【opencv-python- 识别图片中的矩形轮廓，进行原比例恢复】
使用opencv-python 识别图片中的矩形轮廓，进行原比例恢复
首先进行图片导入
cap = cv2.VideoCapture(0,cv2.CAP_DSHOW)
# get是获取视频属性，set是重新设置视频属性
cap.set(3, 640)
cap.set(4, 480)
while True:
success, img = cap.read()
imgContour = img.copy()
res = preprocess(img)
getContours(res)
cv2.imshow("res", imgContour)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
对图片进行预处理，转为灰度图，高斯模糊，边缘化，膨胀和腐蚀
def preprocess(img):
imgGray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
imgBlur = cv2.GaussianBlur(imgGray,(3, 3),0)
imgCanny = cv2.Canny(imgBlur, 200, 200)
imgdialation = cv2.dilate(imgCanny,kernel,iterations=1)
imgerode = cv2.erode(imgdialation,kernel,iterations=1)
res = stackImages(0.3,([img,imgGray,imgBlur],[imgCanny, imgdialation, imgerode]))
cv2.imshow("yy",res)
return imgerode
然后识别处理后的图片轮廓，找出有四个拐点的矩形，选择图片中的最大矩形
轮廓形状识别详细之前博客有写，输出最大矩形
def getContours(img):
# contours：list结构，列表中每个元素代表一个边沿信息。每个元素是(x, 1, 2)的三维向量，x表示该条边沿里共有多少个像素点，第三维的那个“2”表示每个点的横、纵坐标；
# hierarchy：返回类型是(x, 4)的二维ndarray。x和contours里的x是一样的意思。
contours, hierarchy = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
maxarea = 0
bigcontour = np.array([])
bigcnt = np.array([])
for cnt in contours:
#传入轮廓计算面积
area = cv2.contourArea(cnt)
print(area)
if area>5000:
# cv2.drawContours(imgContour, cnt, -1, (255, 0, 0), 3)
# 计算轮廓的周长
peri = cv2.arcLength(cnt,True)
#print(peri)
approx = cv2.approxPolyDP(cnt,0.02*peri,True)
# 提取拐点
objCor = len(approx)
x, y, w, h = cv2.boundingRect(approx)
if objCor == 4 and area > maxarea:
maxarea = area
bigcnt = cnt
bigcontour = approx
cv2.drawContours(imgContour, bigcontour, -1, (255, 0, 0), 15)
cv2.drawContours(imgContour, bigcnt, -1, (255, 0, 0), 3)
return bigcontour
对最大的矩形进行复原，透视矫正图片
width,height =200,300
pts1=np.float32([[651,511],[749,535],[614,594],[717,621]])
pts2=np.float32([[0,0],[width,0],[0,height],[width,height]])
matrix = cv2.getPerspectiveTransform(pts1,pts2)
imgput = cv2.warpPerspective(img,matrix,(width,height))
cv2.imshow("majiang", imgput)
cv2.waitKey(0)
注意如果这里是视频的话输出的矩形坐标不能很容易确定，四角的坐标先后顺序这里需要恢复一下
def reorder (myPoints):
myPoints = myPoints.reshape((4,2))
myPointsNew = np.zeros((4,1,2),np.int32)
add = myPoints.sum(1)
#print("add", add)
myPointsNew[0] = myPoints[np.argmin(add)]
myPointsNew[3] = myPoints[np.argmax(add)]
diff = np.diff(myPoints,axis=1)
myPointsNew[1]= myPoints[np.argmin(diff)]
myPointsNew[2] = myPoints[np.argmax(diff)]
#print("NewPoints",myPointsNew)
return myPointsNew
处理效果如图
完整的代码
import cv2
import numpy as np
###################################
widthImg=540
heightImg =640
#####################################
cap = cv2.VideoCapture(1)
cap.set(10,150)
def preProcessing(img):
imgGray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
imgBlur = cv2.GaussianBlur(imgGray,(5,5),1)
imgCanny = cv2.Canny(imgBlur,200,200)
kernel = np.ones((5,5))
imgDial = cv2.dilate(imgCanny,kernel,iterations=2)
imgThres = cv2.erode(imgDial,kernel,iterations=1)
return imgThres
def getContours(img):
biggest = np.array([])
maxArea = 0
contours,hierarchy = cv2.findContours(img,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)
for cnt in contours:
area = cv2.contourArea(cnt)
if area>5000:
#cv2.drawContours(imgContour, cnt, -1, (255, 0, 0), 3)
peri = cv2.arcLength(cnt,True)
approx = cv2.approxPolyDP(cnt,0.02*peri,True)
if area >maxArea and len(approx) == 4:
biggest = approx
maxArea = area
cv2.drawContours(imgContour, biggest, -1, (255, 0, 0), 20)
return biggest
def reorder (myPoints):
myPoints = myPoints.reshape((4,2))
myPointsNew = np.zeros((4,1,2),np.int32)
add = myPoints.sum(1)
#print("add", add)
myPointsNew[0] = myPoints[np.argmin(add)]
myPointsNew[3] = myPoints[np.argmax(add)]
diff = np.diff(myPoints,axis=1)
myPointsNew[1]= myPoints[np.argmin(diff)]
myPointsNew[2] = myPoints[np.argmax(diff)]
#print("NewPoints",myPointsNew)
return myPointsNew
def getWarp(img,biggest):
biggest = reorder(biggest)
pts1 = np.float32(biggest)
pts2 = np.float32([[0, 0], [widthImg, 0], [0, heightImg], [widthImg, heightImg]])
matrix = cv2.getPerspectiveTransform(pts1, pts2)
imgOutput = cv2.warpPerspective(img, matrix, (widthImg, heightImg))
imgCropped = imgOutput[20:imgOutput.shape[0]-20,20:imgOutput.shape[1]-20]
imgCropped = cv2.resize(imgCropped,(widthImg,heightImg))
return imgCropped
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
hor_con = [imageBlank]*rows
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
while True:
success, img = cap.read()
img = cv2.resize(img,(widthImg,heightImg))
imgContour = img.copy()
imgThres = preProcessing(img)
biggest = getContours(imgThres)
if biggest.size !=0:
imgWarped=getWarp(img,biggest)
# imageArray = ([img,imgThres],
# [imgContour,imgWarped])
imageArray = ([imgContour, imgWarped])
cv2.imshow("ImageWarped", imgWarped)
else:
# imageArray = ([img, imgThres],
# [img, img])
imageArray = ([imgContour, img])
stackedImages = stackImages(0.6,imageArray)
cv2.imshow("WorkFlow", stackedImages)
if cv2.waitKey(1) & 0xFF == ord('q'):
break