Tasvirlarga morfologik ishlov berish algoritmlari. Algoritmlar uchun dasturiy ta`minot ishlab chiqish
![(7-rasm) Noto'g'ri tasvir fonini tuzatish uchun protrusion transformatsiyani
qo'llaydi. (a) 600x600 piksel o'lchamdagi asl rasm. (b) chegaradan keyingi rasm.
(c) radiusi 40 piksel bo'lgan aylana ibtidoiy bo'ylab ochish operatsiyasi natijasi. (d)
"Protrusion" transformatsiyasining natijasi (asl tasvirni ochish natijasini hisobga
olmaganda). (e) o'zgartirilgan tasvirni chegaralash natijasi.
2.Amaliy qism
2.1 . Morfologik ishlov berish algoritmining dasturiy ta`minotini ishlab
chiqish
1. Erosiya (yemirilish).
import numpy as np
from PIL import Image
def rgb2gray(rgb: np.array) -> np.array:
"""
Return gray image from rgb image
>>> rgb2gray(np.array([[[127, 255, 0]]]))
array([[187.6453]])
>>> rgb2gray(np.array([[[0, 0, 0]]]))
array([[0.]])
>>> rgb2gray(np.array([[[2, 4, 1]]]))
array([[3.0598]])
>>> rgb2gray(np.array([[[26, 255, 14], [5, 147, 20], [1, 200, 0]]]))
11](https://docx.uz/documents/11dcf4c2-0d3e-4921-ac6f-7df6d5a5c8a7/page_11.png?v=1)
![array([[159.0524, 90.0635, 117.6989]])
"""
r, g, b = rgb[:, :, 0], rgb[:, :, 1], rgb[:, :, 2]
return 0.2989 * r + 0.5870 * g + 0.1140 * b
def gray2binary(gray: np.array) -> np.array:
"""
Return binary image from gray image
>>> gray2binary(np.array([[127, 255, 0]]))
array([[False, True, False]])
>>> gray2binary(np.array([[0]]))
array([[False]])
>>> gray2binary(np.array([[26.2409, 4.9315, 1.4729]]))
array([[False, False, False]])
>>> gray2binary(np.array([[26, 255, 14], [5, 147, 20], [1, 200, 0]]))
array([[False, True, False],
[False, True, False],
[False, True, False]])
"""
return (127 < gray) & (gray <= 255)
def erosion(image: np.array, kernel: np.array) -> np.array:
"""
Return eroded image
>>> erosion(np.array([[True, True, False]]), np.array([[0, 1, 0]]))
array([[False, False, False]])
>>> erosion(np.array([[True, False, False]]), np.array([[1, 1, 0]]))
array([[False, False, False]])
"""
output = np.zeros_like(image)
image_padded = np.zeros(
12](https://docx.uz/documents/11dcf4c2-0d3e-4921-ac6f-7df6d5a5c8a7/page_12.png?v=1)
![(image.shape[0] + kernel.shape[0] - 1, image.shape[1] +
kernel.shape[1] - 1)
)
# Copy image to padded image
image_padded[kernel.shape[0] - 2 : -1 :, kernel.shape[1] - 2 : -1 :] =
image
# Iterate over image & apply kernel
for x in range(image.shape[1]):
for y in range(image.shape[0]):
summation = (
kernel * image_padded[y : y + kernel.shape[0], x : x +
kernel.shape[1]]
).sum()
output[y, x] = int(summation == 5)
return output
# kernel to be applied
structuring_element = np.array([[0, 1, 0], [1, 1, 1], [0, 1, 0]])
if __name__ == "__main__":
# read original image
image = np.array(Image.open(r"test1.jpg"))
# Apply erosion operation to a binary image
output = erosion(gray2binary(rgb2gray(image)), structuring_element)
# Save the output image
pil_img = Image.fromarray(output).convert("RGB")
pil_img.save("result_erosion.png")
2. Dilitatsiya (kengaytirish).
13](https://docx.uz/documents/11dcf4c2-0d3e-4921-ac6f-7df6d5a5c8a7/page_13.png?v=1)
![import numpy as np
from PIL import Image
def rgb2gray(rgb: np.array) -> np.array:
"""
Return gray image from rgb image
>>> rgb2gray(np.array([[[127, 255, 0]]]))
array([[187.6453]])
>>> rgb2gray(np.array([[[0, 0, 0]]]))
array([[0.]])
>>> rgb2gray(np.array([[[2, 4, 1]]]))
array([[3.0598]])
>>> rgb2gray(np.array([[[26, 255, 14], [5, 147, 20], [1, 200, 0]]]))
array([[159.0524, 90.0635, 117.6989]])
"""
r, g, b = rgb[:, :, 0], rgb[:, :, 1], rgb[:, :, 2]
return 0.2989 * r + 0.5870 * g + 0.1140 * b
def gray2binary(gray: np.array) -> np.array:
"""
Return binary image from gray image
>>> gray2binary(np.array([[127, 255, 0]]))
array([[False, True, False]])
>>> gray2binary(np.array([[0]]))
array([[False]])
>>> gray2binary(np.array([[26.2409, 4.9315, 1.4729]]))
array([[False, False, False]])
>>> gray2binary(np.array([[26, 255, 14], [5, 147, 20], [1, 200, 0]]))
array([[False, True, False],
[False, True, False],
[False, True, False]])
14](https://docx.uz/documents/11dcf4c2-0d3e-4921-ac6f-7df6d5a5c8a7/page_14.png?v=1)
!["""
return (127 < gray) & (gray <= 255)
def dilation(image: np.array, kernel: np.array) -> np.array:
"""
Return dilated image
>>> dilation(np.array([[True, False, True]]), np.array([[0, 1, 0]]))
array([[False, False, False]])
>>> dilation(np.array([[False, False, True]]), np.array([[1, 0, 1]]))
array([[False, False, False]])
"""
output = np.zeros_like(image)
image_padded = np.zeros(
(image.shape[0] + kernel.shape[0] - 1, image.shape[1] +
kernel.shape[1] - 1)
)
# Copy image to padded image
image_padded[kernel.shape[0] - 2 : -1 :, kernel.shape[1] - 2 : -1 :] =
image
# Iterate over image & apply kernel
for x in range(image.shape[1]):
for y in range(image.shape[0]):
summation = (
kernel * image_padded[y : y + kernel.shape[0], x : x +
kernel.shape[1]]
).sum()
output[y, x] = int(summation > 0)
return output
# kernel to be applied
15](https://docx.uz/documents/11dcf4c2-0d3e-4921-ac6f-7df6d5a5c8a7/page_15.png?v=1)
![structuring_element = np.array([[0, 1, 0], [1, 1, 1], [0, 1, 0]])
if __name__ == "__main__":
# read original image
image = np.array(Image.open(r"test1.jpg"))
output = dilation(gray2binary(rgb2gray(image)), structuring_element)
# Save the output image
pil_img = Image.fromarray(output).convert("RGB")
pil_img.save("result_dilation.png")
(8-rasm) Erosiya va Dilitatsiya(kengaytirish).
16](https://docx.uz/documents/11dcf4c2-0d3e-4921-ac6f-7df6d5a5c8a7/page_16.png?v=1)
Tasvirlarga morfologik ishlov berish algoritmlari. Algoritmlar uchun dasturiy ta`minot ishlab chiqish