OpenCV 入门

平凡シンプル2024-12-28 11:11

OpenCV_Python 入门

创建/显示窗口

方法 说明 参数 返回
namedWindow 创建一个窗口 窗口名称,WINDOW_NORMAL(窗口属性)
resizeWindow 设置窗口大小 窗口名称,宽,高
imshow 显示窗口 窗口名称,要显示的图像
destroyAllWindows 关闭所有窗口
waitKey 延时监听键盘按下 0无限 / 单位毫秒 键盘按下键的ASCII码
python 复制代码 
import cv2

cv2.namedWindow("img",cv2.WINDOW_NORMAL)
cv2.resizeWindow("img",800,600)

while True:
    cv2.imshow("img",0)
    key = cv2.waitKey(0)
    if key & 0xFF == ord('q'):
        break
cv2.destroyAllWindows()

显示图片

方法 说明 参数 返回
imread 读取图片 路径,IMREAD_GRAYSCALE(灰)/IMREAD_COLOR(彩)/其它 读取到的图片资源
python 复制代码 
import cv2

while True:
    # cv2.imshow("img",cv2.imread("../1.jpg",cv2.IMREAD_COLOR))
    cv2.imshow("img",cv2.imread("../1.jpg",cv2.IMREAD_GRAYSCALE))

    key = cv2.waitKey(0)
    if key & 0xFF == ord('q'):
        break
cv2.destroyAllWindows()

保存图片

方法 说明 参数 返回
imwrite 保存图片 保存的文件名称,图片资源
python 复制代码 
import  cv2

img = cv2.imread("../1.jpg",cv2.IMREAD_COLOR)

while True:
    cv2.imshow("img",img)
    key = cv2.waitKey(0)
    if key & 0xFF == ord('q'):
        break
    elif key & 0xFF == ord('s'):
        cv2.imwrite("11.png",img)
cv2.destroyAllWindows()

视频采集

方法 说明 参数 返回
VideoCapture 摄像机 0(开启本机摄像头)
VideoCapture.read 获取视频帧 ret(读取到帧为true),frame(视频帧)
VideoCapture.release 释放资源
python 复制代码 
import cv2

cv2.namedWindow("frame",cv2.WINDOW_NORMAL)
cv2.resizeWindow("frame",800,600)
cap = cv2.VideoCapture(0)
while True:
    ret,frame = cap.read()
    cv2.imshow('frame',frame)
    key = cv2.waitKey(1)
    if key & 0xFF == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()

读取视频文件

方法 说明 参数 返回
VideoCapture 摄像机 本机视频文件路径
python 复制代码 
import cv2

cv2.namedWindow("frame",cv2.WINDOW_NORMAL)
cv2.resizeWindow("frame",800,600)
cap = cv2.VideoCapture("../2.mp4")
while True:
    ret,frame = cap.read()
    cv2.imshow('frame',frame)
    key = cv2.waitKey(1)
    if key & 0xFF == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()

视频录制

方法 说明 参数 返回
VideoWriter_fourcc 编码器 *MJPG / 其它
VideoWriter 视频输出 文件名称,编码器,帧数,(宽,高)
VideoWriter.write 视频写入 帧
VideoWriter.release 释放资源
python 复制代码 
import cv2
fourcc = cv2.VideoWriter_fourcc(*'MJPG')
vw = cv2.VideoWriter('output.avi', fourcc, 20.0, (640, 480))
cv2.namedWindow("frame",cv2.WINDOW_NORMAL)
cv2.resizeWindow("frame",800,600)
cap = cv2.VideoCapture(0)
while True:
    ret,frame = cap.read()
    cv2.imshow('frame',frame)
    vw.write(frame)
    key = cv2.waitKey(1)
    if key & 0xFF == ord('q'):
        break
cap.release()
vw.release()
cv2.destroyAllWindows()
python 复制代码 
import cv2
fourcc = cv2.VideoWriter_fourcc(*'MJPG')
vw = cv2.VideoWriter('output.avi', fourcc, 20.0, (640, 480))

cv2.namedWindow("frame",cv2.WINDOW_NORMAL)
cv2.resizeWindow("frame",640,480)
cap = cv2.VideoCapture(0)
while cap.isOpened(): # 判断摄像头是否为打开状态
    ret,frame = cap.read()
    if not ret: break # 判断帧是否打开
    cv2.imshow('frame',frame)
    # 窗口撑开后重新设置
    cv2.resizeWindow("frame", 640, 480)
    vw.write(frame)
    key = cv2.waitKey(1)
    if key & 0xFF == ord('q'):
        break
cap.release()
vw.release()
cv2.destroyAllWindows()

