Second ex refactored

assignment1/solution.py

@@ -12,9 +12,9 @@ import UZ_utils as uz
 
 def excercise_one() -> None:
     image = one_a()
-    #one_b(image)
+    one_b(image)
-    #one_c(image)
+    one_c(image)
-    #one_d(100, 200, 200, 400, image)
+    one_d(100, 200, 200, 400, image)
     one_e()
     
 def one_a() -> npt.NDArray[np.float64]:
@@ -143,10 +143,10 @@ def excercise_two() -> None:
     pixels in the source image is greater or lower than the given threshold.
     """
     two_a()
-    #two_b('./images/bird.jpg', 100, 20)
+    two_b('./images/bird.jpg', 100, 20)
-    #two_c('./images/bird.jpg', 20, 100)
+    two_c('./images/bird.jpg', 20, 100)
-    #two_d()
+    two_d()
-    #two_e(uz.imread_gray('./images/bird.jpg', uz.ImageType.uint8).astype(np.uint8))
+    two_e(uz.imread_gray('./images/bird.jpg', uz.ImageType.uint8).astype(np.uint8))
 
 
 def two_a() -> tuple[npt.NDArray[np.float64], npt.NDArray[np.uint8]]:
@@ -180,48 +180,6 @@ def two_a() -> tuple[npt.NDArray[np.float64], npt.NDArray[np.uint8]]:
     plt.show()
     return (image, binary_mask)
 
-
-def my_hist_for_loop(image: npt.NDArray[np.float64], number_of_bins: int) -> npt.NDArray[np.float64]:
-    bin_restrictions = np.arange(0, 1, 1 / number_of_bins)
-    bins = np.zeros(number_of_bins).astype(np.float64)
-
-    for pixel in image.reshape(-1):
-        # https://stackoverflow.com/a/16244044
-        bins[np.argmax(bin_restrictions > pixel)] += 1
-
-    return bins / np.sum(bins) 
-
-# Much faster implementation than for loop
-def my_hist(image: npt.NDArray[np.float64], number_of_bins: int, img_typ: uz.ImageType) -> npt.NDArray[np.float64]:
-    if img_typ == uz.ImageType.float64: 
-        bins = np.arange(0, 1, 1 / number_of_bins)
-    elif img_typ == uz.ImageType.uint8:
-        bins = np.arange(0, 255, 255/number_of_bins)
-
-    # Put pixels into classes
-    # ex. binsize = 10 then 0.4 would map into 4
-    binarray = np.digitize(image.reshape(-1), bins).astype(np.uint8)
-
-    # Now count those values 
-    binarray = np.unique(binarray, return_counts=True)
-
-    counts = binarray[1].astype(np.float64) # Get the counts out of tuple
-
-    # Check if there is any empty bin
-    empty_bins = []
-    bins = binarray[0]
-    for i in range(1, number_of_bins + 1):
-        if i not in bins:
-            empty_bins.append(i)
-    
-    # Add empty bins with zeros
-    if empty_bins != []:
-        for i in empty_bins:
-            counts = np.insert(counts, i - 1, 0)
-
-    return counts / np.sum(counts)
-    
-
 def two_b(image_path: str, number_of_bins_first: int, number_of_bins_second: int) -> None:
     """
     Write a function myhist that accepts a grayscale image and the number of bins that
@@ -239,20 +197,20 @@ def two_b(image_path: str, number_of_bins_first: int, number_of_bins_second: int
     sum of all cells. Why is that?
     Answer:
     """
-    image = uz.imread_gray(image_path, uz.ImageType.uint8)
+    image = uz_image.imread_gray(image_path, uz_image.ImageType.uint8)
 
-    H1 = my_hist(image, number_of_bins_first, uz.ImageType.uint8)
+    H1 = uz_image.get_image_bins(image, number_of_bins_first)
-    H2 = my_hist(image, number_of_bins_second, uz.ImageType.uint8)
+    H2 = uz_image.get_image_bins(image, number_of_bins_second)
 
-    fig, (ax0, ax1, ax2) = plt.subplots(1, 3)
+    fig, axs = plt.subplots(1, 3)
-    fig.suptitle("Birdie and histgrams")
+    fig.suptitle("Birdie and histograms")
 
