def recognize(self, draw):
#-----------------------------------------------#
# 人脸识别
# 先定位，再进行数据库匹配
#-----------------------------------------------#
height, width, _ = np.shape(draw)
draw_rgb = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
# 检测人脸
rectangles = self.mtcnn_model.detectFace(draw_rgb, self.threshold)
if len(rectangles) == 0:
return
# 转化成正方形
rectangles = utils.rect2square(np.array(rectangles, dtype=np.int32))
rectangles[:, 0] = np.clip(rectangles[:, 0], 0, width)
rectangles[:, 1] = np.clip(rectangles[:, 1], 0, height)
rectangles[:, 2] = np.clip(rectangles[:, 2], 0, width)
rectangles[:, 3] = np.clip(rectangles[:, 3], 0, height)
#-----------------------------------------------#
# 对检测到的人脸进行编码
#-----------------------------------------------#
face_encodings = []
for rectangle in rectangles:
landmark = (np.reshape(rectangle[5:15], (5, 2)) - np.array(
[int(rectangle[0]), int(rectangle[1])])) / (rectangle[3] -
rectangle[1]) * 160
crop_img = draw_rgb[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img, (160, 160))
new_img, _ = utils.Alignment_1(crop_img, landmark)
new_img = (new_img.reshape(1, 160, 160, 3))
new_img = np.array(new_img) / 255.0
pred = model.predict(new_img)
face_encoding = np.argmax(pred, axis=1)
face_encodings.append(face_encoding)
rectangles = rectangles[:, 0:4]
glasses_list = ('Glasses', 'No_glasses')
face_names = []
for i in face_encodings:
glasses_list = glasses_list[int(face_encoding)]
face_names.append(glasses_list)
#-----------------------------------------------#
# 画框~!~
#-----------------------------------------------#
for (left, top, right, bottom), name in zip(rectangles, face_names):
cv2.rectangle(draw, (left, top), (right, bottom), (0, 0, 255), 2)
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(draw, name, (left, bottom - 15), font, 0.75,
(255, 255, 255), 2)
return draw
def __init__(self):
# 创建mtcnn对象用于检测图片中的人脸
self.mtcnn_model = mtcnn()
# 门限函数
self.threshold = [0.5, 0.8, 0.9]
# 载入facenet用于将检测到的人脸转化为128维的向量
self.facenet_model = InceptionResNetV1()
# model.summary() #模型summary信息
model_path = './model_data/facenet_keras.h5' # 模型文件
self.facenet_model.load_weights(model_path)
#-----------------------------------------------#
# 对数据库中的人脸进行编码
# known_face_encodings中存储的是编码后的人脸
# known_face_names为人脸的名字
# face_dataset文件中的图片为人脸数据库
#-----------------------------------------------#
face_list = os.listdir("face_dataset") # 列出文件夹中的人脸图片
self.known_face_encodings = [] # 存储编码后的人脸
self.known_face_names = [] # 人脸的名字及图片的名字
# 遍历人脸
for face in face_list:
# 图片文件名
name = face.split(".")[0]
# 读取图片是BGR格式数据
img = cv2.imread("./face_dataset/" + face)
# 颜色空间转换
# cv2.COLOR_BGR2RGB 将BGR格式转换成RGB格式
# cv2.COLOR_BGR2GRAY 将BGR格式转换成灰度图片
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# 检测图版中的人脸
rectangles = self.mtcnn_model.detectFace(img, self.threshold)
# 长方形转化成正方形
rectangles = utils.rect2square(np.array(rectangles))
# facenet要传入一个160x160的图片
rectangle = rectangles[0]
# 记下他们的landmark
landmark = (np.reshape(rectangle[5:15], (5, 2)) - np.array(
[int(rectangle[0]), int(rectangle[1])])) / (rectangle[3] -
rectangle[1]) * 160
crop_img = img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
# Resize to 160x160
crop_img = cv2.resize(crop_img, (160, 160))
new_img, _ = utils.Alignment_1(crop_img, landmark)
new_img = np.expand_dims(new_img, 0)
# 将检测到的人脸传入到facenet的模型中，实现128维特征向量的提取
face_encoding = utils.calc_128_vec(self.facenet_model, new_img)
# print(face_encoding)
# 记录128维护特征向量到数组
self.known_face_encodings.append(face_encoding)
# 记录文件名到数组
self.known_face_names.append(name)
def __init__(self):
# 创建mtcnn对象，建立一个mtcnn模型
# 检测图片中的人脸
self.mtcnn_model = mtcnn()
# 门限函数
self.threshold = [0.5, 0.8, 0.9]