鼠标控制

方法 说明 参数 返回
setMouseCallback 监听鼠标 窗口名称,监听事件,额外参数
python 复制代码 
import cv2

# 鼠标操作    x    y    组合操作    额外参数 
def mouse_callback(event, x, y, flags, param):
    print(event, x, y, flags, param)
cv2.namedWindow("img",cv2.WINDOW_NORMAL)
cv2.resizeWindow("img",800,600)
cv2.setMouseCallback("img",mouse_callback,"123")
img = cv2.imread("../1.jpg")
while True:
    cv2.imshow("img",img)
    key = cv2.waitKey(0)
    if key & 0xFF == ord('q'):
        break
cv2.destroyAllWindows()

TrackBar 滑块

方法 说明 参数 返回
createTrackbar 创建 滑块名称,窗口名称,value 当前值,count 最大值,callback 回调,额外参数
getTrackbarPos 获取 滑块名称,窗口名称 当前值
python 复制代码 
import  cv2
import numpy as np

def callback():
    pass

cv2.namedWindow("img",cv2.WINDOW_NORMAL)

cv2.createTrackbar("R","img",0,255,callback)
cv2.createTrackbar("G","img",0,255,callback)
cv2.createTrackbar("B","img",0,255,callback)

img = np.zeros((480,640,3),np.uint8)

while True:

    r = cv2.getTrackbarPos("R","img")
    g = cv2.getTrackbarPos("G","img")
    b = cv2.getTrackbarPos("B","img")

    img[:] = [b,g,r]

    cv2.imshow("img",img)
    key = cv2.waitKey(10)
    if key & 0xFF == ord('q'):
        break
cv2.destroyAllWindows()

色彩

  • opencv 采用 BGR 格式的颜色显示
  • HSV 色相 / 饱和度 / 明度
  • HSL 色相 / 饱和度 / 明度
  • 色彩空间转换
方法 说明 参数 返回
cvtColor 色彩转换 获取到的图片资源,色彩转换
python 复制代码 
import cv2

def callback():
    pass
cv2.namedWindow('image',cv2.WINDOW_NORMAL)
cv2.resizeWindow('image',800,600)
img = cv2.imread("../1.jpg",1)
colorspaces = [cv2.COLOR_BGR2RGB,cv2.COLOR_BGR2BGRA,
               cv2.COLOR_BGR2GRAY,cv2.COLOR_BGR2HSV_FULL,
               cv2.COLOR_BGR2YUV]
cv2.createTrackbar('curcolor','image',0,len(colorspaces)-1,callback)
while True:
    v = cv2.getTrackbarPos('curcolor','image')
    # 颜色空间转换
    cvt_img = cv2.cvtColor(img,colorspaces[v])
    cv2.imshow('image',cvt_img)
    key = cv2.waitKey(10)
    if key & 0xFF == ord('q'):
        break
cv2.destroyAllWindows()

Numpy 基本操作

  • 创建矩阵
方法 参数 说明
array []
zeros (行,列,通道数),类型 值为0
ones (行,列,通道数),类型 值为1
full (行,列,通道数),值,类型
identity 3 三行三列
eye 3,5,k=1 三行五列, 从第 1-1列开始
python 复制代码 
import numpy as np

a = np.array([1,2,3])
b = np.array([[1,2,3],[4,5,6]])
print(a)
print(b)

c = np.zeros((8,8,3),np.uint8)
print(c)

d = np.ones((8,8,3),np.uint8)
print(d)

e = np.full((8,8,3),10,np.uint8)
print(e)

f = np.identity(4)
print(f)

y = np.eye(5,7,k=1)
print(y)
  • 赋值 [y,x]
  • 赋值 [y,x,channel]
python 复制代码 
import numpy as np
import cv2

img = np.zeros((640,480,3),np.uint8)
# 检索
print(img[100,100])
count = 0
while count < 100:
    # 赋值      通道  0,1,2
    # img[count,100,0] = 255
    img[count, 100] = [0,0,255]
    count = count+1
cv2.imshow("img",img)
key = cv2.waitKey(0)
if key & 0xFF == ord('q'):
    cv2.destroyAllWindows()
  • ROI 获取子矩阵 [y1:y2,x1:x2]

