Opencv基本操作

读取图片和网络摄像头

1.1 图片读取

import cv2
img = cv2.imread("Resources/jty.jpg")
cv2.namedWindow("Output", cv2.WINDOW_NORMAL) # 创建一个窗口，并指定窗口名称
cv2.resizeWindow("Output", 600, 840) # 设置窗口大小
cv2.imshow("Output",img)
cv2.waitKey(0)

1.2 视频读取

1.2.1 读取视频文件

import cv2
# read video
cap = cv2.VideoCapture("Resources/test_video.mp4")
while True:
   success,img = cap.read()
   cv2.imshow("Video",img)
   if cv2.waitKey(1) & 0xFF == ord('q'):
       break

1.2.2 读取网络摄像头

import cv2
# read webcam
cap = cv2.VideoCapture(0)
cap.set(3,640) #width
cap.set(4,480) #height
cap.set(10,100)

while True:
   success,img = cap.read()
   cv2.imshow("Video",img)
   if cv2.waitKey(1) & 0xFF == ord('q'):
       break

OpenCV基础功能

import cv2
import numpy as np

# basic function
img = cv2.imread("Resources/jty.jpg")
kernel = np.ones((5, 5), np.uint8)

# 灰度转换
imgGray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
imgGray = cv2.resize(imgGray,(350,300))
# 图像模糊
imgBlur = cv2.GaussianBlur(imgGray, (7, 7), 0)
#imgBlur = cv2.resize(imgBlur,(350,300))
# 边缘检测
imgCanny = cv2.Canny(img, 100, 100)
imgCanny = cv2.resize(imgCanny,(350,300))
# 膨胀
imgDialation = cv2.dilate(imgCanny, kernel, iterations=1)
#imgDialation = cv2.resize(imgDialation,(350,300))
# 腐蚀
imgEroded = cv2.erode(imgDialation, kernel, iterations=1)
#imgEroded = cv2.resize(imgEroded,(350,300))

# cv2.imshow("Output",img)
cv2.imshow("Gray Image", imgGray)
cv2.imshow("Blur Image", imgBlur)
cv2.imshow("Canny Image", imgCanny)
cv2.imshow("Dialation Image", imgDialation)
cv2.imshow("Eroded Image", imgEroded)

cv2.waitKey(0)

调整、裁剪图像

3.1 调整图像大小

import cv2

# resize image

img = cv2.imread("Resources/zjy.png")
print(img.shape)

imgResize = cv2.resize(img,(250,300))
print(imgResize.shape)

cv2.imshow("Image",img)
cv2.imshow("Image Resize",imgResize)


cv2.waitKey(0)

裁剪图像

import cv2

img=cv2.imread("Resources/zjy.png")
img = cv2.resize(img,(250,300))
cv2.imshow('image',img)


print(img.shape)#height,width,dpth


crop_img=img[20:200,50:200]
cv2.imshow('crop image',crop_img)

cv2.waitKey(0)

图像上绘制形状和文本

4.1 图像上绘制形状

import cv2
import numpy as np

# shapes and texts
img = np.zeros((512, 512, 3), np.uint8)
cv2.imshow('oringin image', img)

# 从左上角（0, 0）到右下角（图像的宽度和高度）绘制了一条绿色线条，线条的粗细为3个像素
cv2.line(img, (0, 0), (img.shape[1], img.shape[0]), (0, 255, 0), 3)
cv2.imshow('line image', img)

# 在图像上绘制了一个红色矩形，左上角坐标为（0, 0），右下角坐标为（250, 350），线条的粗细为2个像素。
cv2.rectangle(img, (0, 0), (250, 350), (0, 0, 255), 2)
cv2.imshow('rectangle image', img)

# 在图像上绘制了一个黄色圆形，圆心坐标为（400, 500），半径为30个像素，线条的粗细为5个像素。
cv2.circle(img, (400, 500), 30, (255, 255, 0), 5)
cv2.imshow('circle image', img)

cv2.waitKey(0)

4.2 图像上写文字

import cv2
import numpy as np

img = np.zeros((512,512,3),np.uint8)
cv2.imshow('oringin image',img)

