OPENCV

最新推荐文章于 2021-09-29 09:36:54 发布
最新推荐文章于 2021-09-29 09:36:54 发布
阅读量298 收藏 1
点赞数 2
分类专栏： 学习笔记 文章标签： 计算机视觉 opencv cv
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/weixin_47654347/article/details/112231618
版权

day 1

import cv2
lena = cv2.imread('C:\\AppData\\image\\1.png',0)
cv2.imshow("domo",lena)
cv2.waitKey()
cv2.destroyWindow("domo")

import cv2
img = cv2.imread('C:\\AppData\\image\\1.png',0)
cv2.imshow("befor",img)
for i in range(10,100):
    for j in range(80,200):
        img[i,j] = 0
cv2.imshow("after",img)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
img = np.zeros((300,300,3),dtype = np.uint8)
img[:,0:100,2] = 255
img[:,100:200,1] = 255
img[:,200:300,0] = 255
cv2.imshow("img",img)
cv2.waitKey()

import numpy as np
import cv2
img = np.random.randint(0,256,size = [256,256],dtype = np.uint8)
cv2.imshow("demo",img)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
lena = cv2.imread("C:\\AppData\\image\\pyimg.jpg")
cv2.imshow("lena",lena)
#b = lena[:,:,0]
#g = lena[:,:,1]
#r = lena[:,:,2]
b,g,r = cv2.split(lena)
cv2.imshow("b",b)
cv2.imshow("g",g)
cv2.imshow("r",r)
lena[:,:,0] = 0
cv2.imshow("lena0",lena)
lena[:,:,1] = 0
cv2.imshow("lena1",lena)
cv2.waitKey()
cv2.destroyAllWindows()

day2

import cv2
import numpy as np
lena = cv2.imread("C:\\AppData\\image\\pyimg.jpg",-1)
b = np.zeros(lena.shape,dtype = np.uint8)
b[100:300,200:300] = 255
c = cv2.bitwise_and(lena,b)
cv2.imshow("lena",lena)
cv2.imshow("b",b)
cv2.imshow("c",c)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2#位层提取
import numpy as np
lena = cv2.imread("C:\\AppData\\image\\pyimg.jpg",0)
cv2.imshow("lena",lena)
r,c = lena.shape
x = np.zeros((r,c,8),dtype = np.uint8)
for i in range(8):
    x[:,:,i] = 2**i
y = np.zeros((r,c,8),dtype = np.uint8)
for i in range(8):
    y[:,:,i] = cv2.bitwise_and(lena,x[:,:,i])
    mask = y[:,:,i] > 0
    y[mask] = 255
    cv2.imshow(str(i),y[:,:,i])
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2
import numpy as np
lena = cv2.imread("C:\\AppData\\image\\120.jpg",1)
cv2.imshow("lena",lena)
hsv = cv2.cvtColor(lena,cv2.COLOR_BGR2HSV)
minBlue = np.array([110,50,50])
maxBlue = np.array([130,255,255])

mask = cv2.inRange(hsv,minBlue,maxBlue)

blue = cv2.bitwise_and(lena,lena,mask = mask)
cv2.imshow("blue",blue)

minGreen = np.array([50,50,50])
maxGreen = np.array([70,255,255])

mask = cv2.inRange(hsv,minGreen,maxGreen)

green = cv2.bitwise_and(lena,lena,mask = mask)
cv2.imshow("green",green)

minRed = np.array([0,50,50])
maxRed = np.array([30,255,255])

mask = cv2.inRange(hsv,minRed,maxRed)

red = cv2.bitwise_and(lena,lena,mask = mask)
cv2.imshow("red",red)

cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2
import numpy as np
lena = cv2.imread("C:\\AppData\\image\\2.jpg",1)
cv2.imshow("lena",lena)
hsv = cv2.cvtColor(lena,cv2.COLOR_BGR2HSV)
h,s,v = cv2.split(hsv)
minHue = 5
maxHue = 170
hueMask = cv2.inRange(h,minHue,maxHue)
minSat = 25
maxSat = 166
satMask = cv2.inRange(s,minSat,maxSat)
mask = hueMask & satMask
img = cv2.bitwise_and(lena,lena,mask = mask)
cv2.imshow("img",img)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2
import numpy as np
lena = cv2.imread("C:\\AppData\\image\\2.jpg",1)
cv2.imshow("lena",lena)
hsv = cv2.cvtColor(lena,cv2.COLOR_BGR2HSV)
h,s,v = cv2.split(hsv)
v[:,:] = 255
newhsv = cv2.merge([h,s,v])
art = cv2.cvtColor(lena,cv2.COLOR_HSV2BGR)
cv2.imshow("atr",art)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2#旋转
img = cv2.imread("C:\\AppData\\image\\2.jpg",1)
#rst = cv2.resize(img,None,fx = 2,fy = 0.5)
#print("img.shape = ",img.shape)
#print("rst.shape = ",rst.shape)
x = cv2.flip(img,0)
y = cv2.flip(img,1)
xy = cv2.flip(img,-1)
cv2.imshow("new1",x)
cv2.imshow("new12",y)
cv2.imshow("new2",xy)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
img = cv2.imread("C:\\AppData\\image\\2.jpg",1)
height,width = img.shape[:2]
x = 100
y = 200
M = cv2.getRotationMatrix2D((width/2,height/2),45,0.6)
rotate = cv2.warpAffine(img,M,(width,height))
#rst = cv2.resize(img,None,fx = 2,fy = 0.5)
#print("img.shape = ",img.shape)
#print("rst.shape = ",rst.shape)
#x = cv2.flip(img,0)
#y = cv2.flip(img,1)
#xy = cv2.flip(img,-1)
cv2.imshow("new1",img)
cv2.imshow("new12",rotate)
#cv2.imshow("new2",xy)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\2.jpg",1)
rows,cols,ch = img.shape
p1 = np.float32([[0,0],[cols-1,0],[0,rows-1]])#三个点
p2 = np.float32([[0,rows*0.33],[cols*0.85,rows*0.25],[cols*0.15,rows*0.7]])#三个点
M = cv2.getAffineTransform(p1,p2)#前三个后三个求转化矩阵
dst = cv2.warpAffine(img,M,(cols,rows))
cv2.imshow("img",img)
cv2.imshow("dst",dst)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\2.jpg",1)
rows,cols,ch = img.shape
p1 = np.float32([[150,50],[400,50],[60,450],[314,450]])
p2 = np.float32([[50,50],[cols-50,50],[50,rows-50],[rows-50,cols-50]])
M = cv2.getPerspectiveTransform(p1,p2)
dst = cv2.warpPerspective(img,M,(cols,rows))
cv2.imshow("img",img)
cv2.imshow("dst",dst)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2#重映射——复制
import numpy as np
img = cv2.imread("C:\\AppData\\image\\2.jpg",1)
rows,cols,ch = img.shape
mapx = np.zeros(img.shape[:2],np.float32)
mapy = np.zeros(img.shape[:2],np.float32)
for i in range(rows):
    for j in range(cols):
        mapx.itemset((i,j),j)
        mapy.itemset((i,j),i)
        
