使用opencv和python上的黑色png进行Alpha混合

Question

我正在尝试使用opencv创建一个与我脸上的玻璃重叠的应用程序。但是，当视频出现时，眼镜在alpha层上有黑色。这是我的代码：

video_capture = cv2.VideoCapture(0)
anterior = 0
glasses = cv2.imread('Glasses_1.png')

def put_glasses(glasses,fc,x,y,w,h):

    face_width = w
    face_height = h

    glasses_width = int(face_width)
    glasses_height = int(face_height*0.32857)



    glasses = cv2.resize(glasses,(glasses_width,glasses_height))

    for i in range(glasses_height):
        for j in range(glasses_width):
            for k in range(3):
                if glasses[i][j][k]<235:

                    fc[y+i-int(-0.25*face_height)-1][x+j][k] = glasses[i][j][k]
    return fc

while True:
    if not video_capture.isOpened():
        print('Unable to load camera.')
        sleep(5)
        pass
    ret, frame = video_capture.read()
    if ret is True:
        gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    else:
        continue

    faces = faceCascade.detectMultiScale(
        gray,
        scaleFactor=1.1,
        minNeighbors=5,
        minSize=(40,40)
    )
    for (x, y, w, h) in faces:
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
        cv2.putText(frame,"Person Detected",(x,y),cv2.FONT_HERSHEY_SIMPLEX,1,(0,0,255),2)
        frame = put_glasses(glasses, frame, x, y, w, h)

如果有人能提供帮助，我将非常感激。

Answer 1

您以bgr格式读取了png，而不是bgra或未更改的格式。然后，我不认为程序中的玻璃图像是(h,w,4)的形状。您应该阅读国旗cv2.IMREAD_UNCHANGED。

glasses = cv2.imread("xxx.png", cv2.IMREAD_UNCHANGED)

也许这个链接会有所帮助。 How do I clear a white background in OpenCV with c++?

bgra worm：

混合：