轮廓检测

Python 图像处理

Rebeca Gonzalez

Data Engineer

轮廓检测

测量尺寸
分类形状
计算对象数量

多米诺子上的点数：29。

二值图像

可通过应用阈值分割或使用边缘检测获得二值图像。

用 scikit-image 查找轮廓

准备图像

将图像转为二维灰度。

# Make the image grayscale
image = color.rgb2gray(image)

用 scikit-image 查找轮廓

准备图像

将图像二值化

# Obtain the thresh value
thresh = threshold_otsu(image)

# Apply thresholding
thresholded_image = image > thresh

用 scikit-image 查找轮廓

然后使用 find_contours()。

# Import the measure module
from skimage import measure

# Find contours at a constant value of 0.8
contours = measure.find_contours(thresholded_image, 0.8)

恒定水平值

检测轮廓的步骤

from skimage import measure
from skimage.filters import threshold_otsu

# Make the image grayscale
image = color.rgb2gray(image)

# Obtain the optimal thresh value of the image
thresh = threshold_otsu(image)

# Apply thresholding and obtain binary image
thresholded_image = image > thresh


# Find contours at a constant value of 0.8
contours = measure.find_contours(thresholded_image, 0.8)

检测轮廓的步骤

结果

轮廓的形状

轮廓：由形状为 (n,2) 的 ndarray 构成的列表。

for contour in contours:
    print(contour.shape)

(433, 2)
(433, 2)
(401, 2)
(401, 2) 
(123, 2)
(123, 2) 
(59, 2)
(59, 2)
(59, 2)
(57, 2)
(57, 2)
(59, 2)
(59, 2)

轮廓的形状

for contour in contours:
    print(contour.shape)

(433, 2)
(433, 2) --> Outer border
(401, 2)
(401, 2)
(123, 2)
(123, 2)
(59, 2)
(59, 2)
(59, 2)
(57, 2)
(57, 2)
(59, 2)
(59, 2)

轮廓的形状

for contour in contours:
    print(contour.shape)

(433, 2)
(433, 2) --> Outer border
(401, 2)
(401, 2) --> Inner border
(123, 2)
(123, 2) 
(59, 2)
(59, 2)
(59, 2)
(57, 2)
(57, 2)
(59, 2)
(59, 2)

轮廓的形状

for contour in contours:
    print(contour.shape)

(433, 2)
(433, 2) --> Outer border
(401, 2)
(401, 2) --> Inner border
(123, 2)
(123, 2) --> Divisory line of tokens
(59, 2)
(59, 2)
(59, 2)
(57, 2)
(57, 2)
(59, 2)
(59, 2)

轮廓的形状

for contour in contours:
    print(contour.shape)

(433, 2)
(433, 2) --> Outer border
(401, 2)
(401, 2) --> Inner border
(123, 2)
(123, 2) --> Divisory line of tokens
(59, 2)
(59, 2)
(59, 2)
(57, 2)
(57, 2)
(59, 2)
(59, 2) --> Dots

点的数量：7。

Passons à la pratique !

Python 图像处理