dst = cv2.remap(img,mapx,mapy,cv2.INTER_LINEAR)
cv2.imshow("img",img)
cv2.imshow("dst",dst)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2#缩放
import numpy as np
img = cv2.imread("C:\\AppData\\image\\2.jpg",1)
rows,cols,ch = img.shape
mapx = np.zeros(img.shape[:2],np.float32)
mapy = np.zeros(img.shape[:2],np.float32)
for i in range(rows):
    for j in range(cols):
        if 0.25*cols < i <0.75*cols and 0.25*rows < j < 0.75*rows:
            mapx.itemset((i,j),2*(j-cols*0.25)+0.5)
            mapy.itemset((i,j),2*(i-rows*0.25)+0.5)
        else:
            mapx.itemset((i,j),0)
            mapy.itemset((i,j),0)
        
dst = cv2.remap(img,mapx,mapy,cv2.INTER_LINEAR)
cv2.imshow("img",img)
cv2.imshow("dst",dst)
cv2.waitKey()
cv2.destroyAllWindows()

Day3

在这里插入图片描述

import cv2#二值化
import numpy as np
img = cv2.imread("C:\\AppData\\image\\2.jpg",1)
t,rst = cv2.threshold(img,127,255,cv2.THRESH_BINARY_INV)
r,rst1 = cv2.threshold(img,127,255,cv2.THRESH_BINARY)
cv2.imshow("img",img)
cv2.imshow("rst",rst)
cv2.imshow("rst1",rst1)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\2.jpg",1)
t,rst = cv2.threshold(img,127,255,cv2.THRESH_TOZERO_INV)#trunc

#r,rst1 = cv2.threshold(img,127,255,cv2.THRESH_BINARY)
cv2.imshow("img",img)
cv2.imshow("rst",rst)
#cv2.imshow("rst1",rst1)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\2.jpg",1)
t,rst = cv2.threshold(img,127,255,cv2.THRESH_TOZERO)#trunc

#r,rst1 = cv2.threshold(img,127,255,cv2.THRESH_BINARY)#_INV
cv2.imshow("img",img)
cv2.imshow("rst",rst)
#cv2.imshow("rst1",rst1)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\2.jpg",0)
t1,thd = cv2.threshold(img,127,255,cv2.THRESH_BINARY)#trunc
athdMEAN = cv2.adaptiveThreshold(img,255,cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,5,3)
athdGAUS = cv2.adaptiveThreshold(img,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY,5,3)

cv2.imshow("img",img)
cv2.imshow("thd",thd)
cv2.imshow("athdMEAN",athdMEAN)
cv2.imshow("athdGAUS",athdGAUS)

cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\2.jpg",0)
t1,thd = cv2.threshold(img,127,255,cv2.THRESH_BINARY)#trunc
#athdMEAN = cv2.adaptiveThreshold(img,255,cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,7,3)
#athdGAUS = cv2.adaptiveThreshold(img,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY_INV,7,3)
t2,otsu = cv2.threshold(img,200,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
print(t2)
cv2.imshow("img",img)
cv2.imshow("thd",thd)
cv2.imshow("athdMEAN",otsu)
#cv2.imshow("athdGAUS",athdGAUS)

cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述
在这里插入图片描述

import cv2#去噪
import numpy as np
img = cv2.imread("C:\\AppData\\image\\120.jpg")
r5 = cv2.blur(img,(10,10))
cv2.imshow("img",img)
cv2.imshow("r5",r5)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\120.jpg")
r5 = cv2.GaussianBlur(img,(5,5),0,0)
cv2.imshow("img",img)
cv2.imshow("r5",r5)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\120.jpg")
r5 = cv2.medianBlur(img,5)
cv2.imshow("img",img)
cv2.imshow("r5",r5)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\120.jpg")
r5 = cv2.bilateralFilter(img,25,160,160)
cv2.imshow("img",img)
cv2.imshow("r5",r5)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\120.jpg")
#r5 = cv2.bilateralFilter(img,25,160,160)
kernel = np.ones((9,9),np.float32)/81#自定义卷积核
r5 = cv2.filter2D(img,-1,kernel)
cv2.imshow("img",img)
cv2.imshow("r5",r5)
cv2.waitKey()
cv2.destroyAllWindows()

day4

import cv2#腐蚀
img = cv2.imread("C:\\AppData\\image\\001.jpg",cv2.IMREAD_UNCHANGED)
kernel = np.ones((10,10),np.uint8)
dst = cv2.erode(img,kernel,iterations = 5)
cv2.imshow("img",img)
cv2.imshow("dst",dst)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2#膨胀
img = cv2.imread("C:\\AppData\\image\\001.jpg",cv2.IMREAD_UNCHANGED)
kernel = np.ones((10,10),np.uint8)
dst = cv2.dilate(img,kernel,iterations = 5)
cv2.imshow("img",img)
cv2.imshow("dst",dst)
cv2.waitKey()
cv2.destroyAllWindows()

