I am trying to set dpi to (72,72) using opencv in python. can anyone tell me how do we assign dpi in opencv using imwrite ?
img = cv2.imread('kitchen.jpeg')
img = cv2.resize(img,(500,500),interpolation=cv2.INTER_AREA)
img = cv2.cvtColor(img, cv2.COLOR_RGBA2RGB)
mask = np.zeros(img.shape[:2],np.uint8)
bgdModel = np.zeros((1,65),np.float64)
fgdModel = np.zeros((1,65),np.float64)
rect = (10,10,500,500)
cv2.grabCut(img,mask,rect,bgdModel,fgdModel,5,cv2.GC_INIT_WITH_RECT)
mask2 = np.where((mask==2)|(mask==0),0,1).astype('uint8')
img = img*mask2[:,:,np.newaxis]
lower_white = np.array([0, 0, 0], dtype=np.uint8)
upper_white = np.array([0,0,0], dtype=np.uint8)
mask = cv2.inRange(img, lower_white, upper_white) # could also use threshold
res = cv2.bitwise_not(img, img, mask)
cv2.imwrite('kitchen_processed.jpeg',img)
emm dpi is for printing only. during image write you dont have to do it or you cant do it(for some format). It's only at image print you have to do it. if you insist of doing so. After image write, call System.call with the file name as the variable
convert -density 75 -units pixelsperinch infile.jpg outfile.png
normally the density is 300 or more. in your case, use it at 75
edit
Add this in. Not sure if you have other potential problem. But based on your title, add this line should solve your issue
import subprocess
img = cv2.imread('kitchen.jpeg')
img = cv2.resize(img,(500,500),interpolation=cv2.INTER_AREA)
img = cv2.cvtColor(img, cv2.COLOR_RGBA2RGB)
mask = np.zeros(img.shape[:2],np.uint8)
bgdModel = np.zeros((1,65),np.float64)
fgdModel = np.zeros((1,65),np.float64)
rect = (10,10,500,500)
cv2.grabCut(img,mask,rect,bgdModel,fgdModel,5,cv2.GC_INIT_WITH_RECT)
mask2 = np.where((mask==2)|(mask==0),0,1).astype('uint8')
img = img*mask2[:,:,np.newaxis]
lower_white = np.array([0, 0, 0], dtype=np.uint8)
upper_white = np.array([0,0,0], dtype=np.uint8)
mask = cv2.inRange(img, lower_white, upper_white) # could also use threshold
res = cv2.bitwise_not(img, img, mask)
cv2.imwrite('kitchen_processed.png',img)
subprocess.run('convert -density 75 -units pixelsperinch kitchen_processed.png outfile.png')
Related
I am trying to detect orange beats in below image
To detect these, I have first cropped the area from original image and then setting high and low hsv values to detect orange. This seems to be working fine. Below is the detected image:
Below is the code:
import cv2
import numpy as np
win_name = "Image"
cv2.namedWindow(win_name)
img = cv2.imread('image.png')
orangeImg = img[420:510, 457:953]
hsv = cv2.cvtColor(orangeImg, cv2.COLOR_BGR2HSV)
lower_bound = np.array([0, 80, 80])
upper_bound = np.array([20, 255, 255])
origMask = cv2.inRange(hsv, lower_bound, upper_bound)
contours, hierarchy = cv2.findContours(origMask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
for _, c in enumerate(contours):
areas = [cv2.contourArea(c) for c in contours]
for area in areas:
if area >= 20.0:
boundRect = cv2.boundingRect(c)
rectX = boundRect[0]
rectY = boundRect[1]
rectWidth = boundRect[2]
rectHeight = boundRect[3]
color = (0, 0, 255)
cv2.rectangle(orangeImg, (int(rectX), int(rectY)), (int(rectX + rectWidth), int(rectY + rectHeight)), color, 2)
cv2.imshow(win_name, img)
cv2.waitKey(0)
cv2.destroyAllWindows()
In the output image, you can notice that it still has some noise around the bbox created. Is there a better way to reduce the noise in it. Also is there a way to count the detected contours in the image?
I am working on a opencv project, where I need to detect names column and any black color border present around the ROI. I am quite new with image processing so unable to figure out how to do this.
This is one of the sample images from which I wish to remove the column on the right (one containing all the details). But not all images contain this column, so I wish to detect the column and remove it from the image.
Here is the expected output.
