图像预处理：轮廓扩展

Question

I want to do some image preprocessing, but there is one step which I am not sure the best way to do it.

I have MRI Images with interesting zones annotated, I detect the contour and crop the image:

I am going to post here my code, so you get an idea how I've done the previous steps and the data we have

lower_orange = np.array([0, 80, 50],np.uint8)
upper_orange = np.array([255, 255, 255],np.uint8)

for frame in frames:

    cv2.imshow('Original frame',frame)
    cv2.waitKey(0)

    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
    contour = cv2.inRange(hsv, lower_orange, upper_orange)

    x,y,w,h = cv2.boundingRect(contour)

    mask_inv = cv2.bitwise_not(contour)
    frame = cv2.bitwise_and(hsv,hsv,mask = mask_inv)

    cv2.imshow('Contoured frame',frame)
    cv2.waitKey(0)

    croped = frame[y:y+h,x:x+w]

    resized = cv2.resize(croped,(240,240))

    gray = resized[:,:,2]

    cv2.imshow('Grayscale frame',gray)
    cv2.waitKey(0)

    feature.append(gray)

What I want to do now is to black out everything outside the contour:

Do you know any native way to do this with OpenCV? Or any algorithm or non-native way to achieve that?

Thank you very much

Answer 1

As Yunus Temuerlenkl told me in the comments.

The precision of this method depends on how accurate the mask of the contour is .

Although it is an iterative approach it doesn't add up too much time to the processing for me. One thing you can do is to process your images/frames in parallel .

for idx, frame in enumerate(frames):

    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
    contour = cv2.inRange(hsv, lower_orange, upper_orange)

    x,y,w,h = cv2.boundingRect(contour)

    croped_img = frame[y:y+h,x:x+w]
    croped_mask = contour[y:y+h,x:x+w]

    resized_gray_img = cv2.resize(croped_img,(dim,dim))[:,:,2]
    resized_mask = cv2.resize(croped_mask,(dim,dim))

    for row in range(dim):
        i = 0
        is_contour = False

        while((i < dim) & (not is_contour)):
            if(resized_mask[row,i]):
                is_contour = True
            resized_gray_img[row,i] = 0
            i+=1
        
        if not is_contour: continue
        is_contour = False

        i = dim -1

        while((i >= 0) & (not is_contour)):
            if(resized_mask[row,i]):
                is_contour = True
            resized_gray_img[row,i] = 0
            i-=1
   
    mask_inv = cv2.bitwise_not(resized_mask) 
    img = cv2.bitwise_and(resized_gray_img,resized_gray_img,mask = mask_inv)

    feature.append(img)