# 载入facenet模型
# 将检测到的人脸转化为128维的向量
self.facenet_model = InceptionResNetV1()
# model.summary()
model_path = './model_data/facenet_keras.h5'
self.facenet_model.load_weights(model_path)
#-----------------------------------------------#
# 对数据库中的人脸进行编码
# known_face_encodings中存储的是编码后的人脸
# known_face_names为人脸的名字
#-----------------------------------------------#
face_list = os.listdir("face_dataset")
self.known_face_encodings = []
self.known_face_names = []
# 所有的人脸进行遍历，得到仓库里所有人脸的128维特征向量和对应名称
for face in face_list:
# obama.jpg进行'.'分割，取前一段字符串
name = face.split(".")[0]
# 人脸读取出来
img = cv2.imread("./face_dataset/" + face)
# 图像由 BGR -> RGB
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# 检测人脸
rectangles = self.mtcnn_model.detectFace(img, self.threshold)
# 转化成正方形
rectangles = utils.rect2square(np.array(rectangles))
# facenet要传入一个160x160的图片
# 进行读取
rectangle = rectangles[0]
# 记下他们的landmark，5个标记点，进行人脸对齐
landmark = (np.reshape(rectangle[5:15], (5, 2)) - np.array(
[int(rectangle[0]), int(rectangle[1])])) / (rectangle[3] -
rectangle[1]) * 160
#人脸截取
crop_img = img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img, (160, 160))
# 进行对齐操作
new_img, _ = utils.Alignment_1(crop_img, landmark)
# 增加一个维度
new_img = np.expand_dims(new_img, 0)
# 将检测到的人脸传入到facenet的模型中，实现128维特征向量的提取
face_encoding = utils.calc_128_vec(self.facenet_model, new_img)
self.known_face_encodings.append(face_encoding)
self.known_face_names.append(name)
def recognize(self,draw):
#-----------------------------------------------#
# 人脸识别
# 先定位，再进行数据库匹配
#-----------------------------------------------#
height,width,_ = np.shape(draw)
draw_rgb = cv2.cvtColor(draw,cv2.COLOR_BGR2RGB)
# 检测人脸
rectangles = self.mtcnn_model.detectFace(draw_rgb, self.threshold)
if len(rectangles)==0:
return
# 转化成正方形
rectangles = utils.rect2square(np.array(rectangles,dtype=np.int32))
rectangles[:,0] = np.clip(rectangles[:,0],0,width)
rectangles[:,1] = np.clip(rectangles[:,1],0,height)
rectangles[:,2] = np.clip(rectangles[:,2],0,width)
rectangles[:,3] = np.clip(rectangles[:,3],0,height)
#-----------------------------------------------#
# 对检测到的人脸进行编码
#-----------------------------------------------#
face_encodings = []
for rectangle in rectangles:
landmark = (np.reshape(rectangle[5:15],(5,2)) - np.array([int(rectangle[0]),int(rectangle[1])]))/(rectangle[3]-rectangle[1])*160
crop_img = draw_rgb[int(rectangle[1]):int(rectangle[3]), int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img,(160,160))
new_img,_ = utils.Alignment_1(crop_img,landmark)
new_img = np.expand_dims(new_img,0)
face_encoding = utils.calc_128_vec(self.facenet_model,new_img)
face_encodings.append(face_encoding)
face_names = []
for face_encoding in face_encodings:
# 取出一张脸并与数据库中所有的人脸进行对比，计算得分
matches = utils.compare_faces(self.known_face_encodings, face_encoding, tolerance = 0.6)
name = "Unknown"
# 找出距离最近的人脸
face_distances = utils.face_distance(self.known_face_encodings, face_encoding)
# 取出这个最近人脸的评分
best_match_index = np.argmin(face_distances)
if matches[best_match_index]:
name = self.known_face_names[best_match_index]
face_names.append(name)
rectangles = rectangles[:,0:4]
#-----------------------------------------------#
# 画框~!~
#-----------------------------------------------#
for (left, top, right, bottom), name in zip(rectangles, face_names):
cv2.rectangle(draw, (left, top), (right, bottom), (0, 0, 255), 2)
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(draw, name, (left , bottom - 15), font, 0.75, (255, 255, 255), 2)
return draw
def __init__(self):
# 创建mtcnn对象
# 检测图片中的人脸
self.mtcnn_model = mtcnn()
# 门限函数
self.threshold = [0.5, 0.8, 0.9]
# 载入facenet
# 将检测到的人脸转化为128维的向量
self.facenet_model = InceptionResNetV1()
# model.summary()
model_path = './model_data/facenet_keras.h5'
