).
Removing noise in red ellipse
image = cv2.imread("11_Image_after_noise_removal.png")
# copy image
img = image.copy()
imgray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 127, 255, 0, cv2.THRESH_BINARY)
thresh = 255 - thresh
# Use cv2.CCOMP for two level hierarchy
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_CCOMP,
cv2.CHAIN_APPROX_SIMPLE) # Use cv2.CCOMP for two level hierarchy
cv2.drawContours(img, contours, -1, (0, 255, 0), 1)
cv2.imshow("First detection", img)
# loop through the contours
for i, cnt in enumerate(contours):
# if the contour has no other contours inside of it
if hierarchy[0][i][3] != -1: # basically look for holes
# if the size of the contour is less than a threshold (noise)
if cv2.contourArea(cnt) < 70:
# Fill the holes in the original image
cv2.drawContours(img, [cnt], 0, (0, 0, 0), -1)
# display result
# Visualize the image after the Otsu's method application
cv2.imshow("Image after noise removal", img)
cv2.waitKey(0)
cv2.destroyAllWindows().destroyAllWindows()
You might check the contour area using area = cv.contourArea(cnt) and if it is below some threshold, ignore it.
Here is the OpenCV documentations:
https://docs.opencv.org/4.3.0/dd/d49/tutorial_py_contour_features.html
I am trying to extract object from an image using the color using OpenCV, I have tried by inverse thresholding and grayscale combined with cv2.findContours() but I am unable to use it recursively. Furthermore I can't figure out how to "cut out" the match from the original image and save it to a single file.
EDIT
~
import cv2
import numpy as np
# load the images
empty = cv2.imread("empty.jpg")
full = cv2.imread("test.jpg")
# save color copy for visualization
full_c = full.copy()
# convert to grayscale
empty_g = cv2.cvtColor(empty, cv2.COLOR_BGR2GRAY)
full_g = cv2.cvtColor(full, cv2.COLOR_BGR2GRAY)
empty_g = cv2.GaussianBlur(empty_g, (51, 51), 0)
full_g = cv2.GaussianBlur(full_g, (51, 51), 0)
diff = full_g - empty_g
# thresholding
diff_th =
cv2.adaptiveThreshold(full_g,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
cv2.THRESH_BINARY,11,2)
# combine the difference image and the inverse threshold
zone = cv2.bitwise_and(diff, diff_th, None)
# threshold to get the mask instead of gray pixels
_, zone = cv2.threshold(bag, 100, 255, 0)
# dilate to account for the blurring in the beginning
kernel = np.ones((15, 15), np.uint8)
bag = cv2.dilate(bag, kernel, iterations=1)
# find contours, sort and draw the biggest one
contours, _ = cv2.findContours(bag, cv2.RETR_TREE,
cv2.CHAIN_APPROX_SIMPLE)
contours = sorted(contours, key=cv2.contourArea, reverse=True)[:3]
i = 0
while i < len(contours):
x, y, width, height = cv2.boundingRect(contours[i])
roi = full_c[y:y+height, x:x+width]
cv2.imwrite("piece"+str(i)+".png", roi)
i += 1
Where empty is just a white image size 1500 * 1000 as the one above and test is the one above.
This is what I came up with, only downside, I have a third image instead of only the 2 expected showing a shadow zone now...
Here's a simple approach:
Obtain binary image. Load the image, grayscale, Gaussian blur, Otsu's threshold, then dilate to obtain a binary black/white image.
Extract ROI. Find contours, obtain bounding boxes, extract ROI using Numpy slicing, and save each ROI
Binary image (Otsu's thresholding + dilation)
Detected ROIs highlighted in green
To extract each ROI, you can find the bounding box coordinates using cv2.boundingRect(), crop the desired region, then save the image
x,y,w,h = cv2.boundingRect(c)
ROI = original[y:y+h, x:x+w]
First object
Second object
import cv2
# Load image, grayscale, Gaussian blur, Otsu's threshold, dilate
image = cv2.imread('1.jpg')
original = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (5,5), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,7))
dilate = cv2.dilate(thresh, kernel, iterations=1)
# Find contours, obtain bounding box coordinates, and extract ROI
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
image_number = 0
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
ROI = original[y:y+h, x:x+w]
cv2.imwrite("ROI_{}.png".format(image_number), ROI)
image_number += 1
cv2.imshow('image', image)
cv2.imshow('thresh', thresh)
cv2.imshow('dilate', dilate)
cv2.waitKey()
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)
I have an image such as this
I am trying to detect and remove the arrow from this image so that I end up with an image that just has the text.
I tried the below approach but it isn't working
image_src = cv2.imread("roi.png")
gray = cv2.cvtColor(image_src, cv2.COLOR_BGR2GRAY)
canny=cv2.Canny(gray,50,200,3)
ret, gray = cv2.threshold(canny, 10, 255, 0)
contours, hierarchy = cv2.findContours(gray, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
largest_area = sorted(contours, key=cv2.contourArea)[-1]
mask = np.ones(image_src.shape[:2], dtype="uint8") * 255
cv2.drawContours(mask, [largest_area], -1, 0, -1)
image = cv2.bitwise_and(image_src, image_src, mask=mask)
The above code seems to give me back the same image WITH the arrow.
How can I remove the arrow?
The following will remove the largest contour:
import numpy as np
import cv2
image_src = cv2.imread("roi.png")
gray = cv2.cvtColor(image_src, cv2.COLOR_BGR2GRAY)
ret, gray = cv2.threshold(gray, 250, 255,0)
image, contours, hierarchy = cv2.findContours(gray, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
mask = np.zeros(image_src.shape, np.uint8)
largest_areas = sorted(contours, key=cv2.contourArea)
cv2.drawContours(mask, [largest_areas[-2]], 0, (255,255,255,255), -1)
removed = cv2.add(image_src, mask)
cv2.imwrite("removed.png", removed)
Note, the largest contour in this case will be the whole image, so it is actually the second largest contour.