  • :,:\] 整个矩阵 \[:

python 复制代码 
import numpy as np
import cv2

img = np.zeros((640,480,3),np.uint8)
roi = img[100:200,100:200]
img[:] = [255,0,0]
roi[:,:] = [0,0,255]
roi[10:20,10:20] = [255,255,255]
cv2.imshow("img",img)
key = cv2.waitKey(0)
if key & 0xFF == ord('q'):
    cv2.destroyAllWindows()

Mat

  • 深浅拷贝
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')
# 浅拷贝
img2 = img
# 深拷贝
img3 = img.copy()
img[10:100,10:100] = [0,0,255]
cv2.imshow('img',img)
cv2.imshow('img2',img2)
cv2.imshow('img3',img3)
cv2.waitKey(0)
  • 属性
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')
# shape 高,长度,通道
print(img.shape)

# 图像占用多大空间
# 高度 * 长度 * 通道数
print(img.size)

# 图像中每个元素的位深
print(img.dtype)
  • 分割 / 合并
python 复制代码 
import numpy as np
import cv2

img = np.zeros((480,640,3),np.uint8)

# 分割
b,g,r = cv2.split(img)

b[10:100,10:100] = 255
g[10:100,10:100] = 255

# 合并
img2 = cv2.merge([b,g,r])

cv2.imshow("img",img)
cv2.imshow("b",b)
cv2.imshow("g",g)
cv2.imshow("img2",img2)
cv2.waitKey(0)

图形绘制

  • 线
  • 矩形
  • 圆
  • 椭圆
  • 多边形
  • 文本
python 复制代码 
import numpy as np
import cv2

img = np.zeros((480,640,3),np.uint8)

# 画线 坐标点 x,y
# 起始点     结束点    bgr     线条宽     线型:平滑
cv2.line(img,(10,20),(300,400),(0,0,255),2,16)

# 绘制矩形
# 图像   起始点     结束点    bgr     线条宽 -1为填充
cv2.rectangle(img, (100, 120), (160, 200), (0, 255, 0), 2)
cv2.rectangle(img, (180, 300), (160, 200), (0, 255, 0), -1)

# 圆
# 图像   圆点   半径   bgr     线条宽 -1为填充
cv2.circle(img,(300,300), 30, (255,0,0), 5)
cv2.circle(img,(360,360), 30, (255,0,0), -1)

# 椭圆
# 图像   圆点   长宽一半  起始角度  终止角度  角度     bgr  线条宽 -1为填充
cv2.ellipse(img,(300,420), (100,30),0,0,360, (255,0,0), 5)
cv2.ellipse(img,(300,420), (100,30),0,0,360, (255,0,0), -1)

pts = np.array([(300,10),(150,100),(450,100)],np.int32)
# 多边形
# 图像   点集  是否闭合   bgr  线条宽 
cv2.polylines(img,[pts],True,(0,255,0))
# 多边形填充
# 图像   点集    bgr
cv2.fillPoly(img,[pts],(0,255,0))

# 文本
# 图像    文本    起始点    字体    字号    brg
cv2.putText(img,"Hello World!!!",(100,100),cv2.FONT_HERSHEY_PLAIN,3,(255,255,255))

cv2.imshow("img",img)
cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2

# 通过鼠标进行图形的绘制
# 1. l键 画线
# 2. r键 画矩形
# 3. c键 画圆

current = 0
startpos = (0,0)
def mouse_callback(event, x, y, flags, param):
    # print(event, x, y, flags, param)
    global current,startpos
    if event & cv2.EVENT_LBUTTONDOWN == cv2.EVENT_LBUTTONDOWN:
        startpos = (x,y)
    elif event & cv2.EVENT_LBUTTONUP == cv2.EVENT_LBUTTONUP:
        if current == 0:
            cv2.line(img,startpos,(x,y),(0,0,255))
        elif current == 1:
            cv2.rectangle(img,startpos,(x,y),(0,0,255))
        elif current == 2:
            a = (x-startpos[0])
            b = (y-startpos[1])
            r = (a**2 + b**2)**0.5
            cv2.circle(img,startpos,int(r),(0,0,255))
        else:
            print("无其它")

cv2.namedWindow("img",cv2.WINDOW_NORMAL)

cv2.setMouseCallback("img",mouse_callback,"123")

img = np.zeros((480,640,3),np.uint8)
while True:
    cv2.imshow("img",img)
    key = cv2.waitKey(1)
    if key & 0xFF == ord('q'):
        break
    elif key  == ord('l'):
        current =0
    elif key  == ord('r'):
        current =1
    elif key  == ord('c'):
        current =2

cv2.destroyAllWindows()