EDIT
Here is the code that I have tried (I have tried using detection of largest rectangles in the region):
import cv2
from cv2 import dilate
from cv2 import findContours
import imutils
import numpy as np
image_name = 'test2.jpg'
og_plan = cv2.imread('test_images/{}'.format(image_name))
res = og_plan.copy()
img_height, img_width, img_channel = og_plan.shape
img_area = img_width * img_height
if og_plan.shape[0] > 800:
res = imutils.resize(res, height=720)
img_height, img_width, img_channel = res.shape
img_area = img_width * img_height
print(res.shape)
print(img_area)
hsv_plan = cv2.cvtColor(res, cv2.COLOR_BGR2HSV)
grey_plan = cv2.cvtColor(res, cv2.COLOR_BGR2GRAY)
blue_min = np.array([14,100,76])
blue_max = np.array([130,255,255])
bluemask = cv2.inRange(hsv_plan,blue_min,blue_max)
blue_output = cv2.bitwise_and(hsv_plan, hsv_plan, mask=bluemask)
grey_mask = cv2.cvtColor(blue_output, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(grey_mask, 100, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
ret2, thresh2 = cv2.threshold(grey_plan, 160, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
kernel = np.ones((3,3), np.uint8)
dil = dilate(thresh, kernel, iterations=2)
dil_grey = dilate(thresh2, kernel, iterations=2)
cont,hier = findContours(dil, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cont1,hier1 = findContours(dil_grey, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
def max_rect(cntrs):
ar = {}
for cnt in cntrs:
x,y,w,h = cv2.boundingRect(cnt)
area = w*h
ar[area] = (x,y,w,h)
# ar = sorted(ar, key=ar.keys, reverse=True)
return ar
area_dict = max_rect(cont1)
roi_area = []
for area in area_dict:
if area >= img_area*0.1 and area < img_area:
print(area)
roi_area.append(area)
plan_no = 1
for a in roi_area:
plan = area_dict[a]
# del area_dict[a]
x,y,w,h = plan
roi = res[y:y+h, x:x+w]
print(plan)
cv2.rectangle(res, (x-5,y-5), (x+w+5, y+h+5), (255,255,0), 2)
cv2.imshow('ROI-{}'.format(image_name),roi)
cv2.imwrite('./result/{}_plan-{}.png'.format(image_name,plan_no),roi)
cv2.waitKey(0)
plan_no += 1
'''plan1 = area_dict[max(area_dict)]
del area_dict[max(area_dict)]
plan2 = area_dict[max(area_dict)]
x,y,w,h = plan1
x1,y1,w1,h1 = plan2
roi1 = res[y:y+h, x:x+w]
roi2 = res[y1:y1+h1, x1:x1+w1]
print(plan1, plan2)
cv2.rectangle(res, (x-5,y-5), (x+w+5, y+h+5), (255,255,0), 2)
cv2.rectangle(res, (x1-5,y1-5), (x1+w1+5, y1+h1+20), (255,255,0), 2)'''
I am trying to use bitwise operations. In the code below I use 2 images (img1, img2). I create two masks using img2 (gray_inv and gray_test).
img1 = cv2.imread('Computer-Vision-with-Python/DATA/dog_backpack.jpg')
img1 = cv2.cvtColor(img1,cv2.COLOR_BGR2RGB)
img1 = img1[0:600,0:600]
img2 = cv2.imread('Computer-Vision-with-Python/DATA/watermark_no_copy.png')
img2 = cv2.cvtColor(img2,cv2.COLOR_BGR2RGB)
img2 = cv2.resize(img2,(600,600))
gray = cv2.cvtColor(img2,cv2.COLOR_BGR2GRAY)
gray_inv = cv2.bitwise_not(gray)
gray_test = cv2.bitwise_not(gray_inv)
I use a bitwise_or function merge with img1. The first mask works fine. However the second one does not. Am I missing out on something ? Ideally since the they are inverse gray_inv should have showed the background with the text in black.
plt.imshow(cv2.bitwise_or(img1,img1, mask=gray_inv))
plt.imshow(cv2.bitwise_or(img1,img1, mask=gray_test))
You need to "binarize" the mask.
For your code to work properly, the mask should be a binary image.
In OpenCV, the convention of a binary image is an image with all values 0 or 255 (and type np.uint8).
Using only 0 and 255 is not a "must", but when using cv2.bitwise_not(mask), it's important for the mask to be binary (then all zeros are inverted to 255, and all 255 are inverted to zeros).