-    ax0.imshow(image, cmap="gray") 
+    axs[0].imshow(image, cmap="gray") 
-    ax0.set(title="Birdie image")
+    axs[0].set(title="Birdie image")
-    ax1.bar(np.arange(number_of_bins_first), H1)
+    axs[1].bar(np.arange(number_of_bins_first), H1)
-    ax1.set(title="100 bins")
+    axs[1].set(title="100 bins")
-    ax2.bar(np.arange(number_of_bins_second), H2)
+    axs[2].bar(np.arange(number_of_bins_second), H2)
-    ax2.set(title="20 bins")
+    axs[2].set(title="20 bins")
 
     plt.show()
 
@@ -264,14 +222,14 @@ def two_c(image_path: str, number_of_bins_first: int, number_of_bins_second: int
     difference between both versions of the function.
     """
 
-    image_uint8 = uz.imread_gray(image_path, uz.ImageType.uint8)
+    image_uint8 = uz_image.imread_gray(image_path, uz_image.ImageType.uint8)
-    image_float64 = uz.imread_gray(image_path, uz.ImageType.float64)
+    image_float64 = uz_image.imread_gray(image_path, uz_image.ImageType.float64)
 
-    H01 = my_hist(image_uint8, number_of_bins_first, uz.ImageType.uint8)
+    H01 = uz_image.get_image_bins(image_uint8, number_of_bins_first)
-    H02 = my_hist(image_uint8, number_of_bins_second, uz.ImageType.uint8)
+    H02 = uz_image.get_image_bins(image_uint8, number_of_bins_second)
 
-    H11 = my_hist(image_float64, number_of_bins_first, uz.ImageType.float64)
+    H11 = uz_image.get_image_bins(image_float64, number_of_bins_first)
-    H12 = my_hist(image_float64, number_of_bins_second, uz.ImageType.float64)
+    H12 = uz_image.get_image_bins(image_float64, number_of_bins_second)
 
     fig, axs = plt.subplots(2, 3)
     fig.suptitle("Comparison between two histograms")
@@ -283,7 +241,7 @@ def two_c(image_path: str, number_of_bins_first: int, number_of_bins_second: int
     axs[0, 2].bar(np.arange(number_of_bins_second), H02)
     axs[0, 2].set(title=f'{number_of_bins_second} bins used')
 
-    axs[1, 0].imshow(image_float64, cmap="gray")
+    axs[1, 0].imshow(image_uint8, cmap="gray")
     axs[1, 0].set(title="Grayscale image in uint8 representation")
     axs[1, 1].bar(np.arange(number_of_bins_first), H11)
     axs[1, 1].set(title=f'{number_of_bins_first} bins used')
@@ -298,49 +256,26 @@ def two_d() -> None:
     your web camera and change the lighting of the room. Visualize the histograms for
     all images for different number of bins and interpret the results.
     """
-    light = uz.imread_gray("./images/ROOM_LIGHTS_ON.jpg", uz.ImageType.float64)
+    imgs = []
-    darker = uz.imread_gray("./images/ONE_ROOM_LIGH_ON.jpg", uz.ImageType.float64)
+    bins = [20, 60, 100]
-    dark = uz.imread_gray("./images/DARK.jpg", uz.ImageType.float64)
+    imgs.append(uz_image.imread_gray("./images/ROOM_LIGHTS_ON.jpg", uz_image.ImageType.float64)) # light
-
+    imgs.append(uz_image.imread_gray("./images/ONE_ROOM_LIGH_ON.jpg", uz_image.ImageType.float64)) # darker
-    H10 = my_hist(light, 20, uz.ImageType.float64)
+    imgs.append(uz_image.imread_gray("./images/DARK.jpg", uz_image.ImageType.float64)) # dark
-    H11 = my_hist(light, 60, uz.ImageType.float64)
-    H12 = my_hist(light, 100, uz.ImageType.float64)
-    H20 = my_hist(darker, 20, uz.ImageType.float64)
-    H21 = my_hist(darker, 60, uz.ImageType.float64)
-    H22 = my_hist(darker, 100, uz.ImageType.float64)
-    H30 = my_hist(dark, 20, uz.ImageType.float64)
-    H31 = my_hist(dark, 60, uz.ImageType.float64) 
-    H32 = my_hist(dark, 100, uz.ImageType.float64)
 
     fig, axs = plt.subplots(3, 4)
-    fig.suptitle("spanskiduh and histgrams")
+    fig.suptitle("Me and my histograms")
     