图像运算

  • 加
  • 减
  • 乘
  • 除
  • 溶合
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')
img2 = np.ones(img.shape,np.uint8) * 50
# 加    原始图像   相加的图像
img11 = cv2.add(img, img2)
# 减    原始图像   相减的图像
img22 = cv2.subtract(img, img2)
# 乘    原始图像   相乘的图像
img33 = cv2.multiply(img, img2)
# 除    原始图像   相除的图像
img44 = cv2.divide(img, img2)
# 溶合    原始图像 原始图像权重    溶合的图像 溶合的图像权重  静态权重
img55 = cv2.addWeighted(img,0.1, img2,0.9,0)
cv2.imshow('img', img)
cv2.imshow('img11', img11)
cv2.imshow('img22', img22)
cv2.imshow('img33', img33)
cv2.imshow('img44', img44)
cv2.imshow('img55', img55)
cv2.waitKey(0)
  • 非运算
  • 与运算
  • 或运算
  • 异或运算
python 复制代码 
import numpy as np
import cv2

img1 = np.zeros((200,200),np.uint8)
img1[50:150,50:150] = 255
# 非运算
img11 = cv2.bitwise_not(img1)

img2 = np.zeros((200,200),np.uint8)
img22 = np.zeros((200,200),np.uint8)
img2[20:120,20:120] = 255
img22[80:150,80:150] = 255
# 与运算
# img222 = cv2.bitwise_and(img2,img22)
# 或运算
# img222 = cv2.bitwise_or(img2,img22)
# 异或运算
img222 = cv2.bitwise_xor(img2,img22)

cv2.imshow('img1',img1)
cv2.imshow('img11',img11)
cv2.imshow('img222',img222)
cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')

# roi 获取图标在原始图像的位置
roi = img[0:200,0:200]

# 图标创建
logo = np.zeros((200,200, 3), np.uint8)
logo[20:120,20:120] = [0,0,255]
logo[80:180,80:180] = [0,255,0]

# 创建一个与图标相同的图像
# 使用非运算取相反的图像
# 图标在原始图像的位置与当前获取相反图标进行与运算得到原始图像中显示图标的位置
# logo与原始图像中显示图标相加得到原始图像显示logo的图像
mask = np.zeros((200,200), np.uint8)
mask[20:120,20:120] = 255
mask[80:180,80:180] = 255
m = cv2.bitwise_not(mask)
tmp = cv2.bitwise_and(roi,roi,mask=m)
dst = cv2.add(tmp,logo)

# 更改原始图像显示logo位置的图像
img[0:200,0:200] = dst

cv2.imshow('logo', dst)
cv2.waitKey(0)

图像变换

  • 缩放
  • 翻转
  • 旋转
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')

# 缩放
# 图像  (长,宽)   fx 长缩放比例  fy 宽缩放比例   interpolation 插值算法
img1 = cv2.resize(img, (224, 224))
img2 = cv2.resize(img, None, fx=0.6, fy=0.6, interpolation=cv2.INTER_AREA)
img3 = cv2.resize(img, None, fx=1.6, fy=1.6, interpolation=cv2.INTER_AREA)

cv2.imshow('image', img)
cv2.imshow('image1', img1)
cv2.imshow('image2', img2)
cv2.imshow('image3', img3)
cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')

# 翻转
# 图像  0 上下翻转   >0 左右翻转    <0 上下左右翻转
img1 = cv2.flip(img, 0)
img2 = cv2.flip(img, 1)
img3 = cv2.flip(img, -1)

cv2.imshow('image', img)
cv2.imshow('image1', img1)
cv2.imshow('image2', img2)
cv2.imshow('image3', img3)
cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')

