Combining colors and outlines to produce a cartoon

The last step is to combine the two previously achieved effects. Simply fuse the two effects together into a single image using cv2.bitwise_and. The complete function is as follows:

def cartoonize(rgb_image, *,
               num_pyr_downs=2, num_bilaterals=7):
    # STEP 1 -- Apply a bilateral filter to reduce the color palette of
    # the image.
    downsampled_img = rgb_image
    for _ in range(num_pyr_downs):
        downsampled_img = cv2.pyrDown(downsampled_img)

    for _ in range(num_bilaterals):
        filterd_small_img = cv2.bilateralFilter(downsampled_img, 9, 9, 7)

    filtered_normal_img = filterd_small_img
    for _ in range(num_pyr_downs):
        filtered_normal_img = cv2.pyrUp(filtered_normal_img)

    # make sure resulting image has the same dims as original
    if filtered_normal_img.shape != rgb_image.shape:
        filtered_normal_img = cv2.resize(
            filtered_normal_img, rgb_image.shape[:2])

    # STEP 2 -- Convert the original color image into grayscale.
    img_gray = cv2.cvtColor(rgb_image, cv2.COLOR_RGB2GRAY)
    # STEP 3 -- Apply amedian blur to reduce image noise.
    img_blur = cv2.medianBlur(img_gray, 7)

    # STEP 4 -- Use adaptive thresholding to detect and emphasize the edges
    # in an edge mask.
    gray_edges = cv2.adaptiveThreshold(img_blur, 255,
                                       cv2.ADAPTIVE_THRESH_MEAN_C,
                                       cv2.THRESH_BINARY, 9, 2)
    # STEP 5 -- Combine the color image from step 1 with the edge mask
    # from step 4.
    rgb_edges = cv2.cvtColor(gray_edges, cv2.COLOR_GRAY2RGB)
    return cv2.bitwise_and(filtered_normal_img, rgb_edges)

The result looks like this:

In the next section, we'll set up the main script and design a GUI application.