-    axs[0, 0].imshow(light, cmap="gray") 
+    for i in range(3):
+        for j in range(3):
+            axs[i, j+1].bar(np.arange(bins[j]), uz_image.get_image_bins(imgs[i], bins[j]))
+            axs[i, j+1].set(title=f"Using {bins[j]} bins")
+
+    axs[0, 0].imshow(imgs[0], cmap="gray") 
     axs[0, 0].set(title="Image in light conditions")
-    axs[0, 1].bar(np.arange(20), H10)
+    axs[1, 0].imshow(imgs[1], cmap="gray") 
-    axs[0, 1].set(title="Using 20 bins")
-    axs[0, 2].bar(np.arange(60), H11)
-    axs[0, 2].set(title="Using 60 bins")
-    axs[0, 3].bar(np.arange(100), H12)
-    axs[0, 3].set(title="Using 100 bins")
-
-    axs[1, 0].imshow(darker, cmap="gray") 
     axs[1, 0].set(title="Image in darker conditions")
-    axs[1, 1].bar(np.arange(20), H20)
+    axs[2, 0].imshow(imgs[2], cmap="gray") 
-    axs[1, 1].set(title="Using 20 bins")
-    axs[1, 2].bar(np.arange(60), H21)
-    axs[1, 2].set(title="Using 60 bins")
-    axs[1, 3].bar(np.arange(100), H22)
-    axs[1, 3].set(title="Using 100 bins")
-
-    axs[2, 0].imshow(dark, cmap="gray") 
     axs[2, 0].set(title="Image in dark conditions")
-    axs[2, 1].bar(np.arange(20), H30)
-    axs[2, 1].set(title="Using 20 bins")
-    axs[2, 2].bar(np.arange(60), H31)
-    axs[2, 2].set(title="Using 60 bins")
-    axs[2, 3].bar(np.arange(100), H32)
-    axs[2, 3].set(title="Using 100 bins")
  
     plt.show()
 
@@ -352,39 +287,7 @@ def two_e(image: npt.NDArray[np.uint8]):
     shows the algorithm’s results on different images.
     References: https://en.wikipedia.org/wiki/Otsu%27s_method
     """
-    treshold_range = np.arange(np.max(image) + 1) 
+    return uz_image.calculate_best_treshold_using_otsu_method(image)
-    criterias = []
-
-    for treshold in treshold_range:
-        # create the thresholded image
-        thresholded_im = np.zeros(image.shape)
-
-        thresholded_im[image >= treshold] = 1
-
-        # compute weights
-        nb_pixels = image.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 = image[thresholded_im == 1]
-        val_pixels0 = image[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)]
-    print(f'best treshold is: {best_threshold}')
-    return best_threshold
 
 
 ######################################################
@@ -392,7 +295,7 @@ def two_e(image: npt.NDArray[np.uint8]):
 ######################################################
 
 def excercise_three() -> None:
-    #three_a()
+    three_a()
     #mask1, _ = three_b()
     #three_c(uz.imread('./images/bird.jpg', uz.ImageType.float64), mask1)
     #three_d()
@@ -527,6 +430,9 @@ def three_d():
     binary_mask = np.where(binary_mask < TRESHOLD, 0, 1)
     binary_mask = uz.convert_float64_array_to_uint8_array(binary_mask)
 
+    plt.imshow(binary_mask, cmap='gray')
+    plt.show()
+
     # If I would invert image here, then we would get crap 
     # So workaround:
     SE_CROSS = cv2.getStructuringElement(cv2.MORPH_CROSS, (2, 2))
@@ -582,7 +488,7 @@ def three_e():
     sizes = stats[:, -1]
 
     for blob in range(n_blobs):
-        if sizes[blob] > 700:
+        if sizes[blob] > COIN_SIZE:
             binary_mask[im_with_separated_blobs == blob] = 0
 
     three_c(coin_img_color, binary_mask)

assignment1/uz_framework/image.py

@@ -11,7 +11,7 @@ class ImageType(enum.Enum):
     uint8 = 0
     float64 = 1
 
-def imread(path: str, type: ImageType) -> npt.NDArray[np.float64] or npt.NDArray[np.uint8]:
+def imread(path: str, type: ImageType) -> Union[npt.NDArray[np.float64],  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].
@@ -24,10 +24,10 @@ def imread(path: str, type: ImageType) -> npt.NDArray[np.float64] or npt.NDArray
     elif type == ImageType.uint8:
         return I
 