# 旋转
img1 = cv2.rotate(img, cv2.ROTATE_90_CLOCKWISE)

cv2.imshow('image', img1)
cv2.waitKey(0)
  • 仿射变换
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')
h,w,ch = img.shape
print(h,w)
# 平移
# M = np.float32([[1,0,100],[0,1,200]])
# 中心点   旋转角度(逆时针)   缩放
# M = cv2.getRotationMatrix2D((w/2,h/2),15,1.0)
src = np.float32([[200,150],[400,150],[400,500]])
dst = np.float32([[100,200],[300,250],[150,600]])
M = cv2.getAffineTransform(src,dst)
# 修改新图的尺寸dsize(w/2,h/2)
img2 = cv2.warpAffine(img,M,(w,h))

cv2.imshow('img',img)
cv2.imshow('img2',img2)
cv2.waitKey(0)
  • 透视变换
python 复制代码 
import numpy as np
import cv2


img = cv2.imread('../1.jpg')

src = np.float32([[10,300],[100,300],[20,500],[150,450]])
dst = np.float32([[0,0],[120,0],[0,300],[120,300]])
M = cv2.getPerspectiveTransform(src,dst)
img1 = cv2.warpPerspective(img,M,(300,120))

cv2.imshow('img',img)
cv2.imshow('img1',img1)
cv2.waitKey(0)

图像滤波

python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')
kernel = np.ones((5,5),np.uint32) / 25
dst = cv2.filter2D(img,-1,kernel)
cv2.imshow('img',img)
cv2.imshow('dst',dst)
cv2.waitKey(0)
  • 方盒滤波
  • 均值滤波
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')

dst = cv2.blur(img,(5,5))

cv2.imshow('img',img)
cv2.imshow('dst',dst)
cv2.waitKey(0)
  • 高斯滤波
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')

dst = cv2.GaussianBlur(img,(5,5),sigmaX=1)

cv2.imshow('img',img)
cv2.imshow('dst',dst)
cv2.waitKey(0)
  • 中值滤波
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')

dst = cv2.medianBlur(img,5)

cv2.imshow('img',img)
cv2.imshow('dst',dst)
cv2.waitKey(0)
  • 双边滤波
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')

dst = cv2.bilateralFilter(img,5,20,50)

cv2.imshow('img',img)
cv2.imshow('dst',dst)
cv2.waitKey(0)
  • 高通滤波
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('./12.png')

# 索贝尔算子x方向边缘
dst = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=5)
# 索贝尔算子y方向边缘
dst1 = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=5)
dst2 = cv2.add(dst,dst1)
cv2.imshow('img',img)
cv2.imshow('dst',dst2)
cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('./12.png')

# 沙尔算子x方向边缘
dst = cv2.Scharr(img,cv2.CV_64F,1,0)
# 沙尔算子y方向边缘
dst1 = cv2.Scharr(img,cv2.CV_64F,0,1)
dst2 = cv2.add(dst,dst1)
cv2.imshow('img',img)
cv2.imshow('dst',dst2)
cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('./12.png')

# 拉普拉斯算子边缘,需先进行降噪
dst = cv2.Laplacian(img,cv2.CV_64F,ksize=5)

cv2.imshow('img',img)
cv2.imshow('dst',dst)
cv2.waitKey(0)

边缘检测

python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')

# Canny
dst = cv2.Canny(img,100,200)

cv2.imshow('img',img)
cv2.imshow('dst',dst)
cv2.waitKey(0)

形态学图像处理

  • 图像二值化
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')
img1 = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

ret,img2 = cv2.threshold(img1,180,255,cv2.THRESH_BINARY)

cv2.imshow('img',img)
cv2.imshow('img1',img1)
cv2.imshow('img2',img2)

cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('../1.jpg')
img1 = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

dst = cv2.adaptiveThreshold(img1,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY,3,0)

cv2.imshow('img',img)
cv2.imshow('img1',img1)
cv2.imshow('img2',dst)

cv2.waitKey(0)
  • 腐蚀
  • 膨胀
python 复制代码 
import numpy as np
import cv2

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

# kernel = np.ones((3,3),np.uint8)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(3,3))
# 腐蚀
img1 = cv2.erode(img,kernel,iterations = 1)
# 膨胀
img2 = cv2.dilate(img1,kernel,iterations = 1)

cv2.imshow('img',img)
cv2.imshow('img1',img1)
cv2.imshow('img2',img2)

cv2.waitKey(0)
  • 开运算
    • 腐蚀 + 膨胀
  • 闭运算
    • 膨胀 + 腐蚀
  • 梯度
  • 顶帽
    • 原图 - 开运算
  • 黑帽
    • 原图 - 闭运算
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('./img_1.png')
img3 = cv2.imread('./img_3.png')
img6 = cv2.imread('./img_2.png')
imgd = cv2.imread('./img_4.png')