self.facenet_model.load_weights(model_path)
# -----------------------------------------------#
# 对数据库中的人脸进行编码
# known_face_encodings中存储的是编码后的人脸
# known_face_names为人脸的名字
# -----------------------------------------------#
face_list = os.listdir("face_dataset")
# 存放编码后的人脸
self.known_face_encodings = []
# 存放编码后人脸的名字
self.known_face_names = []
for face in face_list:
name = face.split(".")[0]
img = cv2.imread("./face_dataset/" + face)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# 检测人脸
rectangles = self.mtcnn_model.detectFace(img, self.threshold)
# 转化成正方形
rectangles = utils.rect2square(np.array(rectangles))
# facenet要传入一个160x160的图片
rectangle = rectangles[0]
# 记下他们的landmark
landmark = (np.reshape(rectangle[5:15], (5, 2)) - np.array(
[int(rectangle[0]), int(rectangle[1])])) / (rectangle[3] -
rectangle[1]) * 160
crop_img = img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img, (160, 160))
new_img, _ = utils.Alignment_1(crop_img, landmark)
new_img = np.expand_dims(new_img, 0)
# 将检测到的人脸传入到facenet的模型中，实现128维特征向量的提取
face_encoding = utils.calc_128_vec(self.facenet_model, new_img)
self.known_face_encodings.append(face_encoding)
self.known_face_names.append(name)
def __init__(self):
#-------------------------#
# 创建mtcnn的模型
# 用于检测人脸
#-------------------------#
self.mtcnn_model = mtcnn()
self.threshold = [0.5, 0.6, 0.8]
#-----------------------------------#
# 载入facenet
# 将检测到的人脸转化为128维的向量
#-----------------------------------#
self.facenet_model = facenet()
#-----------------------------------------------#
# 对数据库中的人脸进行编码
# known_face_encodings中存储的是编码后的人脸
# known_face_names为人脸的名字
#-----------------------------------------------#
face_list = os.listdir('face_dataset')
# print(face_list)
self.known_face_encodings = []
self.known_face_names = []
for face in face_list:
name = face.split('.')[0]
img = cv2.imread('./face_dataset/' + face)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
#---------------------#
# 检测人脸
#---------------------#
rectangles = self.mtcnn_model.detectFace(img, self.threshold)
#---------------------#
# 转化成正方形
#---------------------#
rectangles = utils.rect2square(np.array(rectangles))
#-----------------------------------------------#
# facenet要传入一个160x160的图片
# 利用landmark对人脸进行矫正
#-----------------------------------------------#
rectangle = rectangles[0]
landmark = np.reshape(rectangle[5:15], (5, 2)) - np.array(
[int(rectangle[0]), int(rectangle[1])])
crop_img = img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
crop_img, _ = utils.Alignment_1(crop_img, landmark)
# cv2.imwrite(name+'.jpg', crop_img)
# print(crop_img.shape)
crop_img = np.expand_dims(cv2.resize(crop_img, (160, 160)), 0)
#--------------------------------------------------------------------#
# 将检测到的人脸传入到facenet的模型中，实现128维特征向量的提取
#--------------------------------------------------------------------#
face_encoding = self.facenet_model.calc_128_vec(crop_img)
self.known_face_encodings.append(face_encoding)
self.known_face_names.append(name)
def recognize(self,draw):
#-----------------------------------------------#
# 人脸识别
# 先定位，再进行数据库匹配
#-----------------------------------------------#
height,width,_ = np.shape(draw)
draw_rgb = cv2.cvtColor(draw,cv2.COLOR_BGR2RGB)
# 检测人脸
rectangles = self.mtcnn_model.detectFace(draw_rgb, self.threshold)
if len(rectangles)==0:
return
rectangles = np.array(rectangles,dtype=np.int32)
rectangles[:,0] = np.clip(rectangles[:,0],0,width)
rectangles[:,1] = np.clip(rectangles[:,1],0,height)
rectangles[:,2] = np.clip(rectangles[:,2],0,width)
rectangles[:,3] = np.clip(rectangles[:,3],0,height)
rectangles_temp = utils.rect2square(np.array(rectangles,dtype=np.int32))
rectangles_temp[:,0] = np.clip(rectangles_temp[:,0],0,width)
