image-table-ocr/table_ocr/ocr_image/__init__.py

import math

import cv2

def crop_to_text(image):
    MAX_COLOR_VAL = 255
    BLOCK_SIZE = 15
    SUBTRACT_FROM_MEAN = -2

    img_bin = cv2.adaptiveThreshold(
        ~image,
        MAX_COLOR_VAL,
        cv2.ADAPTIVE_THRESH_MEAN_C,
        cv2.THRESH_BINARY,
        BLOCK_SIZE,
        SUBTRACT_FROM_MEAN,
    )

    img_h, img_w = image.shape
    horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (int(img_w * 0.5), 1))
    vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, int(img_h * 0.7)))
    horizontal_lines = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, horizontal_kernel)
    vertical_lines = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, vertical_kernel)
    both = horizontal_lines + vertical_lines
    cleaned = img_bin - both

    # Get rid of little noise.
    kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
    opened = cv2.morphologyEx(cleaned, cv2.MORPH_OPEN, kernel)

    contours, hierarchy = cv2.findContours(opened, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
    bounding_rects = [cv2.boundingRect(c) for c in contours]
    NUM_PX_COMMA = 6
    MIN_CHAR_AREA = 5 * 9
    if bounding_rects:
        minx, miny, maxx, maxy = math.inf, math.inf, 0, 0
        for x, y, w, h in [(x, y, w, h) for x, y, w, h in bounding_rects if w * h > MIN_CHAR_AREA]:
            minx = min(minx, x)
            miny = min(miny, y)
            maxx = max(maxx, x + w)
            maxy = max(maxy, y + h)
        x, y, w, h = minx, miny, maxx - minx, maxy - miny
        cropped = image[y:min(img_h, y+h+NUM_PX_COMMA), x:min(img_w, x+w)]
    else:
        # If we morphed out all of the text, fallback to using the unmorphed image.
        cropped = image
    bordered = cv2.copyMakeBorder(cropped, 5, 5, 5, 5, cv2.BORDER_CONSTANT, None, 255)
    return bordered
def ocr_image(image, config):
    return pytesseract.image_to_string(
        image,
        config=config
    )