I am working on a project about extracting the digit from the 7-segment display and I am following this guide:

The extracted black white photo:

Code:

    img_name = 'test2.jpeg'
    image = cv2.imread(img_name)

    image = imutils.resize(image, height=1000)
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    blurred = cv2.GaussianBlur(gray, (5, 5), 0)
    edged = cv2.Canny(blurred, 50, 200, 255)


    #cv2.imshow("test", edged)
    #cv2.waitKey(0)

    cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    cnts = imutils.grab_contours(cnts)
    cnts = sorted(cnts, key=cv2.contourArea, reverse=True)

    displayCnt = None
    # loop over the contours
    for c in cnts:
        # approximate the contour
        peri = cv2.arcLength(c, True)
        approx = cv2.approxPolyDP(c, 0.02 * peri, True)
        # if the contour has four vertices, then we have found
        # the thermostat display
        if len(approx) == 4:
            displayCnt = approx
            break
    warped = four_point_transform(gray, displayCnt.reshape(4, 2))
    output = four_point_transform(image, displayCnt.reshape(4, 2))

    thresh = cv2.threshold(warped, 222, 255, cv2.THRESH_BINARY_INV cv2.THRESH_OTSU)[1]
    cv2.imwrite("black.png", thresh)

CodePudding user response：

Regarding the brightness difference, division normalization and sharping can be applied:

smooth = cv2.GaussianBlur(warped, (95,95), 0)
division = cv2.divide(warped, smooth, scale=255)
sharp = filters.unsharp_mask(division, radius=1.5, amount=1.5, 
        multichannel=False, preserve_range=False)
sharp = (255*sharp).clip(0,255).astype(np.uint8)

Output:

CodePudding user response：

Due to different parts of the image having different overall brightness levels, a global threshold will result in some parts of the image having a threshold that's too low and some too high. This can be remedied by using a median filter on the image to determine local thresholds for the entire image. Here are the steps described (and demonstrated using Paint.NET).

1. Apply a median filter to the image

2. Take the difference between the original image and the filtered image and convert it to grayscale

3. Use a global threshold on this new image