rectangles_temp[:,1] = np.clip(rectangles_temp[:,1],0,height)
rectangles_temp[:,2] = np.clip(rectangles_temp[:,2],0,width)
rectangles_temp[:,3] = np.clip(rectangles_temp[:,3],0,height)
# 转化成正方形
#-----------------------------------------------#
# 对检测到的人脸进行编码
#-----------------------------------------------#
classes_all = []
for rectangle in rectangles_temp:
# 获取landmark在小图中的坐标
landmark = (np.reshape(rectangle[5:15],(5,2)) - np.array([int(rectangle[0]),int(rectangle[1])]))/(rectangle[3]-rectangle[1])*160
# 截取图像
crop_img = draw_rgb[int(rectangle[1]):int(rectangle[3]), int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img,(self.Crop_HEIGHT,self.Crop_WIDTH))
# 对齐
new_img,_ = utils.Alignment_1(crop_img,landmark)
# 归一化
new_img = preprocess_input(np.reshape(np.array(new_img,np.float64),[1,self.Crop_HEIGHT,self.Crop_WIDTH,3]))
classes = self.class_names[np.argmax(self.mask_model.predict(new_img)[0])]
classes_all.append(classes)
rectangles = rectangles[:,0:4]
#-----------------------------------------------#
# 画框~!~
#-----------------------------------------------#
for (left, top, right, bottom), c in zip(rectangles,classes_all):
cv2.rectangle(draw, (left, top), (right, bottom), (0, 0, 255), 2)
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(draw, c, (left , bottom - 15), font, 0.75, (255, 255, 255), 2)
return draw
def make_database():
# prepare models
retinaface_model = insightface.model_zoo.get_model('retinaface_mnet025_v1')
retinaface_model.prepare(ctx_id=-1, nms=0.4)
arcface_model = insightface.model_zoo.get_model('arcface_r100_v1')
arcface_model.prepare(ctx_id=-1)
face_list = getFilePathList('./face_dataset/casia')
face_list.sort()
known_face_encodings = []
known_face_names = []
timea = datetime.datetime.now()
for face in face_list:
name = face.split(os.sep)[-2]
# print(name)
# print(type(name))
image_path = os.path.join('./face_dataset/casia', name, name + '_0.bmp') # 取第一张图片作数据库
if(face != image_path):
continue
print(image_path)
img = cv2.imread(image_path)
# print(type(img))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
rectangle, landmark = retinaface_model.detect(img, threshold=0.5, scale=1.0)
rectangle = utils.rect2square(np.array(rectangle))
crop_img = img[int(rectangle[0, 1]):int(rectangle[0, 3]), int(rectangle[0, 0]):int(rectangle[0, 2])]
crop_img = cv2.resize(crop_img, (112, 112))
new_img, _ = utils.Alignment_1(crop_img, landmark[0])
face_encoding = arcface_model.get_embedding(new_img)
known_face_encodings.append(face_encoding)
known_face_names.append(name)
face_num = len(known_face_names)
known_face_encodings = np.array(known_face_encodings).reshape(face_num, 512)
np.save('faceEmbedding_casia', known_face_encodings)
np.save('name_casia', known_face_names)
timeb = datetime.datetime.now()
diff = timeb - timea
print("Building database:", diff.total_seconds(), 'seconds')
def recognize(self, draw):
#-----------------------------------------------#
# 人脸识别
# 先定位，再进行数据库匹配
#-----------------------------------------------#
height, width, _ = np.shape(draw)
draw_rgb = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
# 检测人脸
time_0 = datetime.datetime.now()
rectangles, landmarks = self.retinaface_model.detect(draw_rgb,
threshold=0.5,
scale=1.0)
if len(rectangles) == 0:
return
# 转化成正方形
rectangles = utils.rect2square(np.array(rectangles, dtype=np.int32))
# rectangles[:,0] = np.clip(rectangles[:,0],0,width)
# rectangles[:,1] = np.clip(rectangles[:,1],0,height)
# rectangles[:,2] = np.clip(rectangles[:,2],0,width)
# rectangles[:,3] = np.clip(rectangles[:,3],0,height)
time_now = datetime.datetime.now()
detect_time = time_now - time_0
print('Detection Time:', detect_time.total_seconds(), 'seconds')
#-----------------------------------------------#