# kernel = np.ones((3,3),np.uint8)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(7,7))
# 开运算
img2 = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)
# 闭运算
img33 = cv2.morphologyEx(img3, cv2.MORPH_CLOSE, kernel)
# 梯度
img66 = cv2.morphologyEx(img6, cv2.MORPH_GRADIENT, kernel)
# 顶帽
imgdd = cv2.morphologyEx(imgd, cv2.MORPH_TOPHAT, cv2.getStructuringElement(cv2.MORPH_RECT,(19,19)))
# 黑帽
imgh = cv2.morphologyEx(img3, cv2.MORPH_BLACKHAT, kernel)

cv2.imshow('img2',img2)
cv2.imshow('img33',img33)
cv2.imshow('img66',img66)
cv2.imshow('imgdd',imgdd)
cv2.imshow('imgh',imgh)
cv2.waitKey(0)

图像轮廓

python 复制代码 
import numpy as np
import cv2

img = cv2.imread('./img_5.png')

# 转为单通道
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 二值化
ret,img1 = cv2.threshold(gray,150,255,cv2.THRESH_BINARY)
# 查找轮廓
contours,hierarchy = cv2.findContours(img1,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
# 绘制轮廓
cv2.drawContours(img,contours,-1,(0,0,255),1)
# 计算面积
area = cv2.contourArea(contours[0])
print(area)
# 计算周长
len = cv2.arcLength(contours[0],True)
print(len)

cv2.imshow('img', img)
cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('./img_6.png')

# 转为单通道
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 二值化
ret,img1 = cv2.threshold(gray,150,255,cv2.THRESH_BINARY)
# 查找轮廓
contours,hierarchy = cv2.findContours(img1,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
# 绘制轮廓
cv2.drawContours(img,contours,0,(255,0,0),1)
# 多边形逼近
approx = cv2.approxPolyDP(contours[0],20,True)
# 多边形凸包
hull = cv2.convexHull(contours[0])

def drawShape(img, approx):
    i = 0
    while i < len(approx):
        if i == len(approx) - 1:
            x, y = approx[i][0]
            x1, y1 = approx[0][0]
            cv2.line(img, (x, y), (x1, y1), (0, 0, 255), 1)
        else:
            x, y = approx[i][0]
            x1, y1 = approx[i + 1][0]
            cv2.line(img, (x, y), (x1, y1), (0, 0, 255), 1)
        i = i+1

drawShape(img,approx)
drawShape(img,hull)

cv2.imshow('img', img)
cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2


img = cv2.imread('./img_7.png')

# 转为单通道
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 二值化
ret,img1 = cv2.threshold(gray,150,255,cv2.THRESH_BINARY)
# 查找轮廓
contours,hierarchy = cv2.findContours(img1,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)

# 最小外接矩形
r = cv2.minAreaRect(contours[1]) 
box = cv2.boxPoints(r)
box = np.int8(box)
cv2.drawContours(img,[box],0,(0,0,255),2)

# 最大外接矩形
x,y,w,h = cv2.boundingRect(contours[1])
cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2)

cv2.imshow("img",img)
cv2.waitKey(0)

特征点检测

  • 哈里斯角点检测
  • Shi-Tomasi 角点检测
  • SIFT
  • SURF
  • ORB
python 复制代码 
import numpy as np
import cv2

img = cv2.imread('./12.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# dst = cv2.cornerHarris(gray, 2, 3, 0.04)
# img[dst>0.01*dst.max()] = [0,0,255]

# corners = cv2.goodFeaturesToTrack(gray, 1000, 0.01, 10)
# corners = np.int8(corners)
# for i in corners:
#     x,y = i.ravel()
#     cv2.circle(img,(x,y),3,(255,0,0),-1)

# sift = cv2.SIFT.create()
# kp,des = sift.detectAndCompute(gray, None)
# cv2.drawKeypoints(gray,kp,img)

orb = cv2.ORB.create()
kp,des = orb.detectAndCompute(gray,None)
cv2.drawKeypoints(gray,kp,img)

cv2.imshow("img",img)
cv2.waitKey(0)

