import cv2
def mark_region(image_path):

    # define threshold of regions to ignore
    THRESHOLD_REGION_IGNORE = 13

    im = cv2.imread(image_path)

    # Convertion de l'image en niveau de gris
    gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)

    # Blurs an image using a Gaussian filter.
    blur = cv2.GaussianBlur(gray, (9, 9), 0)

    # On converti l'image en tableau binaire
    thresh = cv2.adaptiveThreshold(blur, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 15, 30)

    # Dilate to combine adjacent text contours
    kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 9))
    dilate = cv2.dilate(thresh, kernel, iterations=100)

    # Find contours, highlight text areas, and extract ROIs
    cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    cnts = cnts[0] if len(cnts) == 2 else cnts[1]

    line_items_coordinates = []
    for c in cnts:
        area = cv2.contourArea(c)
        x, y, w, h = cv2.boundingRect(c)

        if w < THRESHOLD_REGION_IGNORE or h < THRESHOLD_REGION_IGNORE:
            continue

        if y >= 600 and x <= 1000:
            if area > 10000:
                image = cv2.rectangle(im, (x, y), (2200, y + h), color=(255, 0, 255), thickness=3)
                line_items_coordinates.append([(x, y), (2200, y + h)])

        if y >= 2400 and x <= 2000:
            image = cv2.rectangle(im, (x, y), (2200, y + h), color=(255, 0, 255), thickness=3)
            line_items_coordinates.append([(x, y), (2200, y + h)])
        image = cv2.rectangle(im, (x,y), (x+w, y+h), color=(255,0,255), thickness=3)
        line_items_coordinates.append([(x,y), (x+w, y+h)])

    return image