"""Performs face alignment and calculates L2 distance between the embeddings of images.""" # MIT License # # Copyright (c) 2016 David Sandberg # # Permission is hereby granted, free of charge, to any person obtaining a copy # of this software and associated documentation files (the "Software"), to deal # in the Software without restriction, including without limitation the rights # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell # copies of the Software, and to permit persons to whom the Software is # furnished to do so, subject to the following conditions: # # The above copyright notice and this permission notice shall be included in all # copies or substantial portions of the Software. # # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE # SOFTWARE. from __future__ import absolute_import from __future__ import division from __future__ import print_function from scipy import misc import tensorflow as tf import numpy as np import sys import os import argparse import facenet import align.detect_face def main(): model = "../models/20170216-091149" image_files = ['compare_images/index10.png', 'compare_images/index73.png'] image_size = 160 margin = 44 gpu_memory_fraction = 0.5 images = load_and_align_data(image_files, image_size, margin, gpu_memory_fraction) with tf.Graph().as_default(): with tf.Session() as sess: # Load the model facenet.load_model(model) # Get input and output tensors 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") # Run forward pass to calculate embeddings feed_dict = { images_placeholder: images, phase_train_placeholder:False } emb = sess.run(embeddings, feed_dict=feed_dict) nrof_images = len(image_files) print('Images:') for i in range(nrof_images): print('%1d: %s' % (i, image_files[i])) print('') # Print distance matrix print('Distance matrix') print(' ', end='') for i in range(nrof_images): print(' %1d ' % i, end='') print('') for i in range(nrof_images): print('%1d ' % i, end='') for j in range(nrof_images): dist = np.sqrt(np.sum(np.square(np.subtract(emb[i,:], emb[j,:])))) print(' %1.4f ' % dist, end='') print('') def load_and_align_data(image_paths, image_size, margin, gpu_memory_fraction): minsize = 20 # minimum size of face threshold = [ 0.6, 0.7, 0.7 ] # three steps's threshold factor = 0.709 # scale factor print('Creating networks and loading parameters') with tf.Graph().as_default(): gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction) sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False)) with sess.as_default(): pnet, rnet, onet = align.detect_face.create_mtcnn(sess, None) nrof_samples = len(image_paths) img_list = [None] * nrof_samples for i in range(nrof_samples): img = misc.imread(os.path.expanduser(image_paths[i])) img_size = np.asarray(img.shape)[0:2] bounding_boxes, _ = align.detect_face.detect_face(img, minsize, pnet, rnet, onet, threshold, factor) det = np.squeeze(bounding_boxes[0,0:4]) bb = np.zeros(4, dtype=np.int32) bb[0] = np.maximum(det[0]-margin/2, 0) bb[1] = np.maximum(det[1]-margin/2, 0) bb[2] = np.minimum(det[2]+margin/2, img_size[1]) bb[3] = np.minimum(det[3]+margin/2, img_size[0]) cropped = img[bb[1]:bb[3],bb[0]:bb[2],:] aligned = misc.imresize(cropped, (image_size, image_size), interp='bilinear') prewhitened = facenet.prewhiten(aligned) img_list[i] = prewhitened images = np.stack(img_list) return images # def parse_arguments(argv): # parser = argparse.ArgumentParser() # # parser.add_argument('model', type=str, default="./models/20170216-091149", # help='Could be either a directory containing the meta_file and ckpt_file or a model protobuf (.pb) file') # parser.add_argument('image_files', type=str, default="src/compare_images/index10.png src/compare_images/index73.png " # , nargs='+', help='Images to compare') # parser.add_argument('--image_size', type=int, # help='Image size (height, width) in pixels.', default=160) # parser.add_argument('--margin', type=int, # help='Margin for the crop around the bounding box (height, width) in pixels.', default=44) # parser.add_argument('--gpu_memory_fraction', type=float, # help='Upper bound on the amount of GPU memory that will be used by the process.', default=0.5) # return parser.parse_args(argv) if __name__ == '__main__': main()