-    raise Exception("Unrecognized image format!")
+    raise Exception(f"Unrecognized image format! {type}")
 
 
-def imread_gray(path: str, type: ImageType) -> npt.NDArray[np.float64] or npt.NDArray[np.uint8]:
+def imread_gray(path: str, type: ImageType) -> Union[npt.NDArray[np.float64],  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].
@@ -85,7 +85,7 @@ def transform_coloured_image_to_grayscale(image: npt.NDArray[np.float64]) -> npt
 
     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]:
+def invert_coloured_image_part(image: Union[npt.NDArray[np.float64],  npt.NDArray[np.uint8]], startx: int, endx: int, starty: int, endy: int) -> Union[npt.NDArray[np.float64],  npt.NDArray[np.uint8]]:
     """
     Accepts image, starting position end end position for axes x & y. Returns whole image with inverted part.
     """
@@ -108,13 +108,13 @@ def invert_coloured_image_part(image: npt.NDArray[np.float64] or npt.NDArray[np.
 
     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]:
+def invert_coloured_image(image: Union[npt.NDArray[np.float64],  npt.NDArray[np.uint8]]) -> Union[npt.NDArray[np.float64],  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:
+def calculate_best_treshold_using_otsu_method(image: Union[npt.NDArray[np.float64],  npt.NDArray[np.uint8]]) -> int:
     """
     Accepts image and returns best treshold using otsu method
     """
@@ -159,3 +159,57 @@ def calculate_best_treshold_using_otsu_method(image: npt.NDArray[np.float64] or
 
     best_threshold = treshold_range[np.argmin(criterias)]
     return best_threshold
+
+
+def get_image_bins_for_loop(image: Union[npt.NDArray[np.float64],  npt.NDArray[np.uint8]], number_of_bins: int) -> npt.NDArray[np.float64]:
+    """
+    Accepts image in the float64 format or uint8, returns normailzed
+    image bins, histogram
+    """
+    if image.dtype.type == np.float64 or image.dtype.type == np.uint8: 
+        bin_restrictions = np.linspace(np.min(image), np.max(image), num=number_of_bins)
+    else:
+        raise Exception("Unrecognized image format!")
+
+    bins = np.zeros(number_of_bins).astype(np.float64)
+
+    for pixel in image.reshape(-1):
+        # https://stackoverflow.com/a/16244044
+        bins[np.argmax(bin_restrictions > pixel)] += 1
+
+    return bins / np.sum(bins)
+
+
+# Much faster implementation than for loop
+def get_image_bins(image: Union[npt.NDArray[np.float64],  npt.NDArray[np.uint8]], number_of_bins: int) -> npt.NDArray[np.float64]:
+    """
+    Accepts image in the float64 format or uint8, returns normailzed
+    image bins, histogram
+    """
+    if image.dtype.type == np.float64 or image.dtype.type == np.uint8: 
+        bins = np.linspace(np.min(image), np.max(image), num=number_of_bins)
+    else:
+        raise Exception("Unrecognized image format!")
+
+    # Put pixels into classes
+    # ex. binsize = 10 then 0.4 would map into 4
+    binarray = np.digitize(image.reshape(-1), bins).astype(np.uint8)
+
+    # Now count those values 
+    binarray = np.unique(binarray, return_counts=True)
+
+    counts = binarray[1].astype(np.float64) # Get the counts out of tuple
+
+    # Check if there is any empty bin
+    empty_bins = []
+    bins = binarray[0]
+    for i in range(1, number_of_bins + 1):
+        if i not in bins:
+            empty_bins.append(i)
+    
+    # Add empty bins with zeros
+    if empty_bins != []:
+        for i in empty_bins:
+            counts = np.insert(counts, i - 1, 0)
+
+    return counts / np.sum(counts)