# 对检测到的人脸进行编码
#-----------------------------------------------#
time_0 = datetime.datetime.now()
face_encodings = []
for rectangle, landmark in zip(rectangles, landmarks):
# landmark = (np.reshape(rectangle[5:15],(5,2)) - np.array([int(rectangle[0]),int(rectangle[1])]))/(rectangle[3]-rectangle[1])*112
crop_img = draw_rgb[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img, (112, 112))
new_img, _ = utils.Alignment_1(crop_img, landmark)
# new_img = np.expand_dims(new_img,0)
# face_encoding = utils.calc_128_vec(self.facenet_model,new_img)
face_encoding = self.arcface_model.get_embedding(new_img)
face_encodings.append(face_encoding)
# print(np.linalg.norm(face_encodings, axis=1))
face_names = []
for face_encoding in face_encodings:
# 取出一张脸并与数据库中所有的人脸进行对比，计算得分
# print(type(face_encoding))
matches = utils.compare_faces_1(self.known_face_encodings,
face_encoding,
tolerance=20)
# print(matches)
name = "Unknown"
# 找出距离最近的人脸
face_distances = utils.face_distance_1(self.known_face_encodings,
face_encoding)
# print(face_distances)
# 取出这个最近人脸的评分
best_match_index = np.argmin(face_distances)
# print(best_match_index)
if matches[best_match_index]:
name = self.known_face_names[best_match_index]
face_names.append(name)
time_now = datetime.datetime.now()
rec_time = time_now - time_0
print('Recognition Time:', rec_time.total_seconds(), 'seconds')
rectangles = rectangles[:, 0:4]
#-----------------------------------------------#
# 画框~!~
#-----------------------------------------------#
for (left, top, right, bottom), name in zip(rectangles, face_names):
cv2.rectangle(draw, (left, top), (right, bottom), (0, 0, 255), 2)
# print(1)
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(draw, name, (left, bottom - 15), font, 0.5,
(255, 255, 255), 2)
return draw
def __init__(self):
# 创建mtcnn对象
# 检测图片中的人脸
self.retinaface_model = insightface.model_zoo.get_model(
'retinaface_mnet025_v1')
self.retinaface_model.prepare(ctx_id=-1, nms=0.4)
# 门限函数
# self.threshold = [0.5,0.8,0.9]
# 载入arcface
# 将检测到的人脸转化为512维的向量
self.arcface_model = insightface.model_zoo.get_model('arcface_r100_v1')
self.arcface_model.prepare(ctx_id=-1)
#-----------------------------------------------#
# 对数据库中的人脸进行编码
# known_face_encodings中存储的是编码后的人脸
# known_face_names为人脸的名字
#-----------------------------------------------#
face_list = os.listdir("face_dataset")
# print(face_list)
self.known_face_encodings = []
self.known_face_names = []
timea = datetime.datetime.now()
for face in face_list:
name = face.split(".")[0]
img = cv2.imread("./face_dataset/" + face)
# print(type(img))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# 检测人脸
# rectangles = self.mtcnn_model.detectFace(img, self.threshold)
rectangle, landmark = self.retinaface_model.detect(img,
threshold=0.5,
scale=1.0)
# 转化成正方形
rectangle = utils.rect2square(np.array(rectangle))
# arcface要传入一个112x112的图片
# rectangle = rectangles[0]
# 记下他们的landmark
# landmark = (np.reshape(rectangle[5:15],(5,2)) - np.array([int(rectangle[0]),int(rectangle[1])]))/(rectangle[3]-rectangle[1])*112
# print(rectangle.shape)
# print(landmark.shape)
crop_img = img[int(rectangle[0, 1]):int(rectangle[0, 3]),
int(rectangle[0, 0]):int(rectangle[0, 2])]
crop_img = cv2.resize(crop_img, (112, 112))
# print(crop_img.shape[0:2])
new_img, _ = utils.Alignment_1(crop_img, landmark[0])
# print(new_img.shape[0:2])
# new_img = np.expand_dims(new_img,0)
# print(new_img.shape[0:2])
# 将检测到的人脸传入到arcface的模型中，实现512维特征向量的提取
# face_encoding = utils.calc_128_vec(self.facenet_model,new_img)
face_encoding = self.arcface_model.get_embedding(new_img)
self.known_face_encodings.append(face_encoding)
self.known_face_names.append(name)
self.known_face_encodings = np.array(