The code gray = cv2.cvtColor(img2,cv2.COLOR_BGR2GRAY), converts img2 to grayscale, but not to a binary image (not all values are 0 and 255).
You may apply thresholding for converting gray to binary:
thres_gray = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU)[1] # threshold (binarize) the image
Use thres_gray instead of gray:
gray_inv = cv2.bitwise_not(thres_gray)
gray_test = cv2.bitwise_not(gray_inv)
The following code sample demonstrates the solution:
import cv2
import numpy as np
img1 = cv2.imread('img1.png')
img1 = cv2.resize(img1, (100,100))
img2 = cv2.imread('img2.png')
img2 = cv2.resize(img2, (100,100))
gray = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)
thres_gray = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU)[1] # threshold (binarize) the image
gray_inv = cv2.bitwise_not(thres_gray)
gray_test = cv2.bitwise_not(gray_inv)
out2 = cv2.bitwise_or(img1, img1, mask=gray_inv)
out3 = cv2.bitwise_or(img1, img1, mask=gray_test)
cv2.imshow('out2', out2)
cv2.imshow('out3', out3)
cv2.waitKey()
cv2.destroyAllWindows()
out2:
out3:
For the effect you’re describing you don’t want a bit-wise OR. You want to multiply the values. So output = input1 * input2 / 255.
Hello everybody before you close this question, i have already searched here, here too and also here
I am using python code to detect the Leaf in an image, using contours finding and then find out the largest contour, the part works best, but then i want only the leaf part of the image and skip the rest of the image to avoid unnecessary content in the resultant output, some of the methods in the link suggests bounding box but this still includes extra content in the image as the shape is not rectangular it's irregular, sample is attached
The code is following
import cv2
import numpy as np
img = cv2.imread("blob.jpg", -1)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 101, 3)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5,5))
blob = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9,9))
blob = 255 - cv2.morphologyEx(blob, cv2.MORPH_CLOSE, kernel)
cnts = cv2.findContours(blob, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
if len(cnts) == 2:
cnts = cnts[0]
else:
cnts = cnts[1]
big_contour = max(cnts, key = cv2.contourArea)
blob_area_thresh = 1000
blob_area = cv2.contourArea(big_contour)
if blob_area < blob_area_thresh:
print("Leaf is Too Small")
else:
#problem starts from here . i tested big_contour is just perfect by drawing on actual image
mask = np.zeros_like(img)
cv2.drawContours(mask, big_contour, -1, 255, -1)
out = np.zeros_like(img)
out[mask == 255] = img[mask == 255]
cv2.imwrite('output.jpg', out)
Now the problem is i am getting the resultant image as black nothing cropped all black pixels
There is a problem with your contour because it is not circulating the leaf as the end of the leaf on the right is out of the image.
You can see this when I try to fill the contour to create a mask using
cv2.fillPoly(mask, pts =[big_contour], color=(255,255,255))
it doesn't fill the leaf.
However I tried something although not perfect and has some background left but it crops the leaf to some extend.
import cv2
import numpy as np
img = cv2.imread("96Klg.jpg", -1)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 101, 3)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5,5))
blob = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
#kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9,9))
#blob = 255 - cv2.morphologyEx(blob, cv2.MORPH_CLOSE, kernel)
cnts = cv2.findContours(blob, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
if len(cnts) == 2:
cnts = cnts[0]
else:
cnts = cnts[1]
big_contour = max(cnts, key = cv2.contourArea)
blob_area_thresh = 1000
blob_area = cv2.contourArea(big_contour)
if blob_area < blob_area_thresh:
print("Leaf is Too Small")
else:
#problem starts from here . i tested big_contour is just perfect by drawing on actual image
mask = np.ones_like(img)
mask.fill(255)
cv2.fillPoly(mask, pts =[big_contour], color=(0,0,0))
#cv2.drawContours(mask, big_contour, -1, (255,255,255), 1)
out = np.zeros_like(img)
out[mask == 255] = img[mask == 255]
width = int(gray.shape[1] * 0.25)
height = int(gray.shape[0] * 0.25)
dim = (width, height)
# resize image
resized = cv2.resize(out, dim, interpolation = cv2.INTER_AREA)
resizedmask = cv2.resize(mask, dim, interpolation = cv2.INTER_AREA)
cv2.imshow('gray',resized)
cv2.imshow('out',resizedmask)
Output
I am trying to display an image over another image at a particular co-ordinates. I have detected the aruco markers using the webcam and I want to display another image over the aruco marker. The aruco marker can be moved and the overlaying image should move along with the marker.
