[人工智能]opencv1

环境

装opencv

pip install opencv-python==3.4.1.15
pip install opencv-contrib-python==3.4.1.15 -i https://pypi.douban.com/simple/

图像基本操作

数据读取-图像

cv2.IMREAD_COLOR：彩色图像
cv2.IMREAD_GRAYSCALE：灰度图像

import cv2 #opencv读取的格式是BGR
import matplotlib.pyplot as plt
import numpy as np 
%matplotlib inline 

img=cv2.imread('cat.jpg')

#图像的显示,也可以创建多个窗口
cv2.imshow('image',img) 
# 等待时间，毫秒级，0表示任意键终止
cv2.waitKey(0) 
cv2.destroyAllWindows()
# 数值类型
print(img.shape)

灰色读取与图像保存

import cv2 #opencv读取的格式是BGR
import matplotlib.pyplot as plt
import numpy as np

img=cv2.imread('../image/2009.png',cv2.IMREAD_GRAYSCALE)
#图像的显示,也可以创建多个窗口
cv2.imshow('image',img)
# 等待时间，毫秒级，0表示任意键终止
cv2.waitKey(0)
cv2.destroyAllWindows()
print(img.shape)
#保存
cv2.imwrite('mycat.png',img)

局部截取

import cv2 #opencv读取的格式是BGR
import matplotlib.pyplot as plt
import numpy as np

img=cv2.imread('../image/2009.png')
cat=img[0:50,0:200]
cv2.imshow('cat',cat)
# 等待时间，毫秒级，0表示任意键终止
cv2.waitKey(0)
cv2.destroyAllWindows()
print(img.shape)

颜色通道提取

边界填充

top_size,bottom_size,left_size,right_size = (50,50,50,50)

replicate = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, borderType=cv2.BORDER_REPLICATE)
reflect = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size,cv2.BORDER_REFLECT)
reflect101 = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, cv2.BORDER_REFLECT_101)
wrap = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, cv2.BORDER_WRAP)
constant = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size,cv2.BORDER_CONSTANT, value=0)

import matplotlib.pyplot as plt
plt.subplot(231), plt.imshow(img, 'gray'), plt.title('ORIGINAL')
plt.subplot(232), plt.imshow(replicate, 'gray'), plt.title('REPLICATE')
plt.subplot(233), plt.imshow(reflect, 'gray'), plt.title('REFLECT')
plt.subplot(234), plt.imshow(reflect101, 'gray'), plt.title('REFLECT_101')
plt.subplot(235), plt.imshow(wrap, 'gray'), plt.title('WRAP')
plt.subplot(236), plt.imshow(constant, 'gray'), plt.title('CONSTANT')

plt.show()

数值计算

图像融合

数据读取-视频

cv2.VideoCapture可以捕获摄像头，用数字来控制不同的设备，例如0,1。如果是视频文件，直接指定好路径即可

import cv2 #opencv读取的格式是BGR
import matplotlib.pyplot as plt
import numpy as np

vc = cv2.VideoCapture('../image/test.mp4')

# 检查是否打开正确
if vc.isOpened():
# open是否可读，frame帧
    open, frame = vc.read()
else:
    open = False

while open:
    ret, frame = vc.read()
    if frame is None:
        break
    if ret == True:
        # 灰色读取
        gray = cv2.cvtColor(frame,  cv2.COLOR_BGR2GRAY)
        cv2.imshow('result', gray)
        # oxff esc退出键
        if cv2.waitKey(100) & 0xFF == 27:
            break
vc.release()
cv2.destroyAllWindows()

阈值（突出）

# 前面阈值后面图像
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
cv2.THRESH_BINARY 超过阈值部分取maxval（最大值），否则取0
cv2.THRESH_BINARY_INV THRESH_BINARY的反转
cv2.THRESH_TRUNC 大于阈值部分设为阈值，否则不变
cv2.THRESH_TOZERO 大于阈值部分不改变，否则设为0
cv2.THRESH_TOZERO_INV THRESH_TOZERO的反转

ret, thresh1 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_BINARY)
ret, thresh2 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_BINARY_INV)
ret, thresh3 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TRUNC)
ret, thresh4 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TOZERO)
ret, thresh5 = cv2.threshold(img_gray, 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()

图像平滑处理（与后面两者功能去噪点）

# 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，normalize false最后结果是3*3的总值
box = cv2.boxFilter(img,-1,(3,3), normalize=True)  
cv2.imshow('box', box)
cv2.waitKey(0)
cv2.destroyAllWindows()