通用形态学 cv2.morphologyEx()

在这里插入图片描述

import cv2
img = cv2.imread("C:\\AppData\\image\\001.jpg",cv2.IMREAD_UNCHANGED)
kernel = np.ones((10,10),np.uint8)
dst = cv2.morphologyEx(img,cv2.MORPH_OPEN,kernel)
cv2.imshow("img",img)
cv2.imshow("dst",dst)
cv2.waitKey()
cv2.destroyAllWindows()

dst = cv2.morphologyEx(img,cv2.MORPH_CLOSE,kernel)


dst = cv2.morphologyEx(img,cv2.MORPH_GRADIENT,kernel)

在这里插入图片描述

dst = cv2.morphologyEx(img,cv2.MORPH_TOPHAT,kernel)#礼帽  增强噪点
dst = cv2.morphologyEx(img,cv2.MORPH_BLACKHAT,kernel)#黑帽  获得比原来边缘更暗的边缘部分

import cv2#使用不同形状的核
img = cv2.imread("C:\\AppData\\image\\001.jpg",-1)
kernel1 = np.ones((5,5),np.uint8)
kernel2 = cv2.getStructuringElement(cv2.MORPH_RECT,(59,59))#矩形
kernel3 = cv2.getStructuringElement(cv2.MORPH_CROSS,(59,59))#十字
kernel4 = cv2.getStructuringElement(cv2.MORPH_ELLIPSE,(59,59))#椭圆
dst = cv2.dilate(img,kernel1)#
dst1 = cv2.dilate(img,kernel2)#
dst2 = cv2.dilate(img,kernel3)#
dst3 = cv2.dilate(img,kernel4)#
cv2.imshow("img",img)
cv2.imshow("dst",dst)
cv2.imshow("dst1",dst1)
cv2.imshow("dst2",dst2)
cv2.imshow("dst3",dst3)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

图像梯度

import cv2#
img = cv2.imread("C:\\AppData\\image\\002.jpg",0)
Sobelx = cv2.Sobel(img,cv2.CV_64F,1,0)
Sobelx1 = cv2.convertScaleAbs(Sobelx)
cv2.imshow("img",img)
cv2.imshow("Sobelx",Sobelx)
cv2.imshow("Sobelx1",Sobelx1)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2#
img = cv2.imread("C:\\AppData\\image\\002.jpg",0)
Sobelx = cv2.Sobel(img,cv2.CV_64F,1,0)
Sobelx1 = cv2.convertScaleAbs(Sobelx)
Sobely = cv2.Sobel(img,cv2.CV_64F,0,1)
Sobely1 = cv2.convertScaleAbs(Sobely)
Sobelxy = cv2.addWeighted(Sobelx1,0.5,Sobely1,0.5,0)
cv2.imshow("img",img)
cv2.imshow("Sobelx",Sobelx)
cv2.imshow("Sobely",Sobely)
cv2.imshow("Sobelx1",Sobelx1)
cv2.imshow("Sobely1",Sobely1)
cv2.imshow("Sobelxy",Sobelxy)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2#
img = cv2.imread("C:\\AppData\\image\\002.jpg",0)
Sobelx = cv2.Scharr(img,cv2.CV_64F,1,0)
Sobelx1 = cv2.convertScaleAbs(Sobelx)
Sobely = cv2.Scharr(img,cv2.CV_64F,0,1)
Sobely1 = cv2.convertScaleAbs(Sobely)
Sobelxy = cv2.addWeighted(Sobelx1,1,Sobely1,1,0)
cv2.imshow("img",img)
cv2.imshow("Sobelx",Sobelx)
cv2.imshow("Sobely",Sobely)
cv2.imshow("Sobelx1",Sobelx1)
cv2.imshow("Sobely1",Sobely1)
cv2.imshow("Sobelxy",Sobelxy)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2#
img = cv2.imread("C:\\AppData\\image\\002.jpg",0)
Sobelx = cv2.Scharr(img,cv2.CV_64F,1,0)
Sobelx1 = cv2.convertScaleAbs(Sobelx)
Sobely = cv2.Scharr(img,cv2.CV_64F,0,1)
Sobely1 = cv2.convertScaleAbs(Sobely)
Sobelxy = cv2.addWeighted(Sobelx1,1,Sobely1,1,0)
kernel = np.ones((3,3),np.uint8)
dst = cv2.erode(Sobelxy,kernel,iterations = 1)
cv2.imshow("img",img)
cv2.imshow("Sobelx",Sobelx)
cv2.imshow("Sobely",Sobely)
cv2.imshow("Sobelx1",Sobelx1)
cv2.imshow("Sobely1",Sobely1)
cv2.imshow("Sobelxy",Sobelxy)
cv2.imshow("dst",dst)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2#拉普拉斯
import numpy as np
img = cv2.imread("C:\\AppData\\image\\002.jpg",0)
Laplacian = cv2.Laplacian(img,cv2.CV_64F)
Laplacian = cv2.convertScaleAbs(Laplacian)
cv2.imshow("Laplacian",Laplacian)
cv2.waitKey()
cv2.destroyAllWindows()

