python opencv的最基础初学

滤波

 这个在MATLAB叫点乘，内积不是这个。而且内积是欧几里得空间定义的，矩阵的标准内积

121    75     78

24     204    113

154   104     235

几个取平均

算法里说了nXn的滤波一般是奇数

img = cv2. imread('lenaNoise. png')
cv2. imshow('img', img)
cv2. waitKey(0)
cv2.destroyAllWindows()

#均值滤波
#简单的平均卷积操作
blur = cv2.blur(img, (3, 3))
cv2.imshow('blur', blur)
cv2. waitKey(0)
cv2.destroyAllWindows()
#方框滤波
#基本和均值一样，可以选择归一化
box = cv2. boxFilter(img,-1,(3,3), normalize=True)
cv2. imshow('box', box)
cv2. waitKey(0)
cv2.destroyAllWindows()

#方框滤波
#基本和均值一样，可以选择归一化，容易越界
#越界就是全变为255
box = cv2. boxFilter(img,-1,(3,3), normalize=False)
cv2. imshow('box', box)
cv2.waitKey(0)
cv2.destroyAllWindows()

#高斯滤波
#高斯模糊的卷积核里的数值是满足高斯分布，相当于更重视中间的
aussian = cv2. GaussianBlur(img,(5,5),1)
#1表示权重，就是选取的那个最重要的值，离那个值越远，越不重要，所以比重就越低
cv2. imshow('aussian', aussian)
cv2. waitKey(0)
cv2. destroyAllWindows

#中值滤波
#相当于用中值代替
median = cv2.medianBlur(img, 5)#中值滤波
cv2. imshow('median', median)
cv2.waitKey(0)
cv2. destroyAllWindows()

中值滤波除噪点确实很强，但代价是图像细节损失的最为严重

#展示所有的  
res = np. hstack((blur. aussian. median))
#可以换成vstack
cv2. imshow(' meaian vs average'. res)
cv2. waitKey(0)
cv2. destroyAHWindows()

形态学-腐蚀操作

阈值吃力刚刚好啊bushi       It is useful for removing small white noises

 不同的核大小腐蚀程度不一样

img = cv2. imreadC dige. png')
cv2. imshowC itng'. img)
cv2. waiiKey(O)
cv2. destroyAllWindows ()
 
 
kernel = np. ones ((3,3), np. uint8)
erosion = cv2. erode(img. kernel. iterations= 2)
cv2. imshow('erosion', erosion)
cv2.waitKey(0)
cv2. destroyAllWindows()
 
 
pie = cv2. imread('pie. png')
cv2. imshow('pie'. pie)
cv2. waixKey(0)
cv2. destroyA11Windows()
 
 
#集合
kernel = np. ones ((30,30), np. uint8)
erosion_l = cv2. erode(pie, kernel, iterations = 1)
erosion_2 = cv2. erode(pie, kernel, iterations = 2)
erosion_3 = cv2. erode(pie, kernel, iterations = 3)
res = np. hstack((erosion_l, erosion_2,erosion_3))
cv2. imshow('res', res)
cv2.waitKey(0)
cv2. destroyAllWindows ()

 kernel到底是什么？ 

形态学-膨胀操作

img = cv2. inread ('dige. png')
cv2. imshow('img'. img)
cv2.waitKey(0)
cv2. destroyAllWindows()
 
 
 
kernel = np. ones((3. 3),np. uint8)
erosion = cv2. erode(img, kernel, iterations = 1)
cv2. imshow(' erosion', erosion)
cv2. waitKey(0)
cv2. desrroyAllWindows()
 
 
pie = cv2. imread (' pie. png')
cv2. imshow('pie', pie)
cv2. waitKey(0)
cv2. destroyAllWindows()
 
 
kernel = np. ones((30.30). np. uint8)
erosion_l = cv2. erode(pie, kernel, iterations = 1)
erosion_2 = cv2. erode(pie, kernel, iterations = 2)
erosion_3 = cv2. erode(pie, kernel, iterations = 3)
res = np. hstack((erosion_l, erosion_2, erosion_3))
cv2. imshow('res', res)
cv2.waitKey(0)
cv2. destroyAllWindows()

kernel核矩阵越小，越近圆

开运算和闭运算

把腐蚀膨胀合在一起了，用来提取前景或者提取噪音 huh？

#开:先腐 ,再 胀
img = cv2. imread(' dige. png')
kernel = np. ones((5.5), np. uint8)
opening = cv2. morphologyExCimg. cv2. MORHi.WEN. kernel)
cv2. imshow('opening'. opening)
cv2. waitKey(0)
cv2. destroyAllWindows()
 
 
#：先房底.再用蚀
img = cv2. imread('dige. png')
kernel = np. ones ((5.5). np. uint8)
closing = cv2. morphologyExdmg. cv2. MORPH_CLOSE, kernel)
cv2. imshow('closing',closing)
cv2. waitKey(O)
cv2. destroyAllWindows()

梯度运算

感觉地方感觉有点问题。膨胀减掉腐蚀的图像应该和梯度操作的结果不太一样。最后的边界的宽度差异很大。梯度 = 原图 - 腐蚀.

#梯度=影胀-腐蚀?
pie = cv2. imread('pie. png')
kernel = np. ones((7,7), np. uint8)
dilate = cv2. di late(pie, kernel, iterations = 5)
erosion = cv2. erode(pie, kernel.iterations = 5)
 
res = np. hstack((dilate. erosion))
 
cv2. imshow('res', res)
cv2.wairKey(0)
cv2. destroyAllWindows()
 
 
gradient = cv2. morphologyEx(pie,cv2. MORPH_GRADIENT,kernel)
 
cv2. imshow('gradient', gradient)
cv2. waitKey(0)
cv2. destroyAllWindows()

礼帽和黑帽

剩下毛边和剩下原轮廓

#礼帽=原始输入-开运算结果
#黑帽=闭运算-原始输入
 
#礼帽
lag = cv2. imread（'dige. png')
tophar = cv2. morphologyEx(img. cv2. MORPH_TOPHAT. kernel)
cv2. imsho,(' tophat'. tophat)
cv2. waitKey(O)
cv2. destroyAllWindows()
 
 
#黑帽
img = cv2. imread(' dige. png')
blackhat = cv2. morphologyEx(img, cv2. MORPH_BLAG{HAT. kernel)
cv2. imshow('blackhat '. blackhat )
cv2.waitKey(0)
cv2. destroyAllWindows()