高斯滤波

# 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)  

cv2.imshow('aussian', aussian)
cv2.waitKey(0)
cv2.destroyAllWindows()

中值滤波

# 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()

结果小结

import numpy as np 
# 展示所有的
res = np.hstack((blur,aussian,median))
#print (res)
cv2.imshow('median vs average', res)
cv2.waitKey(0)
cv2.destroyAllWindows()

腐蚀操作、 膨胀操作

kernel = np.ones((3,3),np.uint8) 
# kernel每次腐蚀的框大小，iterations迭代次数
erosion = cv2.erode(img,kernel,iterations = 1)

cv2.imshow('erosion', erosion)
cv2.waitKey(0)
cv2.destroyAllWindows()


kernel = np.ones((3,3),np.uint8) 
dige_erosion = cv2.erode(img,kernel,iterations = 1)

cv2.imshow('erosion', erosion)
cv2.waitKey(0)
cv2.destroyAllWindows()

开运算与闭运算

# 开：先腐蚀，再膨胀
img = cv2.imread('dige.png')
kernel = np.ones((5,5),np.uint8) 
opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)
cv2.imshow('opening', opening)
cv2.waitKey(0)
cv2.destroyAllWindows()


# 闭：先膨胀，再腐蚀
img = cv2.imread('dige.png')
kernel = np.ones((5,5),np.uint8) 
closing = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel)
cv2.imshow('closing', closing)
cv2.waitKey(0)
cv2.destroyAllWindows()

梯度运算

# 梯度=膨胀-腐蚀
pie = cv2.imread('pie.png')
kernel = np.ones((7,7),np.uint8) 
dilate = cv2.dilate(pie,kernel,iterations = 5)
erosion = cv2.erode(pie,kernel,iterations = 5)
res = np.hstack((dilate,erosion))
cv2.imshow('res', res)
cv2.waitKey(0)
cv2.destroyAllWindows()

gradient = cv2.morphologyEx(pie, cv2.MORPH_GRADIENT, kernel)
cv2.imshow('gradient', gradient)
cv2.waitKey(0)
cv2.destroyAllWindows()

礼帽与黑帽

礼帽 = 原始输入-开运算结果（刺头）
黑帽 = 闭运算-原始输入（轮廓）

kernel = np.ones((5,5),np.uint8) 
#礼帽
img = cv2.imread('dige.png')
tophat = cv2.morphologyEx(img, cv2.MORPH_TOPHAT, kernel)
cv2.imshow('tophat', tophat)
cv2.waitKey(0)
cv2.destroyAllWindows()

#黑帽
img = cv2.imread('dige.png')
blackhat  = cv2.morphologyEx(img,cv2.MORPH_BLACKHAT, kernel)
cv2.imshow('blackhat ', blackhat )
cv2.waitKey(0)
cv2.destroyAllWindows()

图像梯度-Sobel算子（轮廓）

dst = cv2.Sobel(src, ddepth, dx, dy, ksize)

ddepth:图像的深度，一般买默认-1
dx和dy分别表示水平和竖直方向
ksize是Sobel算子的大小

x方向

def cv_show(img,name):
    cv2.imshow(name,img)
    cv2.waitKey()
    cv2.destroyAllWindows()

# （参数2）统一负数操作
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3)
cv_show(sobelx,'sobelx')

# 白到黑是正数，黑到白就是负数了，所有的负数会被截断成0，所以要取绝对值
sobelx = cv2.convertScaleAbs(sobelx)
cv_show(sobelx,'sobelx')

y方向

sobely = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=3)
sobely = cv2.convertScaleAbs(sobely)  
cv_show(sobely,'sobely')

分别计算x和y，再求和

sobelxy = cv2.addWeighted(sobelx,0.5,sobely,0.5,0)
cv_show(sobelxy,'sobelxy')

不建议直接计算

sobelxy=cv2.Sobel(img,cv2.CV_64F,1,1,ksize=3)
sobelxy = cv2.convertScaleAbs(sobelxy) 
cv_show(sobelxy,'sobelxy')

