Python + OpenCV:cv2.imwrite

时间:2013-12-06 13:59:03

标签: python opencv python-2.7 numpy

我正在尝试检测一张脸并在一个单独的文件中记下脸部区域。 我该怎么做?我认为我必须使用“faces”(你可以在代码中看到这个var)。但是如何?

from ffnet import mlgraph, ffnet, tmlgraph, imlgraph
import pylab
import sys
import cv,cv2
import numpy
cascade = cv.Load('C:\opencv\data\haarcascades\haarcascade_frontalface_alt.xml')


def detect(image):
 bitmap = cv.fromarray(image)
 faces = cv.HaarDetectObjects(bitmap, cascade, cv.CreateMemStorage(0))
 if faces:
  for (x,y,w,h),n in faces:  
   cv2.rectangle(image,(x,y),(x+w,y+h),(255,255,255),3)
 return image

if __name__ == "__main__":
    cam = cv2.VideoCapture(0)
    while 1:
        _,frame =cam.read()
        frame = numpy.asarray(detect(frame))
        cv2.imshow("features", frame)
        if cv2.waitKey(1) == 0x1b: # ESC
            print 'ESC pressed. Exiting ...'
            break

3 个答案:

答案 0 :(得分:29)

以下代码应提取图像中的面部并将面部保存在磁盘上

def detect(image):
 image_faces = []
 bitmap = cv.fromarray(image)
 faces = cv.HaarDetectObjects(bitmap, cascade, cv.CreateMemStorage(0))
 if faces:
  for (x,y,w,h),n in faces:
   image_faces.append(image[y:(y+h), x:(x+w)])
   #cv2.rectangle(image,(x,y),(x+w,y+h),(255,255,255),3)
 return image_faces

if __name__ == "__main__":
    cam = cv2.VideoCapture(0)
    while 1:
        _,frame =cam.read()
        image_faces = []
        image_faces = detect(frame)
        for i, face in enumerate(image_faces):
           cv2.imwrite("face-" + str(i) + ".jpg", face)

        #cv2.imshow("features", frame)
        if cv2.waitKey(1) == 0x1b: # ESC
            print 'ESC pressed. Exiting ...'
            break

答案 1 :(得分:1)

enter image description here enter image description here enter image description here

或者,借助MTCNN和OpenCV(还需要包括TensorFlow的其他依赖项),您可以:

1 执行面部检测(输入图像,输出检测到的面部的所有框):

from mtcnn.mtcnn import MTCNN
import cv2

face_detector = MTCNN()

img = cv2.imread("Anthony_Hopkins_0001.jpg")
detect_boxes = face_detector.detect_faces(img)
print(detect_boxes)
  

[{'box':[73,69,98,123],'confidence':0.9996458292007446,'keypoints':{'left_eye':(102,116),'right_eye':(150,114), 'nose':(129,142),'mouth_left':(112,168),'mouth_right':(146,167)}}]

2 将所有检测到的脸部保存到单独的文件中

for i in range(len(detect_boxes)):
    face_img = img[detect_boxes[i]["box"][1]:detect_boxes[i]["box"][1] + detect_boxes[i]["box"][3], detect_boxes[i]["box"][0]:detect_boxes[i]["box"][0] + detect_boxes[i]["box"][2]]
    cv2.imwrite("face-%.3d.jpg" % (i+1), face_img)

3或绘制矩形:检测到的所有脸部

for box in detect_boxes:
    pt1 = (box["box"][0], box["box"][1]) # top left
    pt2 = (box["box"][0] + box["box"][2], box["box"][1] + box["box"][3]) # bottom right
    cv2.rectangle(img, pt1, pt2, (0,255,0), 2)
cv2.imwrite("detected-boxes.jpg", img)

答案 2 :(得分:0)

wtluo,太好了! 我可以对您的代码2进行一点修改吗?在这里:

for i, detected_box in enumerate(detect_boxes):
    box = detected_box["box"]
    face_img = img[ box[1]:box[1] + box[3], box[0]:box[0] + box[2] ]
    cv2.imwrite("face-{:03d}.jpg".format(i+1), face_img)