openCV python根据边缘问题查找轮廓

Question

我想检测车号！

看到这张照片

---

使用此代码：

import numpy as np
import imutils
import cv2

# Read the image file
image = cv2.imread('Car_Image_1.jpg')

# Resize the image - change width to 500
image = imutils.resize(image, width=500)

# Display the original image
cv2.imshow("Original Image", image)

# RGB to Gray scale conversion
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv2.imshow("1 - Grayscale Conversion", gray)

# Noise removal with iterative bilateral filter(removes noise while preserving edges)
gray = cv2.bilateralFilter(gray, 11, 17, 17)
cv2.imshow("2 - Bilateral Filter", gray)

# Find Edges of the grayscale image
edged = cv2.Canny(gray, 170, 200)
cv2.imshow("4 - Canny Edges", edged)

# Find contours based on Edges
(new, cnts , _) = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
# sort contours based on their area keeping minimum required area as '30' (anything smaller than this will not be considered)
cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:30]
# we currently have no Number plate contour
NumberPlateCnt = None

# loop over our contours to find the best possible approximate contour of number plate
count = 0
for c in cnts:
        peri = cv2.arcLength(c, True)
        approx = cv2.approxPolyDP(c, 0.02 * peri, True)
        if len(approx) == 4:  # Select the contour with 4 corners
            NumberPlateCnt = approx #This is our approx Number Plate Contour
            break

# Drawing the selected contour on the original image
cv2.drawContours(image, [NumberPlateCnt], -1, (0,255,0), 3)
cv2.imshow("Final Image With Number Plate Detected", image)

cv2.waitKey(0) #Wait for user input before closing the images displayed

但是当我运行代码时，出现此错误：

C:\Python27\python.exe C:/Users/Crypt/PycharmProjects/MyDetector/CarPlateDetection.py
Traceback (most recent call last):
  File "C:/Users/Crypt/PycharmProjects/MyDetector/CarPlateDetection.py", line 27, in <module>
    (new, cnts , _) = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
ValueError: need more than 2 values to unpack

Process finished with exit code 1

我更改此行代码

(new, cnts , _) = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)

到

(new, cnts) = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)

然后运行，错误是：

C:\Python27\python.exe C:/Users/Crypt/PycharmProjects/MyDetector/CarPlateDetection.py
Traceback (most recent call last):
  File "C:/Users/Crypt/PycharmProjects/MyDetector/CarPlateDetection.py", line 29, in <module>
    cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:30]
cv2.error: OpenCV(4.0.0) C:\projects\opencv-python\opencv\modules\imgproc\src\shapedescr.cpp:272: error: (-215:Assertion failed) npoints >= 0 && (depth == CV_32F || depth == CV_32S) in function 'cv::contourArea'

以退出代码1完成的过程

这是github上的代码：

https://github.com/Aqsa-K/Car-Number-Plate-Detection-OpenCV-Python

Answer 1

从OpenCV4，findContours返回2个值contours和hierachy，因此，轮廓在代码中的new中。应该是

cnts, hier = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)