self.known_face_encodings).reshape(6, 512)
timeb = datetime.datetime.now()
diff = timeb - timea
print("Building database:", diff.total_seconds(), 'seconds')
model_path = './model_data/facenet_keras.h5'
facenet_model.load_weights(model_path)
for rectangle in rectangles:
if rectangle is not None:
landmark = (np.reshape(rectangle[5:15], (5, 2)) - np.array(
[int(rectangle[0]), int(rectangle[1])])) / (rectangle[3] -
rectangle[1]) * 160
# y方向的截取和x方向的截取
crop_img = img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
# resize后可以输入facenet中
crop_img = cv2.resize(crop_img, (160, 160))
cv2.imshow("before", crop_img)
new_img, _ = utils.Alignment_1(crop_img, landmark)
cv2.imshow("two eyes", new_img)
# std_landmark = np.array([[54.80897114,59.00365493],
# [112.01078961,55.16622207],
# [86.90572522,91.41657571],
# [55.78746897,114.90062758],
# [113.15320624,111.08135986]])
# crop_img = img[int(rectangle[1]):int(rectangle[3]), int(rectangle[0]):int(rectangle[2])]
# crop_img = cv2.resize(crop_img,(160,160))
# new_img,_ = utils.Alignment_2(crop_img,std_landmark,landmark)
# cv2.imshow("affine",new_img)
new_img = np.expand_dims(new_img, 0)
feature1 = utils.calc_128_vec(facenet_model, new_img)
cv2.waitKey(0)
def read__image(path_name):
num = 1000
for dir_image in os.listdir(
path_name): # os.listdir() 方法用于返回指定的文件夹包含的文件或文件夹的名字的列表
full_path = os.path.abspath(os.path.join(path_name, dir_image))
if os.path.isdir(full_path): # 如果是文件夹，继续递归调用
read__image(full_path)
else: # 如果是文件了
if dir_image.endswith('.jpg'):
img = cv2.imread(full_path)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
print(full_path)
# 检测人脸
rectangles = mtcnn_model.detectFace(img, threshold)
if rectangles != []:
# 转化成正方形
rectangles = utils.rect2square(np.array(rectangles))
for rectangle in rectangles:
if rectangle is not None:
landmark = (np.reshape(rectangle[5:15],
(5, 2)) - np.array([
int(rectangle[0]),
int(rectangle[1])
])) / (rectangle[3] -
rectangle[1]) * 160
crop_img = img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img, (160, 160))
# cv2.imshow("before",crop_img)
new_img, _ = utils.Alignment_1(crop_img, landmark)
# cv2.imshow("two eyes",new_img)
cv2.imwrite(
'C:\\Users\\yu guo long\\PycharmProjects\\face\\mtcnn\\mtcnn-keras-master\\data\\1\\'
+ '%d.jpg' % (num), new_img)
num += 1
if dir_image.endswith('.jpeg'):
img = cv2.imread(full_path)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
print(full_path)
rectangles = mtcnn_model.detectFace(img, threshold)
if rectangles != []:
# 转化成正方形
rectangles = utils.rect2square(np.array(rectangles))
for rectangle in rectangles:
if rectangle is not None:
landmark = (np.reshape(rectangle[5:15],
(5, 2)) - np.array([
int(rectangle[0]),
int(rectangle[1])
])) / (rectangle[3] -
rectangle[1]) * 160
crop_img = img[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img, (160, 160))
# cv2.imshow("before", crop_img)
new_img, _ = utils.Alignment_1(crop_img, landmark)
# cv2.imshow("two eyes", new_img)
# cv2.waitKey(0)
cv2.imwrite(
'C:\\Users\\yu guo long\\PycharmProjects\\face\\mtcnn\\keras-face-recognition-master\\data\\1\\'
+ '%d.jpg' % (num), new_img)
num += 1
def recognize(self, draw):
height, width, _ = np.shape(draw)
draw_rgb = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
time_0 = datetime.datetime.now()
rectangles, landmarks = self.retinaface_model.detect(draw_rgb,
threshold=0.5,
scale=1.0)
if len(rectangles) == 0:
return
# 转化成正方形
rectangles = utils.rect2square(np.array(rectangles, dtype=np.int32))
time_now = datetime.datetime.now()
detect_time = time_now - time_0
print('Detection Time:', detect_time.total_seconds(), 'seconds')
# -----------------------------------------------#
# 对检测到的人脸进行编码
# -----------------------------------------------#
time_0 = datetime.datetime.now()