图像梯度-Scharr算子、图像梯度-laplacian算子（噪音点明显）

def cv_show(img,name):
    cv2.imshow(name,img)
    cv2.waitKey()
    cv2.destroyAllWindows()
import numpy as np
#不同算子的差异
img = cv2.imread('lena.jpg',cv2.IMREAD_GRAYSCALE)
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3)
sobely = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=3)
sobelx = cv2.convertScaleAbs(sobelx)   
sobely = cv2.convertScaleAbs(sobely)  
sobelxy =  cv2.addWeighted(sobelx,0.5,sobely,0.5,0)  

scharrx = cv2.Scharr(img,cv2.CV_64F,1,0)
scharry = cv2.Scharr(img,cv2.CV_64F,0,1)
scharrx = cv2.convertScaleAbs(scharrx)   
scharry = cv2.convertScaleAbs(scharry)  
scharrxy =  cv2.addWeighted(scharrx,0.5,scharry,0.5,0) 

laplacian = cv2.Laplacian(img,cv2.CV_64F)
laplacian = cv2.convertScaleAbs(laplacian)   

res = np.hstack((sobelxy,scharrxy,laplacian))
cv_show(res,'res')

Canny边缘检测

1. 使用高斯滤波器，以平滑图像，滤除噪声。
2. 计算图像中每个像素点的梯度强度和方向。
3. 应用非极大值（Non-Maximum Suppression）抑制，以消除边缘检测带来的杂散响应。（非极大值去除）
4. 应用双阈值（Double-Threshold）检测来确定真实的和潜在的边缘。
5. 通过抑制孤立的弱边缘最终完成边缘检测。
   

img=cv2.imread("lena.jpg",cv2.IMREAD_GRAYSCALE)
# 双阈值最大最小
v1=cv2.Canny(img,80,150)
v2=cv2.Canny(img,50,100)

res = np.hstack((v1,v2))
cv_show(res,'res')

图像金字塔

高斯金字塔

def cv_show(img,name):
    cv2.imshow(name,img)
    cv2.waitKey()
    cv2.destroyAllWindows()

拉普拉斯金字塔

down=cv2.pyrDown(img)
down_up=cv2.pyrUp(down)
l_1=img-down_up
cv_show(l_1,'l_1')

图像轮廓

cv2.findContours(img,mode,method)
mode:轮廓检索模式
RETR_EXTERNAL ：只检索最外面的轮廓；
RETR_LIST：检索所有的轮廓，并将其保存到一条链表当中；
RETR_CCOMP：检索所有的轮廓，并将他们组织为两层：顶层是各部分的外部边界，第二层是空洞的边界;
RETR_TREE：检索所有的轮廓，并重构嵌套轮廓的整个层次;（常用）

method:轮廓逼近方法
CHAIN_APPROX_NONE：以Freeman链码的方式输出轮廓，所有其他方法输出多边形（顶点的序列）。
CHAIN_APPROX_SIMPLE:压缩水平的、垂直的和斜的部分，也就是，函数只保留他们的终点部分。（精简）

为了更高的准确率，使用二值图像。

img = cv2.imread('contours.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 二值处理
ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
cv_show(thresh,'thresh')

# binary二值处理 contours轮廓点 hierarchy结果信息
binary, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)

#传入绘制图像，轮廓，轮廓索引，颜色模式，线条厚度
# 注意需要copy,要不原图会变。。。
draw_img = img.copy()
# -1第几个轮廓，-1全部；(0, 0, 255)轮廓线条颜色； 2线条宽度
res = cv2.drawContours(draw_img, contours, -1, (0, 0, 255), 2)
cv_show(res,'res')

轮廓特征

轮廓近似

img = cv2.imread('contours2.png')

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
binary, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cnt = contours[0]
draw_img = img.copy()
res = cv2.drawContours(draw_img, [cnt], -1, (0, 0, 255), 2)
cv_show(res,'res')


epsilon = 0.15*cv2.arcLength(cnt,True) 
# cnt轮廓，epsilon阈值长度
approx = cv2.approxPolyDP(cnt,epsilon,True)
draw_img = img.copy()
res = cv2.drawContours(draw_img, [approx], -1, (0, 0, 255), 2)
cv_show(res,'res')

边界矩形

img = cv2.imread('contours.png')

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
binary, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cnt = contours[0]

x,y,w,h = cv2.boundingRect(cnt)
# 线条颜色与宽度
img = cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2)
cv_show(img,'img')


area = cv2.contourArea(cnt)
x, y, w, h = cv2.boundingRect(cnt)
rect_area = w * h
extent = float(area) / rect_area
print ('轮廓面积与边界矩形比',extent)

外接圆

(x,y),radius = cv2.minEnclosingCircle(cnt) 
center = (int(x),int(y)) 
radius = int(radius) 
img = cv2.circle(img,center,radius,(0,255,0),2)
cv_show(img,'img')