uz_assignments/assignment1/uz_framework/image.py

import numpy as np
import cv2 as cv2
from matplotlib import pyplot as plt
from PIL import Image
from typing import Union
import numpy.typing as npt
import enum

class ImageType(enum.Enum):
    uint8 = 0
    float64 = 1

def imread(path: str, type: ImageType) -> npt.NDArray[np.float64] or npt.NDArray[np.uint8]:
    """
    Reads an image in RGB order. Image type is transformed from uint8 to float, and
    range of values is reduced from [0, 255] to [0, 1].
    """
    I = Image.open(path).convert('RGB')  # PIL image.
    I = np.asarray(I)  # Converting to Numpy array.
    if type == ImageType.float64:
        I = I.astype(np.float64) / 255
        return I
    elif type == ImageType.uint8:
        return I

    raise Exception("Unrecognized image format!")


def imread_gray(path: str, type: ImageType) -> npt.NDArray[np.float64] or npt.NDArray[np.uint8]:
    """
    Reads an image in gray. Image type is transformed from uint8 to float, and
    range of values is reduced from [0, 255] to [0, 1].
    """

    I = Image.open(path).convert('L')  # PIL image opening and converting to gray.
    I = np.asarray(I)  # Converting to Numpy array.

    if type == ImageType.float64:
        I = I.astype(np.float64) / 255
        return I
    elif type == ImageType.uint8:
        return I

    raise Exception("Unrecognized image format!")

def signal_show(*signals):
    """
    Plots all given 1D signals in the same plot.
    Signals can be Python lists or 1D numpy array.
    """
    for s in signals:
        if type(s) == np.ndarray:
            s = s.squeeze()
        plt.plot(s)
    plt.show()


def convolve(I: np.ndarray, *ks):
    """
    Convolves input image I with all given kernels.

    :param I: Image, should be of type float64 and scaled from 0 to 1.
    :param ks: 2D Kernels
    :return: Image convolved with all kernels.
    """
    for k in ks:
        k = np.flip(k)  # filter2D performs correlation, so flipping is necessary
        I = cv2.filter2D(I, cv2.CV_64F, k)
    return I

def transform_coloured_image_to_grayscale(image: npt.NDArray[np.float64]) -> npt.NDArray[np.float64]:
    """
    Accepts float64 picture with three colour channels and returns float64 grayscale image
    with one channel.
    """
    grayscale_image = np.zeros(image.shape[:2])

    for i in range(image.shape[0]):
        for j in range(image.shape[1]):
            grayscale_image[i, j] = (image[i, j, 0] + image[i,j, 1] + image[i, j, 2]) / 3

    print(grayscale_image)
    print(grayscale_image.shape)

    return grayscale_image

def invert_coloured_image_part(image: npt.NDArray[np.float64] or npt.NDArray[np.uint8], startx: int, endx: int, starty: int, endy: int) -> npt.NDArray[np.float64] or npt.NDArray[np.uint8]:
    """
    Accepts image, starting position end end position for axes x & y. Returns whole image with inverted part.
    """
    inverted_image = image.copy() 

    if image.dtype.type == np.float64:     
        for i in range(startx, endx):
            for j in range(starty, endy):
                inverted_image[i, j, 0] = 1 - image[i, j, 0]
                inverted_image[i, j, 1] = 1 - image[i, j, 1]
                inverted_image[i, j, 2] = 1 - image[i, j, 2]
        return inverted_image
    elif image.dtype.type == np.uint8:
        for i in range(startx, endx):
            for j in range(starty, endy):
                inverted_image[i, j, 0] = 255 - image[i, j, 0]
                inverted_image[i, j, 1] = 255 - image[i, j, 1]
                inverted_image[i, j, 2] = 255 - image[i, j, 2]
        return inverted_image

    raise Exception("Unrecognized image format!")

def invert_coloured_image(image: npt.NDArray[np.float64] or npt.NDArray[np.uint8]) -> npt.NDArray[np.float64] or npt.NDArray[np.uint8]:
    """
    Accepts image and inverts it
    """
    return invert_coloured_image_part(image, 0, image.shape[0], 0, image.shape[1])

def calculate_best_treshold_using_otsu_method(image: npt.NDArray[np.float64] or npt.NDArray[np.uint8]) -> int:
    """
    Accepts image and returns best treshold using otsu method
    """

    if image.dtype.type == np.float64: 
        im = image.copy()
        im  = im * (255.0/im.max())
    elif image.dtype.type == np.uint8:
        im = image.copy()
    else:
        raise Exception("Unrecognized image format!")
        
    treshold_range = np.arange(np.max(im) + 1) 
    criterias = []

    for treshold in treshold_range:
        # create the thresholded image
        thresholded_im = np.zeros(im.shape)

        thresholded_im[im >= treshold] = 1

        # compute weights
        nb_pixels = im.size
        nb_pixels1 = np.count_nonzero(thresholded_im)
        weight1 = nb_pixels1 / nb_pixels
        weight0 = 1 - weight1

        # if one the classes is empty, eg all pixels are below or above the threshold, that threshold will not be considered
        # in the search for the best threshold
        if weight1 == 0 or weight0 == 0:
            continue 

        # find all pixels belonging to each class
        val_pixels1 = im[thresholded_im == 1]
        val_pixels0 = im[thresholded_im == 0]

        # compute variance of these classes
        var0 = np.var(val_pixels0) if len(val_pixels0) > 0 else 0
        var1 = np.var(val_pixels1) if len(val_pixels1) > 0 else 0

        criterias.append( weight0 * var0 + weight1 * var1)

    best_threshold = treshold_range[np.argmin(criterias)]
    return best_threshold