"检测MultiScale"需要"cv2"。CascadeClassifier' 对象，但收到 'numpy.ndarray'

Question

我是opencv的新手，正在尝试检测图像中的人脸，但是我对这行代码有问题

faces = cv2.CascadeClassifier.detectMultiScale(gray_img, scaleFactor=1.05, minNeighbors=5, minSize=(1,1))

我收到此错误

TypeError: descriptor 'detectMultiScale' requires a 'cv2.CascadeClassifier' object but received a 'numpy.ndarray'

我尝试对此错误进行研究，但是似乎没有什么能告诉我为什么会发生这种情况以及如何解决它。 完整代码

import cv2
img = cv2.imread("C:\Users\Astroid\Desktop\.py pics\pic.jpg")
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faceCascade = cv2.CascadeClassifier('C:\Users\Astroid\AppData\Local\Programs\Python\Python37-32\Lib\site-packages\cv2\data\haarcascade_frontalface_default.xml')
faces = faceCascade.detectMultiScale(
gray_img,
scaleFactor=1.1,
minNeighbors=5,
minSize=(10, 10)
flags=cv2.CASCADE_SCALE_IMAGE
)
print(type(faces))
print(faces)
for x, y, w, h in faces:
img = cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)
cv2.imshow("pic", img)
cv2.waitKey(0)
cv2.destroyAllWindows()

Answer 1

如果我没有错的话，我想你没有在你的代码中提到CascadeClassifier。 例如

# Classifier you want to use
faceCascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
...
...
faces = faceCascade.detectMultiScale(
gray,
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30),
flags=cv2.CASCADE_SCALE_IMAGE
)
...

下面是一个执行的代码：

import cv2
# don't add 1 in arg
img = cv2.imread("your path to the image")
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faceCascade = cv2.CascadeClassifier('your Path to 
haarcascade_frontalface_default.xml')
faces = faceCascade.detectMultiScale(
gray_img,
scaleFactor=1.1,
minNeighbors=5,
minSize=(10, 10)
flags=cv2.CASCADE_SCALE_IMAGE
)
print(type(faces))
print(faces)
for x, y, w, h in faces:
img = cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)
cv2.imshow("pic", img)
cv2.waitKey(0)
cv2.destroyAllWindows()

Answer 2

所以在所有这些之后，我对代码进行了一些调整，老实说我不知道出了什么问题，但这是最终的工作代码。

import cv2
img = cv2.imread("C:\Users\Astroid\Desktop\.py pics\image.png")
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faceCascade =  
cv2.CascadeClassifier('C:\Users\Astroid\AppData\Local\Programs\Python\Python37-32\Lib\site-packages\cv2\data\haarcascade_frontalface_default.xml')
faces = faceCascade.detectMultiScale(
gray_img,
scaleFactor=1.1,
minNeighbors=5,
)
print(type(faces))
print(faces)
for x, y, w, h in faces:
img = cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)
cv2.imshow("image", img)
cv2.waitKey(0)
cv2.destroyAllWindows()