How to get separate face from image?

Question

I m working on emotion recognize. Current design could recognize one face. However, multiple faces in one image is only recognized in one emotion .

I tried with for loop to get separate face but the code is throwing error. Help me to get separate face for emotion recognize.

face_detection = cv2.CascadeClassifier('haarcascade_files/haarcascade_frontalface_default.xml')
emotion_classifier = load_model('_mini_XCEPTION.102-0.66.hdf5', compile=False)
EMOTIONS = ["angry" ,"disgust","scared", "happy", "sad", "surprised","neutral"]


image = cv2.imread('test.jpg')

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)


faces = face_detection.detectMultiScale(gray,scaleFactor=1.1,minNeighbors=5,minSize=(30,30),flags=cv2.CASCADE_SCALE_IMAGE)

if one face Working fine

if len(faces) == 1:
print(len(faces), "face Length 1")
faces = sorted(faces, reverse=True,
               key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]

(fX, fY, fW, fH) = faces

roi = gray[fY:fY + fH, fX:fX + fW]
roi = cv2.resize(roi, (64, 64))
roi = roi.astype("float") / 255.0
roi = img_to_array(roi)
roi = np.expand_dims(roi, axis=0)
#print(type(roi), "roi", len(roi))

preds = emotion_classifier.predict(roi)[0]
emotion_probability = np.max(preds)
label = EMOTIONS[preds.argmax()]
print(label)

I tried with loop

for xx in (faces):

xx = sorted(0, reverse=True,
              key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
(fX, fY, fW, fH) = xx 

Error

key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
TypeError: 'int' object is not iterable

Answer 1

loop through the faces like this:

for face in faces:
    (fX, fY, fW, fH) = face
    # rest of your code