effect
First look at the effect
Test results:
Ideas
-
Original image to grayscale
-
Perform Gaussian filtering, median filtering and denoising on grayscale images
-
Use the sobel operator to calculate the gradient (that is, extract the edge). Considering that the words on the license plate are all thin and long, I only use the horizontal gradient here to avoid environmental interference
-
Gaussian filtering of the gradient map to remove details
-
Convert Binary Graph
-
Corrosion once and expand 10 times to connect the license plate into a white color block
-
Find the contour with the largest enclosed area, correct the direction, and finally draw
Code
import cv2 import numpy as np #read the picture imagePath ='car.jpg' img = cv2.imread(imagePath) #turn to grayscale img_gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) #Gaussian filter + median filter img_gaus = cv2.GaussianBlur(img_gray,(3,3),0,0,cv2.BORDER_DEFAULT) img_median = cv2.medianBlur(img_gaus,3) #Use the sobel operator to calculate the gradient and only calculate the horizontal direction #The purpose of turning into a 64-bit float Keep the negative values in the gradient x = cv2.Sobel(img_median,cv2.CV_64F,1,0,ksize = 3) gra = cv2.convertScaleAbs(x) #Gaussian filtering again to remove noise blurred = cv2.GaussianBlur(gra,(9 , 9), 0) # turn binary picture _, = cv2.threshold thresholded (, blurred, 100,255, cv2.THRESH_BINARY) # cross selected nuclear kernel1 = cv2.getStructuringElement (cv2.MORPH_CROSS, (3,3)) # corrosion Swell erode = cv2.erode(thresholded,kernel1,iterations= 1) dilate = cv2.dilate(erode,kernel1,iterations=10) #找轮廓 cnt,_ = cv2.findContours(dilate.copy(),cv2.RETR_LIST,cv2.CHAIN_APPROX_NONE) c = sorted(cnt, key=cv2.contourArea, reverse=True)[0] rect = cv2.minAreaRect(c) Box = np.int0(cv2.boxPoints(rect)) #轮廓校正 x1 = np.max(Box[...,0]) x2 = np.min(Box[...,0]) y1 = np.max(Box[...,1]) y2 = np.min(Box[...,1]) new_box= np.array([[x2,y2],[x2,y1],[x1,y1],[x1,y2]]) #展示效果 Final_img = cv2.drawContours(img.copy(), [new_box], -1, (0, 0, 255), 3) cv2.imshow('License',Final_img) cv2.waitKey(0) cv2.destroyAllWindows() cv2.imwrite('tmp.jpg',Final_img)
Recently, many friends consulted about Python learning issues through private messages. To facilitate communication, click on the blue to join the discussion and answer resource base by yourself