openCV 一 安装、图像二值化、边缘检测

安装

1、window + pycharm

图像二值化（转自：假小牙）

threshold：固定阈值二值化

ret, dst = cv2.threshold(src, thresh, maxval, type)

• src： 输入图，只能输入单通道图像，通常来说为灰度图
• dst： 输出图
• thresh： 阈值
• maxval： 当像素值超过了阈值（或者小于阈值，根据type来决定），所赋予的值
• type：二值化操作的类型，包含以下5种类型： cv2.THRESH_BINARY； cv2.THRESH_BINARY_INV； cv2.THRESH_TRUNC； cv2.THRESH_TOZERO；cv2.THRESH_TOZERO_INV

官方文档的示例代码：

import cv2
import numpy as np
from matplotlib import pyplot as plt
img = cv2.imread('gradient.png',0)
ret,thresh1 = cv2.threshold(img,127,255,cv2.THRESH_BINARY)
ret,thresh2 = cv2.threshold(img,127,255,cv2.THRESH_BINARY_INV)
ret,thresh3 = cv2.threshold(img,127,255,cv2.THRESH_TRUNC)
ret,thresh4 = cv2.threshold(img,127,255,cv2.THRESH_TOZERO)
ret,thresh5 = cv2.threshold(img,127,255,cv2.THRESH_TOZERO_INV)
titles = ['Original Image','BINARY','BINARY_INV','TRUNC','TOZERO','TOZERO_INV']
images = [img, thresh1, thresh2, thresh3, thresh4, thresh5]
for i in range(6):
    plt.subplot(2,3,i+1),plt.imshow(images[i],'gray')
    plt.title(titles[i])
    plt.xticks([]),plt.yticks([])
plt.show()

adaptiveThreshold：自适应阈值二值化

自适应阈值二值化函数根据图片一小块区域的值来计算对应区域的阈值，从而得到也许更为合适的图片。

dst = cv2.adaptiveThreshold(src, maxval, thresh_type, type, Block Size, C)

• src： 输入图，只能输入单通道图像，通常来说为灰度图
• dst： 输出图
• maxval： 当像素值超过了阈值（或者小于阈值，根据type来决定），所赋予的值
• thresh_type： 阈值的计算方法，包含以下2种类型：cv2.ADAPTIVE_THRESH_MEAN_C； cv2.ADAPTIVE_THRESH_GAUSSIAN_C.
• type：二值化操作的类型，与固定阈值函数相同，包含以下5种类型： cv2.THRESH_BINARY； cv2.THRESH_BINARY_INV； cv2.THRESH_TRUNC； cv2.THRESH_TOZERO；cv2.THRESH_TOZERO_INV.
• Block Size： 图片中分块的大小
• C ：阈值计算方法中的常数项

import cv2
import numpy as np
from matplotlib import pyplot as plt

img = cv2.imread('sudoku.png', 0)
img = cv2.medianBlur(img, 5)
ret, th1 = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY)
th2 = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 11, 2)
th3 = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2)
titles = ['Original Image', 'Global Thresholding (v = 127)',
          'Adaptive Mean Thresholding', 'Adaptive Gaussian Thresholding']
images = [img, th1, th2, th3]
for i in range(4):
    plt.subplot(2, 2, i + 1), plt.imshow(images[i], 'gray')
    plt.title(titles[i])
    plt.xticks([]), plt.yticks([])
plt.show()

Otsu’s Binarization: 基于直方图的二值化 （Otsu:最大类间方差法）

 

import cv2
import numpy as np
from matplotlib import pyplot as plt

img = cv2.imread('noisy2.png', 0)
# global thresholding
ret1, th1 = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY)
# Otsu's thresholding
ret2, th2 = cv2.threshold(img, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
# Otsu's thresholding after Gaussian filtering
blur = cv2.GaussianBlur(img, (5, 5), 0)
ret3, th3 = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
# plot all the images and their histograms
images = [img, 0, th1,
          img, 0, th2,
          blur, 0, th3]
titles = ['Original Noisy Image', 'Histogram', 'Global Thresholding (v=127)',
          'Original Noisy Image', 'Histogram', "Otsu's Thresholding",
          'Gaussian filtered Image', 'Histogram', "Otsu's Thresholding"]
for i in range(3):
    plt.subplot(3, 3, i * 3 + 1), plt.imshow(images[i * 3], 'gray')
    plt.title(titles[i * 3]), plt.xticks([]), plt.yticks([])
    plt.subplot(3, 3, i * 3 + 2), plt.hist(images[i * 3].ravel(), 256)
    plt.title(titles[i * 3 + 1]), plt.xticks([]), plt.yticks([])
    plt.subplot(3, 3, i * 3 + 3), plt.imshow(images[i * 3 + 2], 'gray')
    plt.title(titles[i * 3 + 2]), plt.xticks([]), plt.yticks([])
plt.show()

 

 边缘检测

1、边缘检测滤波函数（Laplacian,Sobel,Scharr）,滤波函数会把非边缘区域转换为黑色，将边缘区域转化白色或其他饱和的颜色。

2、由于滤波函数会把噪声识别为边缘，缓解这个问题的办法是对图像进行模糊处理

3、得到Laplacian函数的结果后，需要将其转化为黑色边缘和白色背景的图像，然后将其归一化（使其像素值在0和1之间，并乘以原图以便能将边缘变黑）

import numpy as np
import cv2


def strokeEdge(src, dst, blurKsize=7, edgeKsize=5):
    if blurKsize >= 3:
        blurSrc = cv2.medianBlur(src, blurKsize)
        graySrc = cv2.cvtColor(blurSrc, cv2.COLOR_BGR2GRAY)
    else:
        graySrc = cv2.cvtColor(src, cv2.COLOR_BGR2GRAY)
    cv2.Laplacian(graySrc, cv2.CV_8U, graySrc, ksize=edgeKsize)
    normalizedInverseAlpha = (1.0 / 255) * (255 - graySrc)
    channels = cv2.split(src)
    for channel in channels:
        channel[:] = channel * normalizedInverseAlpha
    cv2.merge(channels, dst)
    cv2.imshow("origin", src)
    cv2.imshow("Laplacian", graySrc)
    cv2.imshow("normalizedInverse", dst)


if __name__ == '__main__':
    img = cv2.imread("img/1.jpg")
    image = np.zeros(img.shape,img.dtype)
    strokeEdge(img, image)
    cv2.waitKey(0)

 Canny边缘检测

img = cv2.imread("img/1.jpg", 0)
# cv2.imwrite("canny.jpg",cv2.Canny(img, 200, 300))
cv2.imshow("origin", img)
cv2.imshow("canny", cv2.Canny(img, 200, 300))
cv2.waitKeyEx(0)
cv2.destroyAllWindows()