# 这将在图像 img 上绘制文本 "OPENCV"，文本的左下角位于坐标 (300, 200) 处，使用 cv2.FONT_HERSHEY_COMPLEX 字体，字体大小为基本大小的 1 倍，文本颜色为蓝绿色 (0, 150, 0)，线条粗细为 1 像素。
cv2.putText(img,"OPENCV",(300,200),cv2.FONT_HERSHEY_COMPLEX,1,(0,150,0),1)
cv2.imshow("putText01 Image",img)
cv2.putText(img,"I LOVE XD",(100,300),cv2.FONT_HERSHEY_COMPLEX,1,(0,150,0),1)
cv2.imshow("putText02 Image",img)

cv2.waitKey(0)

图像拼接

import cv2
import numpy as np
# join images
def stackImages(scale,imgArray):
    rows = len(imgArray)
    cols = len(imgArray[0])
    rowsAvailable = isinstance(imgArray[0], list)
    width = imgArray[0][0].shape[1]
    height = imgArray[0][0].shape[0]
    if rowsAvailable:
        for x in range ( 0, rows):
            for y in range(0, cols):
                if imgArray[x][y].shape[:2] == imgArray[0][0].shape [:2]:
                    imgArray[x][y] = cv2.resize(imgArray[x][y], (0, 0), None, scale, scale)
                else:
                    imgArray[x][y] = cv2.resize(imgArray[x][y], (imgArray[0][0].shape[1], imgArray[0][0].shape[0]), None, scale, scale)
                if len(imgArray[x][y].shape) == 2: imgArray[x][y]= cv2.cvtColor( imgArray[x][y], cv2.COLOR_GRAY2BGR)
        imageBlank = np.zeros((height, width, 3), np.uint8)
        hor = [imageBlank]*rows
        # 这行代码使用了一个for循环来遍历imgArray中的每一行（imgArray应该是一个二维列表，其中每个子列表包含了一行中要堆叠的图像）。np.hstack函数用于将imgArray[x]中的所有图像在水平方向上堆叠起来，然后将堆叠后的结果赋值给hor[x]。
        for x in range(0, rows):
            hor[x] = np.hstack(imgArray[x])
        ver = np.vstack(hor)
    else:
        for x in range(0, rows):
            if imgArray[x].shape[:2] == imgArray[0].shape[:2]:
                imgArray[x] = cv2.resize(imgArray[x], (0, 0), None, scale, scale)
            else:
                imgArray[x] = cv2.resize(imgArray[x], (imgArray[0].shape[1], imgArray[0].shape[0]), None,scale, scale)
            if len(imgArray[x].shape) == 2: imgArray[x] = cv2.cvtColor(imgArray[x], cv2.COLOR_GRAY2BGR)
        hor= np.hstack(imgArray)
        ver = hor
    return ver


img = cv2.imread('Resources/jty.jpg')
imgGray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

imgStack = stackImages(0.15,([img,imgGray,img],[img,img,img]))

cv2.imshow("ImageStack",imgStack)

cv2.waitKey(0)

人脸识别

6.1 静态图片

import cv2
# face detection
faceCascade = cv2.CascadeClassifier("Resources/haarcascade_frontalface_default.xml")
img = cv2.imread("Resources/jty.jpg")
img = cv2.resize(img,(250,300))
imgGray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

faces = faceCascade.detectMultiScale(imgGray,1.1,4)

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

cv2.waitKey(0)

6.2 摄像头

import cv2

faceCascade = cv2.CascadeClassifier("Resources/haarcascade_frontalface_default.xml")

cap = cv2.VideoCapture(0)
cap.set(3,640) #width
cap.set(4,480) #height
cap.set(10,100)

while True:
   success,img = cap.read()
   cv2.imshow("Video",img)
   imgGray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

   faces = faceCascade.detectMultiScale(imgGray, 1.1, 4)

   for (x, y, w, h) in faces:
       cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
   cv2.imshow("Result", img)
   if cv2.waitKey(1) & 0xFF == ord('q'):
       break