dya5

Canny边缘检测

1.去噪 2.梯度和方向3.取大4.过滤

img = cv2.imread("C:\\AppData\\image\\002.jpg",0)
r1 = cv2.Canny(img,128,200)
r2 = cv2.Canny(img,32,128)
cv2.imshow("img",img)
cv2.imshow("r1",r1)
cv2.imshow("r2",r2)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

img = cv2.imread("C:\\AppData\\image\\002.jpg",0)#高斯金字塔
up = cv2.pyrUp(img)
down = cv2.pyrDown(up)
diff = img - down
img1 = down + diff#拉普拉斯   L0 = G0 - cv2.pyrUP(G)
xo = img1 - img
cv2.imshow("img",img)
cv2.imshow("up",up)
cv2.imshow("down",down)
cv2.imshow("diff",diff)
cv2.imshow("img1",img1)
cv2.imshow("xxo",xo)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

图像轮廓

img = cv2.imread("C:\\AppData\\image\\004.jpg",-1)#
gray0 = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY,1)#色彩空间转化
ret,binary = cv2.threshold(gray0,127,255,cv2.THRESH_BINARY_INV)#阈值处理
kernel = np.ones((5,5),np.uint8)#做核
dst = cv2.morphologyEx(binary,cv2.MORPH_OPEN,kernel)#开运算先腐蚀再膨胀
contours,hierarchy = cv2.findContours(dst,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE) #ＣＶ４．４返回值只有两个轮廓和关系
cv2.drawContours(img,contours,-1,(0,0,255),5)#画图
print(len(contours))#轮廓数
cv2.imshow("gray",gray0)
cv2.imshow("binary",dst)
cv2.imshow("img",img)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2
import numpy as np
img = cv2.imread("C:\\AppData\\image\\005.jpg",-1)#
gray0 = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY,1)#色彩空间转化
ret,binary = cv2.threshold(gray0,200,255,cv2.THRESH_BINARY_INV)#阈值处理
kernel = np.ones((5,5),np.uint8)#做核
dst = cv2.morphologyEx(binary,cv2.MORPH_OPEN,kernel)#开运算先腐蚀再膨胀
contours,hierarchy = cv2.findContours(dst,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE) #ＣＶ４．４返回值只有两个轮廓和关系
cv2.drawContours(img,contours,-1,(0,0,255),2)#画图
n = len(contours)#轮廓数
contoursimg = []
length = []
for i in range(n):
    temp = np.zeros(img.shape,np.uint8)
    contoursimg.append(temp)
    cv2.drawContours(contoursimg[i],contours,i,(255,0,255),2)
    cv2.imshow("contoursimg"+str(i),contoursimg[i])
    #print("contoursimg面积1"+str(i)+"   " , cv2.moments(contours[i])['m00'])#面积1
    #print("contoursimg面积2"+str(i)+"   " , cv2.contourArea(contours[i]))#面积2
    print("contoursimg长度"+str(i)+"   " , cv2.arcLength(contours[i],1))#长度
    length.append(cv2.arcLength(contours[i],1))

allle = np.average(length)
print(allle)
cv2.imshow("gray",gray0)
cv2.imshow("binary",dst)
cv2.imshow("img",img)
cv2.waitKey()
cv2.destroyAllWindows()

#显示
contoursimg0    808.0
contoursimg1    796.0
contoursimg2    1695.0
contoursimg3    1692.0
contoursimg4    6389.0

contoursimg长度0    108.76955187320709
contoursimg长度1    107.94112479686737
contoursimg长度2    179.5979790687561
contoursimg长度3    179.59797883033752
contoursimg长度4    544.8528124094009
224.1518893957138

在这里插入图片描述

形状匹配

import cv2
import numpy as np
img1 = cv2.imread("C:\\AppData\\image\\002.jpg",1)
img2 = cv2.imread("C:\\AppData\\image\\005.jpg",1)
gray1 = cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)#色彩空间转化
gray2 = cv2.cvtColor(img2,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary1 = cv2.threshold(gray1,127,255,cv2.THRESH_BINARY)
ret,binary2 = cv2.threshold(gray2,127,255,cv2.THRESH_BINARY)
contours1,hierarchy = cv2.findContours(binary1,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
contours2,hierarchy = cv2.findContours(binary2,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
#print(len(contours1))11
#print(len(contours2))4
ret1 = cv2.matchShapes(contours1[0],contours1[1],1,0.0)###结果越小越相似
print(ret1)
cv2.imshow("gray0",gray0)
cv2.waitKey()
cv2.destroyAllWindows()

轮廓拟合

import cv2#矩形
import numpy as np
img1 = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray1 = cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary1 = cv2.threshold(gray1,127,255,cv2.THRESH_BINARY_INV)
contours1,hierarchy = cv2.findContours(binary1,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
x,y,w,h = cv2.boundingRect(contours1[0])
brcnt = np.array([[[x,y]],[[x+w,y]],[[x+w,y+h]],[[x,y+h]]])
cv2.drawContours(img1,[brcnt],-1,(0,255,255),2)
#cv2.rectangle(img1,(x,y),(x+w,y+h),(0,0,255),2)
cv2.imshow("img1",img1)
print(len(contours1))
cv2.waitKey()
cv2.destroyAllWindows()


import cv2#最小矩形
import numpy as np
img1 = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray1 = cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary1 = cv2.threshold(gray1,127,255,cv2.THRESH_BINARY_INV)
contours1,hierarchy = cv2.findContours(binary1,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
rect = cv2.minAreaRect(contours1[0])#
points = cv2.boxPoints(rect)#转化为drawContours可用的格式
points = np.int0(points)#取整
x,y,w,h = cv2.boundingRect(contours1[0])
brcnt = np.array([[[x,y]],[[x+w,y]],[[x+w,y+h]],[[x,y+h]]])
cv2.drawContours(img1,[points],0,(0,255,255),2)
#cv2.rectangle(img1,(x,y),(x+w,y+h),(0,0,255),2)
cv2.imshow("img1",img1)
print(len(contours1))
cv2.waitKey()
cv2.destroyAllWindows()

