为什么 haarcascades 在 opencv 上不起作用

Question

我正在尝试在 opencv 中检测人脸，但我遇到了一些问题： 1-当我输入以下语法时：gray = cv2.cvtColor(frames,cv2.COLOR_BGR2GRAY)，它显示为红色并且不起作用。 2-haarcascade 也显示为红色：faces = face_cascade.detectMultiScale( gray,scaleFactor=1.1,minNeighbors=5,minSize=(30, 30),flags = cv2.CV_HAAR_SCALE_IMAGE)。我尝试在一些教程中这样做，但它不起作用。你有什么想法吗？ 这是我的代码：

#importing packages
import cv2
import numpy as np

#variables
webcam = cv2.VideoCapture(0)
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
w_size = (700,500)
#turn the webcam on
while (True):
    #reading camera and turing into frames
    ret,frames = webcam.read()
    frames = cv2.resize(frames,w_size)
    #detection
    gray = cv2.cvtColor(frames,cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale( gray,scaleFactor=1.1,minNeighbors=5,minSize=(30, 30),flags = cv2.CV_HAAR_SCALE_IMAGE)
    for (x, y, w, h) in faces:
        cv2.rectangle(frames, (x, y), (x+w, y+h), (0, 255, 0), 2)
    cv2.imshow('face_recognition',frames)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
#running script
webcam.release()
cv2.destroyAllWindows()

Answer 1

我只是：

1. 添加 cv2.data.haarcascades 作为 CascadeClassifier 类型的前缀
2. 已删除cv2.CV_HAAR_SCALE_IMAGE（参数不再使用）

代码：

import cv2
import numpy as np
import cv2.data
#variables
webcam = cv2.VideoCapture(0)

face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades+'haarcascade_frontalface_default.xml')

w_size = (700,500)
#turn the webcam on
while (True):

    #reading camera and turing into frames
    ret,frames = webcam.read()
    frames = cv2.resize(frames,w_size)
    #detection
    gray = cv2.cvtColor(frames,cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale( gray,scaleFactor=1.1,minNeighbors=5,minSize=(30, 30))

    for (x, y, w, h) in faces:
        cv2.rectangle(frames, (x, y), (x+w, y+h), (0, 255, 0), 2)
    cv2.imshow('face_recognition',frames)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
#running script
webcam.release()
cv2.destroyAllWindows()