tools.py

import cv2
import imutils
import numpy as np
from skimage.filters import gaussian, threshold_otsu
from skimage.feature import canny
from skimage.transform import probabilistic_hough_line, rotate


# get grayscale image
def get_grayscale(image):
    image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    return image


# noise removal
def remove_noise(image):
    return cv2.medianBlur(image, 5)


# thresholding
def thresholding(image):
    return cv2.threshold(image, 249, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]


# dilation
def dilate(image):
    kernel = np.ones((5, 5), np.uint8)
    return cv2.dilate(image, kernel, iterations=1)


# erosion
def erode(image):
    kernel = np.ones((5, 5), np.uint8)
    return cv2.erode(image, kernel, iterations=1)


# opening - erosion followed by dilation
def opening(image):
    kernel = np.ones((5, 5), np.uint8)
    return cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel)


# skew correction
def deskew(image):
    image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # threshold to get rid of extraneous noise
    thresh = threshold_otsu(image)
    normalize = image > thresh

    # gaussian blur
    blur = gaussian(normalize, 3)

    # canny edges in scikit-image
    edges = canny(blur)

    # hough lines
    hough_lines = probabilistic_hough_line(edges)

    # hough lines returns a list of points, in the form ((x1, y1), (x2, y2))
    # representing line segments. the first step is to calculate the slopes of
    # these lines from their paired point values
    slopes = [(y2 - y1) / (x2 - x1) if (x2 - x1) else 0 for (x1, y1), (x2, y2) in hough_lines]

    # it just so happens that this slope is also y where y = tan(theta), the angle
    # in a circle by which the line is offset
    rad_angles = [np.arctan(x) for x in slopes]

    # and we change to degrees for the rotation
    deg_angles = [np.degrees(x) for x in rad_angles]

    # which of these degree values is most common?
    histo = np.histogram(deg_angles, bins=180)

    # correcting for 'sideways' alignments
    rotation_number = histo[1][np.argmax(histo[0])]

    if rotation_number > 45:
        rotation_number = -(90 - rotation_number)
    elif rotation_number < -45:
        rotation_number = 90 - abs(rotation_number)

    return rotation_number


# template matching
def match_template(image, template):
    return cv2.matchTemplate(image, template, cv2.TM_CCOEFF_NORMED)


def process_image(image_path):
    image_path = image_path.lower()
    if image_path.endswith('.tif') or image_path.endswith('.png') or image_path.endswith('.jpg') or image_path.endswith('.jpeg'):
        image = cv2.imread(image_path)
        height, width, channels = image.shape
        new_width = 640  # pixels
        new_height = int(height * (new_width / width))
        image = cv2.resize(image, (new_width, new_height))
        rotation_angle = deskew(image)
        image = imutils.rotate(image, angle=rotation_angle)
        gray = get_grayscale(image)
        thresh = thresholding(gray)

        return image, gray, thresh
    else:
        print('Invalid image format')
        return None, None, None