class Camera_reader(object):
def __init__(self):
self.model = Model()
self.model.load()
self.img_size = 128
def build_camera(self):
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_alt.xml')
name_list = read_name_list("C:\\Users\\jimmychen\\Desktop\\chernger\\chernger_faceRecognition\\dataset")
cameraCapture = cv2.VideoCapture(0)
success, frame = cameraCapture.read()
while success and cv2.waitKey(1) == -1:
success, frame = cameraCapture.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x, y, w, h) in faces:
ROI = gray[x:x + w, y:y + h]
ROI = cv2.resize(ROI, (self.img_size, self.img_size), interpolation=cv2.INTER_LINEAR)
label,prob = self.model.predict(ROI)
if prob > 0.7:
show_name = name_list[label]
cv2.putText(frame, show_name + "{}".format(prob), (x, y - 20), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
frame = cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
else:
show_name = 'Stranger'
cv2.putText(frame, show_name + "{}".format(prob), (x, y - 20), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 2)
frame = cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2)
frame = cv2.flip(frame, 1)
cv2.imshow("Camera", frame)
cameraCapture.release()
cv2.destroyAllWindows()
class Camera_reader(object):
#Load model
def __init__(self):
self.model = Model()
self.model.load()
self.img_size = 128
def build_camera(self):
face_cascade = cv2.CascadeClassifier('D:\proj\opencv-master\opencv-master\data\haarcascades\haarcascade_frontalface_alt.xml')
#Read the subfolder in dataset folder
name_list = read_name_list('D:\proj\dataset')
cameraCapture = cv2.VideoCapture(0)
success, frame = cameraCapture.read()
while success and cv2.waitKey(1) == -1:
success, frame = cameraCapture.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x, y, w, h) in faces:
ROI = gray[x:x + w, y:y + h]
ROI = cv2.resize(ROI, (self.img_size, self.img_size), interpolation=cv2.INTER_LINEAR)
label,prob = self.model.predict(ROI)
if prob >0.7: #Only output higher than 70% label
show_name = name_list[label]
else:
show_name = 'Stranger'
cv2.putText(frame, show_name, (x, y - 20), cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2)
frame = cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2)
cv2.imshow("Camera", frame)
cameraCapture.release()
cv2.destroyAllWindows()
class Camera_reader(object):
#在初始化camera的时候建立模型，并加载已经训练好的模型
def __init__(self):
self.model = Model()
self.model.load()
def build_camera(self):
#
face_cascade = cv2.CascadeClassifier('E:\openCV\opencv\sources\data\haarcascades\haarcascade_frontalface_alt.xml')
name_list = read_name_list('D:\myProject\pictures\dataset')
#打开摄像头并开始读取画面
cameraCapture = cv2.VideoCapture(0)
success, frame = cameraCapture.read()
while success and cv2.waitKey(1) == -1:
success, frame = cameraCapture.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x, y, w, h) in faces:
ROI = gray[x:x + w, y:y + h]
ROI = cv2.resize(ROI, (64, 64), interpolation=cv2.INTER_LINEAR)
label,prob = self.model.predict(ROI) #利用模型对cv2识别出的人脸进行比对
if prob >0.95: #如果模型认为概率高于95%则显示为模型中已有的label
show_name = name_list[label]
else:
show_name = 'Stranger'
cv2.putText(frame, show_name, (x, y - 20), cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2) #显示名字
frame = cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2) #在人脸区域画一个正方形出来
cv2.imshow("Camera", frame)
cameraCapture.release()
cv2.destroyAllWindows()
def __init__(self):
self.selector_rf = None
self.selector_svm = None
self.x_selected_rf = None
self.x_selected_svm = None
self.rfc = RandomForestClassifier(
criterion='gini',
n_estimators=191,
max_depth=13
# , max_features=6
,
min_samples_leaf=1,
random_state=30)
self.svc = SVC(kernel='linear',
C=0.007564633275546291,
tol=0.0001,
cache_size=1000,
random_state=30)
self.dh = DataHandle('data/phone_data.csv')
self.dh.read_data('data/smote_rf_data.csv')
self.model_rf = Model(self.dh.get_data(), self.dh.get_target())
self.dh.read_data('data/smote_svm_data.csv')
self.model_svm = Model(self.dh.get_data(), self.dh.get_target())
def evaluate_model(args):
hparams = PARAMS_MAP[args.model]
hparams["pickle_dir"] = args.eval_pickle
hparams = collections.namedtuple("HParams",
sorted(hparams.keys()))(**hparams)
model = Model(hparams)
print(hparams.init_checkpoint)
model.analysis_evaluate(saved_file=args.evaluate)
def __init__(self):
self.model = Model(read_save=True)
self.model.load()
self.img_size = 128
#opencv文件中人脸级联文件的位置，用于帮助识别图像或者视频流中的人脸
self.face_cascade = cv2.CascadeClassifier(
"haarcascade_frontalface_default.xml")