特征匹配

  • BF
python 复制代码 
import numpy as np
import cv2

img1 = cv2.imread('./img.png')
img2 = cv2.imread('./img_1.png')
gray1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
gray2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)

sift = cv2.SIFT.create()
kp1,des1 = sift.detectAndCompute(gray1, None)
kp2,des2 = sift.detectAndCompute(gray2, None)

bf = cv2.BFMatcher(cv2.NORM_L1)
matches = bf.match(des1, des2)
img3 = cv2.drawMatches(img1, kp1, img2, kp2, matches, None, flags=2)

cv2.imshow("img",img3)
cv2.waitKey(0)
  • FLANN
python 复制代码 
import numpy as np
import cv2

img1 = cv2.imread('./img.png')
img2 = cv2.imread('./img_1.png')
gray1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
gray2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)

sift = cv2.SIFT.create()
kp1,des1 = sift.detectAndCompute(gray1, None)
kp2,des2 = sift.detectAndCompute(gray2, None)


flann = cv2.FlannBasedMatcher( dict(trees=5,algorithm=1),dict(checks=50))
matches = flann.knnMatch(des1, des2,k=2)

good = []
for i,(m,n) in enumerate(matches):
    if m.distance < 0.7*n.distance:
        good.append(m)

ret = cv2.drawMatchesKnn(img1,kp1,img2,kp2,[good],None)

cv2.imshow("img",ret)
cv2.waitKey(0)

图像分割

python 复制代码 
import numpy as np
import cv2

img = cv2.imread("./img.png")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)

kernel = np.ones((3,3),np.uint8)
open1 = cv2.morphologyEx(thresh,cv2.MORPH_OPEN,kernel,iterations=2)

bg = cv2.dilate(open1,kernel,iterations=2)

dist = cv2.distanceTransform(open1,cv2.DIST_L2,5)
re1t,fg = cv2.threshold(dist,0.7*dist.max(),255,cv2.THRESH_BINARY)

fg = np.uint8(fg)
unknow = cv2.subtract(bg,fg)

ret3,marker = cv2.connectedComponents(fg)
marker = marker + 1
marker[unknow == 255] = 0

result = cv2.watershed(img,marker)

img[result == -1] = [0,0,255]

cv2.imshow("img",img)
cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2


class App:
    rect = (0,0,0,0)
    flag_rect = False
    startX = 0
    startY = 0

    def onmouse(self,event,x,y,flags,param):
        print("onmouse")

        if event == cv2.EVENT_LBUTTONDOWN:
            self.flag_rect = True
            self.startX = x
            self.startY = y
        elif event == cv2.EVENT_LBUTTONUP:
            self.flag_rect = False
            cv2.rectangle(self.img,(self.startX,self.startY),(x,y),(0,0,255),2)

            self.rect = (min(self.startX,x),min(self.startY,y),abs(self.startX - x),abs(self.startY - y))
            print("左键抬起")
        elif event == cv2.EVENT_MOUSEMOVE:
            if self.flag_rect:
                self.img = self.img2.copy()
                cv2.rectangle(self.img,(self.startX,self.startY),(x,y),(255,0,0),2)
            print("移动")


    def run(self):
        print("run")
        cv2.namedWindow('input')
        cv2.setMouseCallback('input',self.onmouse)

        self.img = cv2.imread('./img.png')
        self.img2 = self.img.copy()
        self.mask = np.zeros(self.img.shape[:2],np.uint8)
        self.output = np.zeros(self.img.shape,np.uint8)

        while 1:
            cv2.imshow('input',self.img)
            cv2.imshow('output',self.output)
            k = cv2.waitKey(100)
            if k == 27:
                break
            if k == ord('g'):
                bgmodel = np.zeros((1,65),np.float64)
                fgmodel = np.zeros((1,65),np.float64)
                cv2.grabCut(self.img2,self.mask,self.rect,bgmodel,fgmodel,1,cv2.GC_INIT_WITH_RECT)

            mask2 = np.where((self.mask == 1)|(self.mask == 3),255,0).astype('uint8')
            self.output = cv2.bitwise_and(self.img2,self.img2,mask=mask2)


App().run()
python 复制代码 
import numpy as np
import cv2

img = cv2.imread("./img.png")

img2 = cv2.pyrMeanShiftFiltering(img, 20, 30)

img3 = cv2.Canny(img2, 150, 300)

contours,_ = cv2.findContours(img3, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(img, contours, -1, (0,0,255), 2)

cv2.imshow("img", img)
cv2.imshow("img2", img2)
cv2.imshow("img3", img3)

cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2

cap = cv2.VideoCapture('../2.mp4')

mog = cv2.createBackgroundSubtractorMOG2()

while cap.isOpened():
    ret, frame = cap.read()
    fgmask = mog.apply(frame)

    cv2.imshow('frame', fgmask)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()