"""Validate a face recognizer on the "Labeled Faces in the Wild" dataset (http://vis-www.cs.umass.edu/lfw/). Embeddings are calculated using the pairs from http://vis-www.cs.umass.edu/lfw/pairs.txt and the ROC curve is calculated and plotted. Both the model metagraph and the model parameters need to exist in the same directory, and the metagraph should have the extension '.meta'. """ # MIT License # # Copyright (c) 2016 David Sandberg # # Permission is hereby granted, free of charge, to any person obtaining a copy # of this software and associated documentation files (the "Software"), to deal # in the Software without restriction, including without limitation the rights # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell # copies of the Software, and to permit persons to whom the Software is # furnished to do so, subject to the following conditions: # # The above copyright notice and this permission notice shall be included in all # copies or substantial portions of the Software. # # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE # SOFTWARE. from __future__ import absolute_import from __future__ import division from __future__ import print_function import tensorflow as tf import numpy as np import argparse import facenet import lfw import os import sys import math from sklearn import metrics from scipy.optimize import brentq from scipy import interpolate import numpy from PIL import Image,ImageDraw import cv2 from scipy import misc import argparse import align.detect_face def detetet_face_init(): cap = cv2.VideoCapture(0) print(cap.isOpened()) classifier=cv2.CascadeClassifier("./xml/haarcascade_frontalface_alt.xml") count=0 return cap,classifier,count def detect_face_clear(): cap.release() cv2.destroyAllWindows() def load_and_align_data(image_paths, image_size, margin, gpu_memory_fraction): minsize = 20 # minimum size of face threshold = [ 0.6, 0.7, 0.7 ] # three steps's threshold factor = 0.709 # scale factor print('Creating networks and loading parameters') with tf.Graph().as_default(): gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction) sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False)) with sess.as_default(): pnet, rnet, onet = align.detect_face.create_mtcnn(sess, None) nrof_samples = len(image_paths) img_list = [None] * nrof_samples for i in range(nrof_samples): img = misc.imread(os.path.expanduser(image_paths[i])) img_size = np.asarray(img.shape)[0:2] bounding_boxes, _ = align.detect_face.detect_face(img, minsize, pnet, rnet, onet, threshold, factor) det = np.squeeze(bounding_boxes[0,0:4]) bb = np.zeros(4, dtype=np.int32) bb[0] = np.maximum(det[0]-margin/2, 0) bb[1] = np.maximum(det[1]-margin/2, 0) bb[2] = np.minimum(det[2]+margin/2, img_size[1]) bb[3] = np.minimum(det[3]+margin/2, img_size[0]) cropped = img[bb[1]:bb[3],bb[0]:bb[2],:] aligned = misc.imresize(cropped, (image_size, image_size), interp='bilinear') prewhitened = facenet.prewhiten(aligned) img_list[i] = prewhitened images = np.stack(img_list) return images def compare_facevec(facevec1, facevec2): dist = np.sqrt(np.sum(np.square(np.subtract(facevec1, facevec2)))) #print(' %1.4f ' % dist, end='') return dist def face_recognition_using_facenet(): cap,classifier,count = detetet_face_init() model = "../models/20170216-091149" image_files = ['compare_images/index10.png', 'compare_images/index73.png'] image_size = 160 margin = 44 gpu_memory_fraction = 0.5 with tf.Graph().as_default(): with tf.Session() as sess: # Load the model facenet.load_model(model) # Get input and output tensors 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") #image_size = images_placeholder.get_shape()[1] # For some reason this doesn't work for frozen graphs image_size = 160 embedding_size = embeddings.get_shape()[1] index = 0 th = 0.7 face_recognition_tag = True color = (0,255,0) exist_face_vec = [] face_detect_vec = [] while count > -1: ret,img = cap.read() faceRects = classifier.detectMultiScale(img, 1.2, 2, cv2.CASCADE_SCALE_IMAGE,(20,20)) if len(faceRects)>0: for faceRect in faceRects: x, y, w, h = faceRect #cv2.rectangle(img, (int(x), int(y)), (int(x)+int(w), int(y)+int(h)), (0,255,0), 2,0) #print "save faceimg" face_win = img[int(y):int(y) + int(h), int(x):int(x) + int(w)] face_detect = cv2.resize(face_win,(image_size,image_size),interpolation=cv2.INTER_CUBIC) #cv2.imwrite('faceimg/index' + str(index) + '.bmp', face_win) # Run forward pass to calculate embeddings #print('Runnning forward pass on face detect') nrof_samples = 1 img_list = [None] * nrof_samples prewhitened = facenet.prewhiten(face_detect) img_list[0] = prewhitened images = np.stack(img_list) if index == 10: feed_dict = {images_placeholder:images, phase_train_placeholder:False } exist_face_vec = sess.run(embeddings, feed_dict=feed_dict) elif index > 10 and index % 10 == 0: feed_dict = {images_placeholder:images, phase_train_placeholder:False } face_detect_vec = sess.run(embeddings, feed_dict=feed_dict) cp = compare_facevec(face_detect_vec, exist_face_vec) print("index ", index, " dist ", cp) if cp < th: print(True) face_recognition_tag = True else: print(False) face_recognition_tag = False index +=1 # if face_recognition_tag == True: # cv2.rectangle(img, (int(x), int(y)), (int(x)+int(w), int(y)+int(h)), (255,0,0), 2,0) # else: # cv2.rectangle(img, (int(x), int(y)), (int(x)+int(w), int(y)+int(h)), (0,255,0), 2,0) cv2.rectangle(img, (int(x), int(y)), (int(x)+int(w), int(y)+int(h)), (0,255,0), 2,0) cv2.imshow('video',img) key=cv2.waitKey(1) if key==ord('q'): break detect_face_clear(cap) if __name__ == '__main__': face_recognition_using_facenet()