无法一次检测多个人脸

Posted 2023-03-16

【中文标题】无法一次检测多个人脸

【英文标题】：Unable to detect multiple faces at a time

【发布时间】：2019-05-23 03:01:14

【问题描述】：

由于某种原因，我无法一次检测到多张面孔。它一次只检测一张脸。我该如何解决这个问题？我在下面添加了代码。我使用谷歌的 facenet 进行实时人脸识别。

在视频输出中，它一次只在一个面上创建一个边界框。但在控制台输出中，它可以计算出存在的面数是两个或两个以上。

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import tensorflow as tf
from scipy import misc
import cv2
import matplotlib.pyplot as plt
import numpy as np
import argparse
import facenet
import detect_face
import os
from os.path import join as pjoin
import sys
import time
import copy
import math
import pickle
from sklearn.svm import SVC
from sklearn.externals import joblib

#addded
#import reload
#reload(sys)
#sys.setdefaultencoding('utf8')

print('Creating networks and loading parameters')
with tf.Graph().as_default():
    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.6)
    sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, 
 log_device_placement=False))
    with sess.as_default():
    pnet, rnet, onet = detect_face.create_mtcnn(sess, './') #face detection

    minsize = 20  # minimum size of face                    #minsize, threshold, factor used for detection
    threshold = [0.6, 0.7, 0.7]  # three steps's threshold
    factor = 0.709  # scale factor
    margin = 44
    frame_interval = 3
    batch_size = 1000
    image_size = 182
    input_image_size = 160


    items = os.listdir("/Aryabhatta Robotics Internship/facenet-master/Real_time_face/ids/aligned")
    #HumanNames = []
    #for names in items:
        #HumanNames.append(names)
    #print(HumanNames)
    #HumanNames = ['Alok','Siddhant','tesra','s01','s02','s03','s04','s05','s06','s07','s08','s09','s10','s11','s12','s13','s14','s15','s16','s17','s18','s19','s20']    #train human name, known face names

    print('Loading feature extraction model')
    modeldir = '/Aryabhatta Robotics Internship/facenet-master/Real_time_face/models/20180402-114759/20180402-114759.pb' #feature extraction mmodel
    facenet.load_model(modeldir)

    images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
    embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
    phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
    embedding_size = embeddings.get_shape()[1]

    classifier_filename = '/Aryabhatta Robotics Internship/facenet-master/Real_time_face/models/my_classifier/my_classifier.pkl' #out own classifier
    classifier_filename_exp = os.path.expanduser(classifier_filename)
    with open(classifier_filename_exp, 'rb') as infile:
        (model, class_names) = pickle.load(infile)#, encoding='latin1')
        print('load classifier file-> %s' % classifier_filename_exp)

    video_capture = cv2.VideoCapture(0)
    c = 0

    # #video writer
    # fourcc = cv2.VideoWriter_fourcc(*'DIVX')
    # out = cv2.VideoWriter('3F_0726.avi', fourcc, fps=30, frameSize=(640,480))

    print('Start Recognition!')
    prevTime = 0
    while True: #infinite loop
        ret, frame = video_capture.read() #video capture from webcam

        frame = cv2.resize(frame, (0,0), fx=0.5, fy=0.5)    #resize frame (optional)

        curTime = time.time()    # calc fps
        timeF = frame_interval

        if (c % timeF == 0):
            find_results = []

            if frame.ndim == 2:
                frame = facenet.to_rgb(frame)
            frame = frame[:, :, 0:3]
            bounding_boxes, _ = detect_face.detect_face(frame, minsize, pnet, rnet, onet, threshold, factor)
            nrof_faces = bounding_boxes.shape[0]
            print('Detected_FaceNum: %d' % nrof_faces)

            if nrof_faces > 0:
                det = bounding_boxes[:, 0:4]
                img_size = np.asarray(frame.shape)[0:2]

                cropped = []
                scaled = []
                scaled_reshape = []
                bb = np.zeros((nrof_faces,4), dtype=np.int32)

                for i in range(nrof_faces):
                    print("faceno:" + str(i))
                    emb_array = np.zeros((1, embedding_size))

                    bb[i][0] = det[i][0]
                    bb[i][1] = det[i][1]
                    bb[i][2] = det[i][2]
                    bb[i][3] = det[i][3]

