Python OpenCV 实时人脸检测裁剪保存

Question

我对此进行了大量研究，我认为我的逻辑已经过时了，几乎到此为止，但似乎无法理解为什么 cv2.imshow() 窗口中没有显示任何内容只是一个灰色框，但好消息是我能够检测人脸并裁剪该人脸，然后将其保存在文件夹中。

你能不能解释一下我哪里出错了

#Author: Waheed Rafiq
#Research Student Birmingham City University
#Date: 03/11/2016
#Description :detect and Save capture face in a folder.

#Import library required for Capture face.

import cv2


#import the cascade for face detection
FaceClassifier =cv2.CascadeClassifier
('haarcascade_frontalface_default.xml')
# access the webcam (every webcam has 
capture = cv2.VideoCapture(0)

   while(True):
     # Capture frame-by-frame

    ret, frame = capture.read()
    if not capture:
    print "Error opening webcam device"
    sys.exit(1)


    # to detect faces in video
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    faces = FaceClassifier.detectMultiScale(gray, 1.3, 5)

    # Resize Image 
    minisize = (frame.shape[1],frame.shape[0])
    miniframe = cv2.resize(frame, minisize)
    # Store detected frames in variable name faces
   faces =  FaceClassifier.detectMultiScale(miniframe)
   # Draw rectangle 
   for f in faces:
    x, y, w, h = [ v for v in f ]
    cv2.rectangle(frame, (x,y), (x+w,y+h), (255,255,255))
    #Save just the rectangle faces in SubRecFaces
    sub_face = frame[y:y+h, x:x+w]
    FaceFileName = "unknowfaces/face_" + str(y) + ".jpg"
    cv2.imwrite(FaceFileName, sub_face)
    #Display the image 
    cv2.imshow('Result',frame)


    break

    # When everything done, release the capture

    img.release()
    cv2.waitKey(20)
    cv2.destroyAllWindows()

真的很想得到你的支持

Answer 1

我不得不修改我的代码，并再次重新思考逻辑：对于那些希望知道如何使用 Opencv 从网络摄像头或 Raspberry PI 检测人脸然后裁剪检测到的人脸的人，这就是你在 python 2.7 中的做法使用 OpenCV 2.4.12

# croppfacedetection.py
#Author: Waheed Rafiq
#Research Student Birmingham City University
#Date: 03/11/2016
#Description : Save capture face in a folder.

#Import library required for Capture face.
# Should you wish to use this code for 
#education purpose in your assignment or dissertation
# please use the correct citation and give credit where required. 


import cv2
size = 4
webcam = cv2.VideoCapture(0) #Use camera 0

# We load the xml file
classifier = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
#  Above line normalTest
#classifier = cv2.CascadeClassifier('haarcascade_frontalface_alt.xml') 
#Above line test with different calulation
#classifier = cv2.CascadeClassifier('haarcascade_frontalface_alt_tree.xml')
#classifier = cv2.CascadeClassifier('lbpcascade_frontalface.xml')


while True:
    (rval, im) = webcam.read()
    im=cv2.flip(im,1,0) #Flip to act as a mirror

    # Resize the image to speed up detection
    mini = cv2.resize(im, (im.shape[1] / size, im.shape[0] / size))

    # detect MultiScale / faces 
    faces = classifier.detectMultiScale(mini)

    # Draw rectangles around each face
    for f in faces:
        (x, y, w, h) = [v * size for v in f] #Scale the shapesize backup
        cv2.rectangle(im, (x, y), (x + w, y + h),(0,255,0),thickness=4)
        #Save just the rectangle faces in SubRecFaces
        sub_face = im[y:y+h, x:x+w]
        FaceFileName = "unknowfaces/face_" + str(y) + ".jpg"
        cv2.imwrite(FaceFileName, sub_face)

    # Show the image
    cv2.imshow('BCU Research by Waheed Rafiq (c)',   im)
    key = cv2.waitKey(10)
    # if Esc key is press then break out of the loop 
    if key == 27: #The Esc key
    break

请记住，您将需要创建一个文件夹，在该区域内您将需要一个名为 unknownfaces 的文件夹，从该文件夹的根目录运行脚本，它将检测到的任何人脸保存到 unknowfaces 文件夹中。有关此代码的更多信息将很快可用我的网站
waheedrafiq.net