import cv2#圆
import numpy as np
img1 = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray1 = cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary1 = cv2.threshold(gray1,127,255,cv2.THRESH_BINARY_INV)
contours1,hierarchy = cv2.findContours(binary1,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
(x,y),radius = cv2.minEnclosingCircle(contours1[0])
center = (int(x),int(y))
radius = int(radius)
cv2.circle(img1,center,radius,(0,0,255),2)
cv2.imshow("img1",img1)
print(len(contours1))
cv2.waitKey()
cv2.destroyAllWindows()


ellipse = cv2.fitEllipse(contours1[0])#椭圆
cv2.ellipse(img1,ellipse,(0,255,0),2)

import cv2#画线
import numpy as np
img1 = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray1 = cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary1 = cv2.threshold(gray1,127,255,cv2.THRESH_BINARY_INV)
contours1,hierarchy = cv2.findContours(binary1,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
rows,cols = img1.shape[:2]
[vx,vy,x,y] = cv2.fitLine(contours1[0],cv2.DIST_L2,0,0.01,0.01)
lefty = int((-x*vy/vx)+y)
righty = int(((cols-x)*vy/vx)+y)
cv2.line(img1,(cols-1,righty),(0,lefty),(0,255,255),2)
cv2.imshow("img",img1)
print(len(contours1))
cv2.waitKey()
cv2.destroyAllWindows()

area,trgl = cv2.minEnclosingTriangle(contours1[0])#最小外包三角形
for i in range(0,3):
    cv2.line(img1,tuple(trgl[i][0]),tuple(trgl[(i+1)%3][0]),(0,0,255),2)
cv2.imshow("img",img1)

在这里插入图片描述
在这里插入图片描述
在这里插入图片描述
在这里插入图片描述
在这里插入图片描述

在这里插入图片描述

import cv2#逼近多边形
import numpy as np
img1 = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray1 = cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary1 = cv2.threshold(gray1,127,255,cv2.THRESH_BINARY_INV)
contours1,hierarchy = cv2.findContours(binary1,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
adp = img1.copy()
epsilon = 0.1*cv2.arcLength(contours1[0],True)
approx = cv2.approxPolyDP(contours1[0],epsilon,True)
cv2.drawContours(adp,[approx],0,(0,0,225),2)
cv2.imshow("0.1",adp)

adp = img1.copy()
epsilon = 0.09*cv2.arcLength(contours1[0],True)
approx = cv2.approxPolyDP(contours1[0],epsilon,True)
cv2.drawContours(adp,[approx],0,(0,0,225),2)
cv2.imshow("0.09",adp)

adp = img1.copy()
epsilon = 0.02*cv2.arcLength(contours1[0],True)
approx = cv2.approxPolyDP(contours1[0],epsilon,True)
cv2.drawContours(adp,[approx],0,(0,0,225),2)
cv2.imshow("0.02",adp)

adp = img1.copy()
epsilon = 0.01*cv2.arcLength(contours1[0],True)
approx = cv2.approxPolyDP(contours1[0],epsilon,True)
cv2.drawContours(adp,[approx],0,(0,0,225),2)
cv2.imshow("0.01",adp)
#cv2.imshow("img",img1)
print(len(contours1))
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述
在这里插入图片描述

import cv2#凸包
import numpy as np
img1 = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray1 = cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary1 = cv2.threshold(gray1,127,255,cv2.THRESH_BINARY_INV)
contours1,hierarchy = cv2.findContours(binary1,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
hul1 = cv2.convexHull(contours1[0])
cv2.polylines(img1,[hul1],True,(0,0,200),2)
cv2.imshow("img",img1)

cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2#凸缺陷最低点
import numpy as np
img1 = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray1 = cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary1 = cv2.threshold(gray1,127,255,cv2.THRESH_BINARY_INV)
contours1,hierarchy = cv2.findContours(binary1,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
hul1 = cv2.convexHull(contours1[0],returnPoints = False)
defects = cv2.convexityDefects(contours1[0],hul1)
for i in range(defects.shape[0]):#线段条数
    s,e,f,d = defects[i,0]#开始、结束点的索引，距离线段最远，最近的点
    start = tuple(contours1[0][s][0])#线段起点位置
    end = tuple(contours1[0][e][0])#线段终点位置
    far = tuple(contours1[0][f][0])#最远点的位置
    cv2.line(img1,start,end,(0,0,255),2)#画线段
    cv2.circle(img1,far,5,[255,0,0],-1)#画圆点
#cv2.polylines(img1,[hul1],True,(0,0,200),2)
cv2.imshow("img",img1)

cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2#几何学测试
import numpy as np
img = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary = cv2.threshold(gray,127,255,cv2.THRESH_BINARY_INV)
contours,hierarchy = cv2.findContours(binary,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
image = img.copy()
hull = cv2.convexHull(contours[0])#求外围的点
cv2.polylines(image,[hull],True,(0,255,255),2)
print("isn't a ao   ",cv2.isContourConvex(hull))#

image1 = img.copy()#逼近多边形
epsilon = 0.01*cv2.arcLength(contours[0],True)
approx = cv2.approxPolyDP(contours[0],epsilon,True)
cv2.drawContours(image1,[approx],0,(0,0,225),2)
cv2.imshow("0.002",image1)

cv2.waitKey()
cv2.destroyAllWindows()

