helxsz's profile - activity

I have a picture like enter image description here, which i need to segment the picture into 8 blocks.

I have tried this threshold method

img_gray = cv2.imread(input_file,cv2.IMREAD_GRAYSCALE) 
ret,thresh = cv2.threshold(img_gray,254,255,cv2.THRESH_BINARY)
kernel = np.array(cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3), (-1, -1)))

img_open = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel) cv2.imshow('abc',img_open) ret1,thresh1 = cv2.threshold(img_open,254,255,cv2.THRESH_BINARY_INV) contours, hierarchy = cv2.findContours(thresh1, cv2.RETR_CCOMP ,cv2.CHAIN_APPROX_NONE) for i in range(len(contours)): if len(contours[i]) > 20: x, y, w, h = cv2.boundingRect(contours[i]) cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), 2) print (x, y),(x+w, y+h)

after the thresholding

the end result is some blocks connected together are formed into a large segment, which is not what I hoped.

Any other ways to get it around

Thanks a lot, @Missing, it works perfectly and I learned a lot! if you can add it to the answer, I can score it. :)

@Missing, thanks for reminding me this. I tried the approach, it works but only partially, there is some parts not being transformed. Any ideas? I have updated in the main content.

Hi, @Missing, actually it works for the original image but it is strange that the resulted mask from inRange() can't be performed on same operation`enter code here.

frame = cv2.imread("/home/ad/Desktop/1.png")
lower_black = np.array([0,0,0], dtype = "uint16")
upper_black = np.array([70,70,70], dtype = "uint16")
black_mask = cv2.inRange(frame, lower_black, upper_black)
frame[np.where((frame == [0,0,0]).all(axis = 2))] = [0,255,255]     # it works
black_mask[np.where((black_mask == [0,0,0]).all(axis = 2))] = [0,255,255]   # it doesn't work

@Missing, I tried " image[np.where((image==[0,0,0]).all(axis=2))] = [255,255,255] ", but returns " AttributeError: 'bool' object has no attribute 'all' ", so I guess it another way, image[np.where((image==[0,0,0])).all(axis=2)] = [255,255,255], but still telling me a error "AttributeError: 'tuple' object has no attribute 'all' "

I have a image with white background, grey and black part, I want to segment three parts into different color.

so far I could segment the black and grey part with inRange, but I wonder Is there a python API that substitute one color with another color, for example to substitute the black part with red color.

original image

   frame = cv2.imread("/home/ad/Desktop/1.png")
   cv2.imshow('frame',frame)

image after inrange

lower_black = np.array([0,0,0], dtype = "uint16")
upper_black = np.array([70,70,70], dtype = "uint16")
black_mask = cv2.inRange(frame, lower_black, upper_black)
cv2.imshow('mask0',black_mask)

substitute the black color to white color

black_mask[np.where((black_mask == [0] ).all(axis = 1))] = [255]
cv2.imshow('mask1',black_mask)

However, in the last image when trying to substitute the black color into the white color, only a traction of black color has been transformed, there are some parts of the black part remains to be black

Is there a python based API for doing this?

I have a road scene picture, and I can detect the vehicles on the road. What I want to do is to blur the whole picture except the vehicle detection areas, my solution is firstly I create a empty Mat and crop the vehicle detection area into the empty Mat, and secondly blur the whole picture, now the problem is how to combine the blury picture with the vehicle parts ?

I am using opencv (both c++ and java) to segement a white paper in the picture showed below, this works , but now I have to split the paper into 8 small section and get the Mat of each section, since each section is not a pure square, it is hard to use submate(startrow, endrow, startcol, endcol).

Is there any way in opencv to extract the Mat for this kind of none square object?