                    # inner exception
                    if bb[i][0] <= 0 or bb[i][1] <= 0 or bb[i][2] >= len(frame[0]) or bb[i][3] >= len(frame):
                        print('face is inner of range!')
                        continue

                    cropped.append(frame[bb[i][1]:bb[i][3], bb[i][0]:bb[i][2], :])
                    cropped[0] = facenet.flip(cropped[0], False)
                    scaled.append(misc.imresize(cropped[0], (image_size, image_size), interp='bilinear'))
                    scaled[0] = cv2.resize(scaled[0], (input_image_size,input_image_size),
                                           interpolation=cv2.INTER_CUBIC)
                    scaled[0] = facenet.prewhiten(scaled[0])
                    scaled_reshape.append(scaled[0].reshape(-1,input_image_size,input_image_size,3))
                    feed_dict = images_placeholder: scaled_reshape[0], phase_train_placeholder: False
                    emb_array[0, :] = sess.run(embeddings, feed_dict=feed_dict)
                    #print(emb_array)


                    threshold_accuracy = 155
                    predictions = model.predict_proba(emb_array)
                    #print(predictions)

                    for i in range(len(predictions[0])):
                        predictions[0][i] = np.exp(18*predictions[0][i])
                        #print(predictions)

                    best_class_indices = np.argmax(predictions, axis=1)
                    print(best_class_indices)
                    print("next")
                    best_class_probabilities = predictions[np.arange(len(best_class_indices)), best_class_indices]
                    print(best_class_probabilities)
                    for i in range(len(best_class_indices)):
                        print('%4d  %s: %.3f' % (i, class_names[best_class_indices[i]], best_class_probabilities[i]))


                    cv2.rectangle(frame, (bb[i][0], bb[i][1]), (bb[i][2], bb[i][3]), (0, 255, 0), 2) #boxing face

                        #plot result idx under box
                    text_x = bb[i][0]
                    text_y = bb[i][3] + 20
                    # print('result: ', best_class_indices[0])

                    if best_class_probabilities[i] > threshold_accuracy :
                                    #result_names = HumanNames[best_class_indices[0]]
                        cv2.putText(frame, class_names[best_class_indices[i]], (text_x, text_y), cv2.FONT_HERSHEY_COMPLEX_SMALL,
                                    1, (0, 0, 255), thickness=1, lineType=2)
                    else:
                        cv2.putText(frame, 'Unknown', (text_x, text_y), cv2.FONT_HERSHEY_COMPLEX_SMALL,
                                    1, (0, 0, 255), thickness=1, lineType=2)

                    #for H_i in HumanNames:
                        #if HumanNames[best_class_indices[0]] == H_i and best_class_probabilities[0] > threshold_accuracy :
                            #flag = 1
                            #result_names = HumanNames[best_class_indices[0]]
                            #cv2.putText(frame, result_names, (text_x, text_y), cv2.FONT_HERSHEY_COMPLEX_SMALL,
                                        #1, (0, 0, 255), thickness=1, lineType=2)


                        #else:
                            #cv2.putText(frame, 'Unknown', (text_x, text_y), cv2.FONT_HERSHEY_COMPLEX_SMALL,
                                       # 1, (0, 0, 255), thickness=1, lineType=2)
            else:
                print('Unable to align')

        sec = curTime - prevTime
        prevTime = curTime
        fps = 1 / (sec)
        str1 = 'FPS: %2.3f' % fps
        text_fps_x = len(frame[0]) - 150
        text_fps_y = 20
        cv2.putText(frame, str1, (text_fps_x, text_fps_y),
                        cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 0), thickness=1, lineType=2)
        # c+=1
        cv2.imshow('Video', frame)

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    video_capture.release()
    # #video writer
    # out.release()
    cv2.destroyAllWindows()

【参考方案1】：

阈值精度应在0 to 1 之间。确保您的阈值准确度必须为>0.60。

【参考方案2】：

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
from scipy import misc
from skimage.transform import resize
import cv2
import numpy as np
import facenet
import detect_face
import os
import time
import pickle
import sys

img_path='download.jpeg'
modeldir = './model/20170511-185253.pb'
classifier_filename = './class/classifier.pkl'
npy='./npy'
train_img="./train_img"

with tf.Graph().as_default():
    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.6)
    sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
    with sess.as_default():
        pnet, rnet, onet = detect_face.create_mtcnn(sess, npy)

        minsize = 10  # minimum size of face
        threshold = [0.6, 0.7, 0.7]  # three steps's threshold
        factor = 1   # scale factor
        margin = 44
        frame_interval = 3
        batch_size = 1000
        image_size = 182
        input_image_size = 160
        