图像修复

python 复制代码 
import numpy as np
import cv2

img = cv2.imread("./img_1.png")
mask = cv2.imread("./img_2.png",0)
mask = cv2.resize(mask,(img.shape[1],img.shape[0]))
print(img.shape)
print(mask.shape)
dst = cv2.inpaint(img,mask,3,cv2.INPAINT_TELEA)

cv2.imshow("img",dst)
cv2.waitKey(0)

哈尔级联法

人脸识别

python 复制代码 
import numpy as np
import cv2

# 创建haar级联器
facer = cv2.CascadeClassifier(
    'D:\SoftWare\py\Lib\site-packages\cv2\data\haarcascade_frontalface_default.xml'
)

img = cv2.imread('./img_3.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

faces = facer.detectMultiScale(gray,1.1,5)

for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)

cv2.imshow('img', img)
cv2.waitKey(0)
python 复制代码 
import numpy as np
import cv2

# 创建haar级联器
facer = cv2.CascadeClassifier(
    'D:\SoftWare\py\Lib\site-packages\cv2\data\haarcascade_frontalface_default.xml'
)

img = cv2.VideoCapture(0)

while True:
    ret,frame = img.read()

    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    faces = facer.detectMultiScale(gray,1.1,5)

    for (x, y, w, h) in faces:
        cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2)

    cv2.imshow('img', frame)
    k = cv2.waitKey(10)
    if k == 27:
        break
img.release()
cv2.destroyAllWindows()
  • 眼
python 复制代码 
import numpy as np
import cv2

# 眼
facer = cv2.CascadeClassifier(
    'D:\SoftWare\py\Lib\site-packages\cv2\data\haarcascade_eye.xml'
)

img = cv2.imread('./img_3.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

faces = facer.detectMultiScale(gray,1.1,5)


for (x, y, w, h) in faces:
    cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)

cv2.imshow('img', img)
cv2.waitKey(0)
相关推荐
Funny_AI_LAB1 小时前
深度解析Andrej Karpathy访谈：关于AI智能体、AGI、强化学习与大模型的十年远见
人工智能·计算机视觉·ai·agi
滨HI03 小时前
opencv 计算面积、周长
人工智能·opencv·计算机视觉
格林威4 小时前
AOI在风电行业制造领域中的应用
人工智能·数码相机·计算机视觉·视觉检测·制造·机器视觉·aoi
禁默6 小时前
第四届图像处理、计算机视觉与机器学习国际学术会议(ICICML 2025)
图像处理·机器学习·计算机视觉
唯道行7 小时前
计算机图形学·9 几何学
人工智能·线性代数·计算机视觉·矩阵·几何学·计算机图形学
AndrewHZ7 小时前
【图像处理基石】什么是alpha matting？
图像处理·人工智能·计算机视觉·matting·发丝分割·trimap·人像模式
这张生成的图像能检测吗9 小时前
（综述）基于深度学习的制造业表面缺陷检测图像合成方法综述
人工智能·计算机视觉·图像生成·工业检测·计算机图像学
AI纪元故事会17 小时前
【计算机视觉目标检测算法对比：R-CNN、YOLO与SSD全面解析】
人工智能·算法·目标检测·计算机视觉
音视频牛哥18 小时前
SmartMediaKit：如何让智能系统早人一步“跟上现实”的时间架构--从实时流媒体到系统智能的演进
人工智能·计算机视觉·音视频·音视频开发·具身智能·十五五规划具身智能·smartmediakit
音视频牛哥19 小时前
超清≠清晰：视频系统里的分辨率陷阱与秩序真相
人工智能·机器学习·计算机视觉·音视频·大牛直播sdk·rtsp播放器rtmp播放器·smartmediakit
热门推荐
01GitHub 镜像站点02UV安装并设置国内源03综合整理：pdf预览显示：你尝试预览的文件可能对你的计算机有害。如果你信任此文件以及其来源，请打开此文件以看其内容，如何解决以正常预览文件04Linux下V2Ray安装配置指南05npm使用国内淘宝镜像的方法06安娜的档案(Anna’s Archive) 镜像网站/国内最新可访问入口（持续更新）07《大数据技术原理与应用》实验报告三 熟悉HBase常用操作08NVIDIA显卡驱动、CUDA、cuDNN 和 TensorRT 版本匹配指南09BongoCat - 跨平台键盘猫动画工具10GitLab 零基础入门指南：从安装到项目管理全流程