face_encodings = []
for rectangle, landmark in zip(rectangles, landmarks):
# landmark = (np.reshape(rectangle[5:15],(5,2)) - np.array([int(rectangle[0]),int(rectangle[1])]))/(rectangle[3]-rectangle[1])*112
crop_img = draw_rgb[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img, (112, 112))
new_img, _ = utils.Alignment_1(crop_img, landmark)
# new_img = np.expand_dims(new_img,0)
face_encoding = self.arcface_model.get_embedding(new_img)
face_encodings.append(face_encoding)
face_names = []
for face_encoding in face_encodings:
#print(face_encoding.shape)
name = 'Unknown'
# Query the elements for themselves
names, distances = self.p.knn_query(face_encoding,
k=1) # 返回的距离是 1 - cosine
# print(distances)
matches = list(1 - distances >= 0.45)
best_match_index = np.argmax(distances)
if matches[best_match_index]:
name = str(names[best_match_index][0]) # names 多了个维度
face_names.append(name)
time_now = datetime.datetime.now()
rec_time = time_now - time_0
print('Recognition Time:', rec_time.total_seconds(), 'seconds')
#-----------------------------------------------#
# 画框~!~
#-----------------------------------------------#
rectangles = rectangles[:, 0:4]
for (left, top, right, bottom), name in zip(rectangles, face_names):
cv2.rectangle(draw, (left, top), (right, bottom), (0, 0, 255), 1)
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(draw, name, (left, bottom - 15), font, 0.5,
(0, 0, 255), 1)
return draw
def recognize(self, draw):
#-----------------------------------------------#
# recognise the face
# Position the face the match in database
#-----------------------------------------------#
height, width, _ = np.shape(draw)
draw_rgb = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
# recognise the face
rectangles = self.mtcnn_model.detectFace(draw_rgb, self.threshold)
if len(rectangles) == 0:
return
rectangles = np.array(rectangles, dtype=np.int32)
rectangles[:, 0] = np.clip(rectangles[:, 0], 0, width)
rectangles[:, 1] = np.clip(rectangles[:, 1], 0, height)
rectangles[:, 2] = np.clip(rectangles[:, 2], 0, width)
rectangles[:, 3] = np.clip(rectangles[:, 3], 0, height)
rectangles_temp = utils.rect2square(
np.array(rectangles, dtype=np.int32))
rectangles_temp[:, 0] = np.clip(rectangles_temp[:, 0], 0, width)
rectangles_temp[:, 1] = np.clip(rectangles_temp[:, 1], 0, height)
rectangles_temp[:, 2] = np.clip(rectangles_temp[:, 2], 0, width)
rectangles_temp[:, 3] = np.clip(rectangles_temp[:, 3], 0, height)
# reshape to square
#-----------------------------------------------#
# encode the face
#-----------------------------------------------#
classes_all = []
for rectangle in rectangles_temp:
# get the axis in landmark
landmark = (np.reshape(rectangle[5:15], (5, 2)) - np.array(
[int(rectangle[0]), int(rectangle[1])])) / (rectangle[3] -
rectangle[1]) * 160
# Intercept the image
crop_img = draw_rgb[int(rectangle[1]):int(rectangle[3]),
int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img,
(self.Crop_HEIGHT, self.Crop_WIDTH))
# Oppose
new_img, _ = utils.Alignment_1(crop_img, landmark)
# Normalization
new_img = preprocess_input(
np.reshape(np.array(new_img, np.float64),
[1, self.Crop_HEIGHT, self.Crop_WIDTH, 3]))
classes = self.class_names[np.argmax(
self.mask_model.predict(new_img)[0])]
classes_all.append(classes)
rectangles = rectangles[:, 0:4]
#-----------------------------------------------#
# draw the square
#-----------------------------------------------#
for (left, top, right, bottom), c in zip(rectangles, classes_all):
cv2.rectangle(draw, (left, top), (right, bottom), (0, 0, 255), 2)
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(draw, c, (left, bottom - 15), font, 0.75,
(255, 255, 255), 2)
return draw