        HumanNames = os.listdir(train_img)
        HumanNames.sort()

        print('Loading feature extraction model')
        facenet.load_model(modeldir)

        images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
        embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
        phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
        embedding_size = embeddings.get_shape()[1]


        classifier_filename_exp = os.path.expanduser(classifier_filename)
        with open(classifier_filename_exp, 'rb') as infile:
            (model, class_names) = pickle.load(infile)

        # video_capture = cv2.VideoCapture("akshay_mov.mp4")
        c = 0


        print('Start Recognition!')
        prevTime = 0
        # ret, frame = video_capture.read()
        frame = cv2.imread(img_path,0)

        frame = cv2.resize(frame, (0,0), fx=0.5, fy=0.5)    #resize frame (optional)

        curTime = time.time()+1    # calc fps
        timeF = frame_interval

        if (c % timeF == 0):
            find_results = []

            if frame.ndim == 2:
                frame = facenet.to_rgb(frame)
            frame = frame[:, :, 0:3]
            print(1)
            bounding_boxes, _ = detect_face.detect_face(frame, minsize, pnet, rnet, onet, threshold, factor)
            nrof_faces = bounding_boxes.shape[0]
            print('Face Detected: %d' % nrof_faces)

            if nrof_faces > 0:
                det = bounding_boxes[:, 0:4]
                img_size = np.asarray(frame.shape)[0:2]

                cropped = []
                scaled = []
                scaled_reshape = []
                bb = np.zeros((nrof_faces,4), dtype=np.int32)

                for i in range(nrof_faces):
                    emb_array = np.zeros((1, embedding_size))

                    bb[i][0] = det[i][0]
                    bb[i][1] = det[i][1]
                    bb[i][2] = det[i][2]
                    bb[i][3] = det[i][3]

                    # inner exception
                    if bb[i][0] <= 0 or bb[i][1] <= 0 or bb[i][2] >= len(frame[0]) or bb[i][3] >= len(frame):
                        print('face is too close')
                        continue

                    cropped.append(frame[bb[i][1]:bb[i][3], bb[i][0]:bb[i][2], :])
                    cropped[i] = facenet.flip(cropped[i], False)
                    scaled.append(resize(cropped[i], (image_size, image_size), anti_aliasing=True))
                    scaled[i] = cv2.resize(scaled[i], (input_image_size,input_image_size),
                                           interpolation=cv2.INTER_CUBIC)
                    scaled[i] = facenet.prewhiten(scaled[i])
                    scaled_reshape.append(scaled[i].reshape(-1,input_image_size,input_image_size,3))
                    feed_dict = images_placeholder: scaled_reshape[i], phase_train_placeholder: False
                    emb_array[0, :] = sess.run(embeddings, feed_dict=feed_dict)
                    predictions = model.predict_proba(emb_array)
                    print(predictions)
                    best_class_indices = np.argmax(predictions, axis=1)
                    # print(best_class_indices)
                    best_class_probabilities = predictions[np.arange(len(best_class_indices)), best_class_indices]
                    print(best_class_probabilities)
                    cv2.rectangle(frame, (bb[i][0], bb[i][1]), (bb[i][2], bb[i][3]), (0, 255, 0), 2)    #boxing face

                    #plot result idx under box
                    text_x = bb[i][0]
                    text_y = bb[i][3] + 20
                    print('Result Indices: ', best_class_indices[0])
                    print(HumanNames)
                    for H_i in HumanNames:
                        # print(H_i)
                        if HumanNames[best_class_indices[0]] == H_i:
                            result_names = HumanNames[best_class_indices[0]]
                            
            else:
                print('Unable to align')
        cv2.imshow('Image', frame)

        if cv2.waitKey(100) & 0xFF == ord('q'):
            sys.exit("Thanks")
        cv2.destroyAllWindows()

【讨论】：

您能解释一下您的解决方案吗？