import cv2#几何学测试
import numpy as np
img = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary = cv2.threshold(gray,127,255,cv2.THRESH_BINARY_INV)
contours,hierarchy = cv2.findContours(binary,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)

hull = cv2.convexHull(contours[0])
image = cv2.cvtColor(gray,cv2.COLOR_GRAY2BGR)
cv2.polylines(image,[hull],True,(0,255,0),2)#画hull
distA = cv2.pointPolygonTest(hull,(300,150),True)#求点的参数
font = cv2.FONT_HERSHEY_SIMPLEX#字体选择
cv2.putText(image,'A',(300,150),font,1,(0,0,255),2)#打印文字
print("dist= ",distA)
cv2.imshow("img",image)
cv2.waitKey()
cv2.destroyAllWindows()


import cv2#矩形轮廓宽高比
import numpy as np
img = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary = cv2.threshold(gray,127,255,cv2.THRESH_BINARY_INV)
contours,hierarchy = cv2.findContours(binary,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
x,y,w,h = cv2.boundingRect(contours[0])
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
aspectRatio = float(w)/h
print("   ",aspectRatio)
cv2.imshow("img",img)
cv2.waitKey()
cv2.destroyAllWindows()


import cv2#轮廓面积比矩形面积
import numpy as np
img = cv2.imread("C:\\AppData\\image\\006.jpg",1)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)#色彩空间转化
ret,binary = cv2.threshold(gray,127,255,cv2.THRESH_BINARY_INV)
contours,hierarchy = cv2.findContours(binary,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
x,y,w,h = cv2.boundingRect(contours[0])
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
cv2.drawContours(img,contours[0],-1,(0,0,255),2)
rectArea = w*h
outArea = cv2.contourArea(contours[0])
extend = float(outArea)/rectArea
aspectRatio = float(w)/h
print("   ",extend)
cv2.imshow("img",img)
cv2.waitKey()
cv2.destroyAllWindows()


hull = cv2.convexHull(contours[0])
hullArea = cv2.contourArea(hull)
cv2.polylines(img,[hull],True,(255,0,0),2)

look
在这里插入图片描述

直方图

import cv2#直方图
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread("C:\\AppData\\image\\120.jpg",0)
img1 = cv2.imread("C:\\AppData\\image\\120.jpg",1)
img2 = cv2.cvtColor(img1,cv2.COLOR_BGR2RGB)
equ = cv2.equalizeHist(img)

#cv2.imshow("img",img)
#cv2.imshow("equ",equ)

plt.figure("img")
plt.subplot(121),plt.hist(img.ravel(),256)
plt.subplot(122),plt.hist(equ.ravel(),256)
plt.figure("img1")
plt.imshow(img2)

cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

傅里叶变换

import cv2#频域
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread("C:\\AppData\\image\\100.jpg",0)
f = np.fft.fft2(img)#二维傅里叶转化
fshift = np.fft.fftshift(f)#0频置中

ishift = np.fft.ifftshift(fshift)#逆运算
iimg = np.fft.ifft2(ishift)#逆运算
iimg = np.abs(iimg)#有复数
magnitude_spectrum = 20*np.log(np.abs(fshift))#
plt.subplot(121)#
plt.imshow(img,cmap = 'gray')
plt.title("ori")
plt.axis('off')
plt.subplot(122)
plt.imshow(magnitude_spectrum,cmap = 'gray')
plt.title("result")
plt.axis('off')
plt.show()
plt.figure("img1")
plt.imshow(iimg,cmap = 'gray')
#cv2.imshow("pu",magnitude_spectrum)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2#傅里叶高通滤波
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread("C:\\AppData\\image\\100.jpg",0)
f = np.fft.fft2(img)
fshift = np.fft.fftshift(f)

rows,cols = img.shape
row,col = int(rows/2),int(cols/2)
fshift[row-50:row+50,col-50:col+50] = 0 #使低频率的值为零而显示黑色

ishift = np.fft.ifftshift(fshift)
iimg = np.fft.ifft2(ishift)
iimg = np.abs(iimg)
magnitude_spectrum = 10*np.log(np.abs(fshift))
plt.subplot(121)
plt.imshow(img,cmap = 'gray')
plt.title("ori")
plt.axis('off')
plt.subplot(122)
plt.imshow(magnitude_spectrum,cmap = 'gray')
plt.title("result")
plt.axis('off')
plt.show()
plt.figure("img1")
plt.imshow(iimg,cmap = 'gray')
#cv2.imshow("pu",magnitude_spectrum)
img2 = np.abs(img-iimg)
ret,binary1 = cv2.threshold(img2,2,255,cv2.THRESH_BINARY)
#cv2.imshow("im01",binary1)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2#opencv实现傅里叶功能同上
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread("C:\\AppData\\image\\100.jpg",0)
dft = cv2.dft(np.float32(img),flags = cv2.DFT_COMPLEX_OUTPUT)#利用cv进行傅里叶
dftshift = np.fft.fftshift(dft)#用numpy将0频置中
rows,cols = img.shape
cow,col = int(rows/2),int(cols/2)
mask = np.zeros((rows,cols,2),np.uint8)
mask[row-30:row+30,col-30:col+30] = 1
fshift = dftshift*mask#将部分置0
ishift = np.fft.ifftshift(fshift)#逆中转
iimg = cv2.idft(ishift)
iimg = cv2.magnitude(iimg[:,:,0],iimg[:,:,1])# 逆转图像
plt.subplot(121),plt.imshow(img,cmap = 'gray'),plt.title('original'),plt.axis('off')
plt.subplot(122),plt.imshow(iimg,cmap = 'gray'),plt.title('inverse'),plt.axis('off')
plt.show()
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread("C:\\AppData\\image\\2.jpg",0)
template = cv2.imread("C:\\AppData\\image\\22.jpg",0)
th,tw = template.shape[::-1]
rv = cv2.matchTemplate(img,template,cv2.TM_SQDIFF)
minVal,maxVal,minLoc,maxLoc = cv2.minMaxLoc(rv)
topLeft = minLoc
print(topLeft)
bottomRight = (topLeft[0]+tw,topLeft[1]+th)
cv2.rectangle(img,topLeft,bottomRight,255,5)

