我正在尝试使用树莓派3和pi摄像头进行人脸识别。
工作环境如下：
Python 2.7.13
Python3 3.5.3
scikit-learn 0.18
numpy 1.12.1
scipy 0.18.1
matplotlib 2.0.0
PIL(Pillow) 4.0.0
keras 2.2.0
theano 1.0.2
当我执行这个程序时，出现了以下错误。在stackoverflow和其他网站上搜索错误后，有一个解决方案是使用'VideoCapture(1)'而不是'VideoCapture(0)',但在我的情况下，它并没有起作用。 然后，当我搜索关于'libpng warning: Image width is zero in IHDR'的错误时，有人建议插入time.sleep()以等待相机启动。我尝试了，但对我来说没有用。
pi@raspberrypi:~/20180717_WebScrb $ python3 face_detection.py
Using Theano backend.
libpng warning: Image width is zero in IHDR
libpng warning: Image height is zero in IHDR
libpng error: Invalid IHDR data
OpenCV Error: Assertion failed (size.width>0 && size.height>0) in imshow, file /home/pi/opencv-3.4.0/modules/highgui/src/window.cpp, line 331
Traceback (most recent call last):
File "face_detection.py", line 75, in <module>
main()
File "face_detection.py", line 63, in main
cv2.imshow("Show FLAME Image", frame)
cv2.error: /home/pi/opencv-3.4.0/modules/highgui/src/window.cpp:331: error: (-215) size.width>0 && size.height>0 in function imshow
以下是Python代码。
import face_keras as face
import sys, os
from keras.preprocessing.image import load_img, img_to_array
import numpy as np
import cv2
import time
cascade_path = "/usr/local/share/OpenCV/haarcascades/haarcascade_frontalface_alt.xml"
#cascade_path = "haarcascade_frontalface_alt.xml"
cascade = cv2.CascadeClassifier(cascade_path)
cam = cv2.VideoCapture(0)
color = (255, 255, 255)
image_size = 32
categories = ["obama", "trump"]
def main():
while(True):
ret, frame = cam.read()
facerect = cascade.detectMultiScale(frame, scaleFactor=1.2, minNeighbors=2, minSize=(10, 10))
cv2.imwrite("frontalface.png", frame)
img = cv2.imread("frontalface.png")
for rect in facerect:
cv2.rectangle(frame, tuple(rect[0:2]),tuple(rect[0:2] + rect[2:4]), color, thickness=2)
x = rect[0]
y = rect[1]
width = rect[2]
height = rect[3]
dst = img[y:y+height, x:x+width]
cv2.imwrite("output.png", dst)
cv2.imread("output.png")
X = []
img = load_img("./output.png", target_size=(image_size,image_size))
in_data = img_to_array(img)
X.append(in_data)
X = np.array(X)
X = X.astype("float") / 256
model = face.build_model(X.shape[1:])
model.load_weights("./image/face-model.h5")
pre = model.predict(X)
print(pre)
if pre[0][0] > 0.9:
print(categories[0])
text = categories[0] + str(pre[0][0]*100) + "%"
font = cv2.FONT_HERSHEY_PLAIN
cv2.putText(frame,text,(rect[0],rect[1]-10),font, 2, color, 2, cv2.LINE_AA)
elif pre[0][1] > 0.9:
print(categories[1])
text = categories[1] + str(pre[0][1]*100) + "%"
font = cv2.FONT_HERSHEY_PLAIN
cv2.putText(frame,text,(rect[0],rect[1]-10),font, 2, color, 2, cv2.LINE_AA)
elif pre[0][2] > 0.9:
print(categories[2])
text = categories[2] + str(pre[0][2]*100) + "%"
font = cv2.FONT_HERSHEY_PLAIN
cv2.putText(frame,text,(rect[0],rect[1]-10),font, 2, color, 2, cv2.LINE_AA)
cv2.imshow("Show FLAME Image", frame)
time.sleep(0.4)
k = cv2.waitKey(1)
if k == ord('q'):
break
cam.release()
cv2.destroyAllWindows()
if __name__ == '__main__':
main()
我认为 'cv2.imwrite("frontalface.png", frame)' 不起作用，因为它在当前文件夹中输出 frontalface.png，但是它是 0 字节（空的）。如果这篇文章与某个人的问题完全相同，我很抱歉。然而，我自己找不到它，所以让我在这里问一个问题。