There is various draw functions and to input text into the image. I have tried image overlay and image homography.
I can obtain the co-ordinates for the corners.
Is there any function to insert the image at those co-ordinates?
import cv2
import cv2.aruco as aruco
import glob
markerLength = 0.25
cap = cv2.VideoCapture(0)
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 0.001)
objp = np.zeros((6*7,3), np.float32)
objp[:,:2] = np.mgrid[0:7,0:6].T.reshape(-1,2)
objpoints = []
imgpoints = []
images = glob.glob('calib_images/*.jpg')
for fname in images:
img = cv2.imread(fname)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret, corners = cv2.findChessboardCorners(gray, (7,6),None)
if ret == True:
objpoints.append(objp)
corners2 = cv2.cornerSubPix(gray,corners,(11,11),(-1,-1),criteria)
imgpoints.append(corners2)
img = cv2.drawChessboardCorners(img, (7,6), corners2,ret)
ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpoints, imgpoints, gray.shape[::-1],None,None)
calibrationFile = "calibrationFileName.xml"
calibrationParams = cv2.FileStorage(calibrationFile, cv2.FILE_STORAGE_READ)
camera_matrix = calibrationParams.getNode("cameraMatrix").mat()
dist_coeffs = calibrationParams.getNode("distCoeffs").mat()
while(True):
ret, frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
aruco_dict = aruco.Dictionary_get(aruco.DICT_6X6_250)
arucoParameters = aruco.DetectorParameters_create()
corners, ids, rejectedImgPoints = aruco.detectMarkers(gray, aruco_dict, parameters=arucoParameters)
if np.all(ids != None):
rvec, tvec, _ = aruco.estimatePoseSingleMarkers(corners, markerLength, mtx, dist)
axis = aruco.drawAxis(frame, mtx, dist, rvec, tvec, 0.3)
print(ids)
display = aruco.drawDetectedMarkers(axis, corners)
display = np.array(display)
else:
display = frame
cv2.imshow('Display',display)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()```
To replace a part of image
import cv2
import numpy as np
img1 = cv2.imread('Desert.jpg')
img2 = cv2.imread('Penguins.jpg')
img3 = img1.copy()
# replace values at coordinates (100, 100) to (399, 399) of img3 with region of img2
img3[100:400,100:400,:] = img2[100:400,100:400,:]
cv2.imshow('Result1', img3)
To alpha blend two images
alpha = 0.5
img3 = np.uint8(img1*alpha + img2*(1-alpha))
cv2.imshow('Result2', img3)
#user8190410's answer works fine. Just to give a complete answer, in order to alpha blend two images with different size at a particular position, you can do the following:
alpha= 0.7
img1_mod = img1.copy()
img1_mod[:pos_x,:pos_y,:] = img1[:pos_x,:pos_y,:]*alpha + img2*(1-alpha)
cv2.imshow('Image1Mod', img1_mod)
Actually, I found that image homography can be used to do it.
Here is the updated code.
import numpy as np
import cv2
import cv2.aruco as aruco
cap = cv2.VideoCapture(0)
while(True):
ret, frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
aruco_dict = aruco.Dictionary_get(aruco.DICT_6X6_250)
arucoParameters = aruco.DetectorParameters_create()
corners, ids, rejectedImgPoints = aruco.detectMarkers(gray, aruco_dict, parameters=arucoParameters)
if np.all(ids != None):
display = aruco.drawDetectedMarkers(frame, corners)
x1 = (corners[0][0][0][0], corners[0][0][0][1])
x2 = (corners[0][0][1][0], corners[0][0][1][1])
x3 = (corners[0][0][2][0], corners[0][0][2][1])
x4 = (corners[0][0][3][0], corners[0][0][3][1])
im_dst = frame
im_src = cv2.imread("mask.jpg")
size = im_src.shape
pts_dst = np.array([x1,x2,x3,x4])
pts_src = np.array(
[
[0,0],
[size[1] - 1, 0],
[size[1] - 1, size[0] -1],
[0, size[0] - 1 ]
],dtype=float
);
h, status = cv2.findHomography(pts_src, pts_dst)
temp = cv2.warpPerspective(im_src, h, (im_dst.shape[1],im_dst.shape[0]))
cv2.fillConvexPoly(im_dst, pts_dst.astype(int), 0, 16);
im_dst = im_dst + temp
cv2.imshow('Display',im_dst)
else:
display = frame
cv2.imshow('Display',display)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()