plt.subplot(121),plt.imshow(img,cmap = 'gray'),plt.title('original'),plt.axis('off')
plt.subplot(122),plt.imshow(rv,cmap = 'gray'),plt.title('inverse'),plt.axis('off')
plt.show()
cv2.imshow("imh",rv)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread("C:\\AppData\\image\\2.jpg",0)
template = cv2.imread("C:\\AppData\\image\\22.jpg",0)
th,tw = template.shape[::-1]
rv = cv2.matchTemplate(img,template,cv2.TM_CCOEFF_NORMED)
threshold = 0.5
loc = np.where(rv>=threshold)
for i in zip(*loc[::-1]):
    cv2.rectangle(img,i,(i[0]+th,i[1]+tw),255,1)


cv2.imshow("imh",img)
cv2.waitKey()
cv2.destroyAllWindows()

import cv2
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread("C:\\AppData\\image\\007.jpg",1)
b,g,r = cv2.split(img)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ishow = r.copy()
img1 = np.zeros(r.shape,np.uint8)
ret,thresh = cv2.threshold(r,160,255,cv2.THRESH_BINARY)
kernel = np.ones((3,3),np.uint8)
opening = cv2.morphologyEx(thresh,cv2.MORPH_OPEN,kernel,iterations = 3)
dist_transform = cv2.distanceTransform(opening,cv2.DIST_L2,3)
rte,fore = cv2.threshold(dist_transform,0.3*dist_transform.max(),255,0)
mask = fore[:,:] >0
img1[mask] = 255
contours1,hierarchy = cv2.findContours(img1,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
print(len(contours1))
cv2.imshow("img",r)
cv2.imshow("dist_transform",dist_transform)
cv2.imshow("fore",fore)
cv2.waitKey()
cv2.destroyAllWindows()

在这里插入图片描述

import cv2#读取视频
import numpy as np
cap = cv2.VideoCapture(0)
while(cap.isOpened()):
    ret,frame = cap.read()
    frame = cv2.Canny(frame,90,220)
    cv2.imshow('frame',frame)
    c = cv2.waitKey(100)
    if c == 27:
        break
cap.release()
cv2.destroyAllWindows()

学习书籍 —《Opencv 轻松入门：面向python》

西木康
关注
  • 2
    点赞
  • 踩
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
动手学深度学习PyTorch版---lastDay_2
Courageux_J的博客
02-25 387
lastDay 数据增强； 1.数据增强 翻转和裁剪；变化颜色（亮度（brightness）、对比度（contrast）、饱和度（saturation）和色调（hue）） 2.模型微调
opencv_day06
qq_35966478的博客
10-14 228
#结合上面实现绕x轴和y轴翻转 import cv2 import numpy as np img=np.random.randint(0,256,size=[4,5],dtype=np.uint8) rows,cols=img.shape mapx=np.zeros(img.shape,np.float32) mapy=np.zeros(img.shape,np.float32) for i i...
MapX开发
郁闷阳光的专栏
05-29 753
我用MapInfo公司的MapX开发过几个项目。在项目的开发过程中，也接触了一些使用相同技术的公司和开发人员，感觉到他们的开发过程常常被一些问题所困扰，却得不到很好的解决。在这里，我把我在开发过程中积累的一些经验写出来，希望能起到抛砖引玉的作用。 二、开发经验 1、如何在MapX下读取属性值，这里介绍三种方法： 1）由Layer对象的KeyField属性来设立要读取属性值的字段名。接着，由F
(23)像素重映射
nuc_Sheryl的博客
07-17 474
/* *像素重映射 先想一下数学上面的映射的概念 简单点说就是把输入图像中各个像素按照一定的规则映射到另外一张图像的对应位置上去，形成一张新的图像。 API介绍cv::remap Remap( InputArray src,// 输入图像 没有要求 OutputArray dst,// 输出图像 ...
SICP_Python第二章:映射(子集问题,排列问题,N皇后问题)
pyb的博客
07-16 627
下面是自己实现的map方法。def simple_map(proc,items): result = [] for item in items: result.append(proc(item)) return result def scale_list(items,factor): return simple_map(lambda x:x*facto
OpenCV 4.8.0
12-17
OpenCV（开源计算机视觉库）是计算机视觉和机器学习领域广泛应用的一个强大工具，它提供了丰富的API，支持多种编程语言，包括C++、Python、Java等。OpenCV 4.8.0是该库的一个更新版本，它包含了最新的特性和优化，以...
opencv-4.10.0
最新发布
06-09
opencv-4.10.0内容： opencv-4.10.0.tar.gz opencv-4.10.0.zip opencv-4.10.0-android-sdk.zip opencv-4.10.0-ios-framework.zip opencv-4.10.0-windows.exe opencv-4.10.0-docs.zip
opencv-4.9.0
01-31
opencv-4.9.0内容： opencv-4.9.0-android-sdk.zip opencv-4.9.0-docs.zip opencv-4.9.0-ios-framework.zip opencv-4.9.0-windows.exe opencv-4.9.0.tar.gz opencv-4.9.0.zip
opencv4nodejs
10-16
opencv4nodejs 允许您在nodejs 中使用原生OpenCV 库。除了同步 API 之外，该包还提供异步 API，它允许您构建非阻塞和多线程计算机视觉任务。 opencv4nodejs 支持 OpenCV 3 和 OpenCV 4。 该项目的最终目标是提供与 ...
OpenCV4.5.5
03-31
OpenCV4.5.5编译好的动态库，可下载直接使用，省去自己编译的麻烦
《Python数据结构与算法》
人生苦短，我用Python
11-30 498
《Data Structures and Algorithms Using Python》 1章：ADT抽象数据类型，定义数据和其操作 什么是ADT: 抽象数据类型，学过数据结构的应该都知道。 How to select datastructures for ADT Dose the ...
Python库 - Albumentations 图片数据增强库
胭脂草的ABC博客
11-20 2974
Python库 - Albumentations 图片数据增强库 Python图像处理库 - Albumentations，可用于深度学习中网络训练时的图片数据增强. Github - Albumentations 帮助文档Document - albumentations Albumentations 图像数据增强库特点： 基于高度优化的 OpenCV 库实现图像快速数据增强. 针对不同图像任务，如分割，检测等，超级简单的 API 接口. 易于个性化定制. 易于添加到其它框架，比如 PyTorch
OpenCV图像掩模，外加加密解密
tangzhihui520的博客
09-29 219
import numpy as np import cv2 image = cv2.imread('C://Users//Administrator//Desktop//20190317151231154.jpg') #读图 cv2.imshow("Oringinal", image) #显示原图 print(image.shape[:2]) site = np.array([[[500,300],[250,300],[250,5],[500,5]]],dtype=np.int32) im = np..
Python处理图像 加、减、与非
zhuimengshaonian66的博客
08-13 3750
转：https://blog.csdn.net/jnulzl/article/details/47129887 一、函数简介 1、add—图像矩阵相加 函数原型：add(src1, src2, dst=None, mask=None, dtype=None) src1：图像矩阵1 src1：图像矩阵2 dst：默认选项 mask：默认选项 dtype：默认选项 2、subtrac...
图像处理基础操作二（边缘检测、轮廓检测、光流估计）
Asia-Lee
11-09 7536
一、边缘检测 边缘检测通常是在保留原有图像属性的情况下，对图像数据规模进行缩减，提取图像边缘轮廓的处理方式。边缘检测算法主要是基于图像强度的一阶和二阶导数，但导数通常对噪声很敏感，因此需要采用滤波器来过滤噪声，并调用图像增强或阈值化算法进行处理，最后再进行边缘检测。 1、Roberts算子 Roberts算子又称为交叉微分算法，它是基于交叉差分的梯度算法，通过局部差分计算检测边缘线条。常用来处理具有陡峭的低噪声图像，当图像边缘接近于正45度或负45度时，该算法处理效果更理想。其缺点是对边缘的定位不太准
零基础小白必看：教你在python画不同颜色的画布，简单好玩
python_miao的博客
10-13 1343
文章目录 摘要 numpy的ndarray数据结构的索引与赋值 创建空白画布 初始化白色的画布 初始化彩色的画布 利用cv2的内置方法merge与split 利用numpy内置的索引 综合实验-初始化背景 「❤️ 感谢大家」 摘要 在这篇文章中将给大家讲解如何分别用numpy的方法，与numpy与cv2结合的方法创建空白画布，创建白色画布，与创建彩色画布。在讲解过程中还会介绍cv2进行通道分割cv2.split与通道合并cv2.merge的两个函数的具体使用以及深究numpy的ndarray
画中世界
nameofcsdn的博客
07-18 1439
目录 一，画中世界 二，图片截取 三，红苹果 三，绿苹果 四，黄苹果 一，画中世界 安装包链接：https://pan.baidu.com/s/1lTj_kNw04D85t6SChLNwsw 提取码：ve9c 后面的关卡依次是获取红苹果、绿苹果、黄苹果 蓝苹果和紫苹果 二，图片截取 import cv2 for i in range(1,6,1): s = 'D:/img ('+str(i)+').jpg' image = cv2.imread(s, -..
python写诗
西木康的博客
06-08 4324
用简单的python语句随机出古诗思路诗句提取再将逐个诗句的每个词提取看看结果吧！结语 下面是记录本人编写的过程新手见谅啊！ 思路 首先去找些古诗，一万字多的，谢谢度娘，古诗他出。用正则将每句是提取与原来的文本分离，然后将诗句中的词提取出来，相同长度的词放在一起，最后随机调用，组成一首毫无逻辑的诗 诗句提取 先看看把诗句提取的过程 诗词的样例： 01. 《黄鹤楼》崔颢 昔人已乘黄鹤去，此地空余黄鹤楼。黄鹤一去不复返，白云千载空悠悠。晴川历历汉阳树，芳草萋萋鹦鹉洲。日暮乡关何处是烟波江上使人愁。 02. 《登
我的Autojs学习日记
西木康的博客
06-27 3570
autojs学习日记自述软件的准备工作 自述 最近，发现autojs是个好东西，于是乎，想自学试试，本人有C和python的基础。看了看他的代码和他们几乎一样。感觉不是很难。以下是本人的学习记录，大家可以参考。 软件的准备工作 1.下载VS code(free)，安装 2.准备一部安卓手机或者安卓模拟器（建议模拟器） 3.在安卓平台上安装auto.js 4.在VS中安装插件：如下 关于python 、C的插件是不需要下载的 5.操作步骤： 1）.查看—控制面板—运行（autojs:new project
OpenCV入门指南：学习OpenCV
"Learning OpenCV 是一本面向初学者的OpenCV学习指南，由Gary Bradski和Adrian Kaehler合著，旨在帮助读者掌握计算机视觉库OpenCV的基础知识和应用技巧。" OpenCV（开源计算机视觉库）是一个强大的跨平台库，用于...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值