#读取dataset数据集下的子文件夹名称
self.name_list = read_name_list(dataset_path)
def __init__(self):
self.model = Model()
self.model.load()
self.img_size = 128
classname = 0
titlename = "untitled (hzy_order) - Sublime Text (UNREGISTERED)"
#获取句柄
self.hwnd = win32gui.FindWindow(classname, titlename)
print("得到句柄")
def load_model(fn):
m = Model(filter_sizes=[3, 3, 2, 2],
kernel_nums=[10, 10, 10, 10],
strides=[1, 1, 1, 1],
batch_size=50,
training_mode=False)
m.build_model()
m.model.load_weights(fn)
return m
def test_onePicture(path):
model = Model()
model.load()
color = (0, 255, 0)
img1 = cv2.imread(path)
img = cv2.resize(img1, (128, 128))
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
classfier = cv2.CascadeClassifier(
"C:\\ProgramData\\Anaconda3\\Lib\\site-packages\\cv2\\data\\haarcascade_frontalface_alt2.xml"
)
faceRects = classfier.detectMultiScale(img1,
scaleFactor=1.2,
minNeighbors=3,
minSize=(32, 32))
if len(faceRects) > 0: # 大于0则检测到人脸
for faceRect in faceRects: # 单独框出每一张人脸
x, y, w, h = faceRect
cv2.rectangle(img1, (x - 10, y - 10), (x + w + 10, y + h + 10),
color, 3) # 5控制绿色框的粗细
picType, prob = model.predict(img)
if picType != -1:
name_list = read_name_list('dataset')
info = name_list[picType].split('_')
infoName = 'Name:' + info[0]
infoAge = 'Age:' + info[1]
infoUniversity = 'University:' + info[2]
infoSex = 'Sex:' + info[3]
infoDrivingLN = 'Driving number:' + info[4]
cv2.rectangle(img1, (0, 0), (300, 255), color, 3) # 5控制绿色框的粗细
cv2.putText(img1, "Driver Info", (80, 25),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, 255, 2, 2) # 显示性别
cv2.putText(img1, infoDrivingLN, (0, 60), cv2.FONT_HERSHEY_SIMPLEX,
0.8, 255, 2, 2) # 显示驾驶证号码
cv2.putText(img1, infoName, (0, 100), cv2.FONT_HERSHEY_SIMPLEX,
0.8, 255, 2, 2) # 显示名字
cv2.putText(img1, infoAge, (0, 140), cv2.FONT_HERSHEY_SIMPLEX, 0.8,
255, 2, 2) # 显示年龄
cv2.putText(img1, infoUniversity, (0, 180),
cv2.FONT_HERSHEY_SIMPLEX, 0.8, 255, 2, 2) # 显示学历
cv2.putText(img1, infoSex, (0, 220), cv2.FONT_HERSHEY_SIMPLEX, 0.8,
255, 2, 2) # 显示性别
cv2.imshow("Camera", img1)
# cv2.imshow(name_list[picType],img1)
cv2.waitKey(0)
print(name_list[picType], prob)
else:
cv2.imshow(" Don't know this person", img1)
cv2.waitKey(0)
print(" Don't know this person")
else:
cv2.imshow("No Face in this picture !!!", img1)
cv2.waitKey(0)
print("No Face in this picture")
def train_model(args):
hparams = PARAMS_MAP[args.model]
timestamp = datetime.now().strftime('%Y%m%d-%H%M%S')
root_dir = os.path.join(hparams["root_dir"], "%s/" % timestamp)
logger = init_logger(root_dir)
logger.info("Hyper-parameters: %s" % str(hparams))
hparams["root_dir"] = root_dir
hparams = collections.namedtuple("HParams",
sorted(hparams.keys()))(**hparams)
model = Model(hparams)
model.train(pretrained_file=args.pretrained)
def test_onePicture(path):
model = Model()
model.load()
img = cv2.imread(path)
img = cv2.resize(img, (64, 64))
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
picType, prob = model.predict(img)
if picType != -1:
name_list = read_name_list('D:\myProject\pictures\dataset')
print name_list[picType], prob
else:
print " Don't know this person"
def test_onePicture(path):
model = Model()
model.load()
img = cv2.imread(path)
img = cv2.resize(img, (128, 128))
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
picType, prob = model.predict(img)
if picType != -1:
name_list = read_name_list(r'E:\cut-face')
print(name_list[picType], prob)
else:
print("Don't know this person")
def test_onePicture(path):
model= Model()
model.load()
img = cv2.imread(path)
img = cv2.resize(img, (128, 128))
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
picType,prob = model.predict(img)
if picType != -1:
name_list = read_name_list('/Users/gaoxingyun/Documents/uw/courses/Sp19/EE576_CV/project/realtime_emotion_recognition/dataset')
print (name_list[picType],prob)
else:
print (" Don't know this person")
def __init__(self):
self.model = Model()
self.model.load()
self.img_size = 128
print("init")
# 摄像头初始化 加快使用速度
self.face_cascade = cv2.CascadeClassifier(
'./haarcascade_frontalface_alt.xml')
# 读取dataset数据集下的子文件夹名称
self.name_list = read_name_list('res')
# 打开摄像头并开始读取画面
self.cameraCapture = cv2.VideoCapture(0)
class Camera_reader(object):
# 在初始化camera的时候建立模型，并加载已经训练好的模型
def __init__(self):
self.model = Model()
self.model.load()
self.img_size = 128
def build_camera(self):
# opencv文件中人脸级联文件的位置，用于帮助识别图像或者视频流中的人脸
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades +
'haarcascade_frontalface_alt.xml')
# 读取dataset数据集下的子文件夹名称，即标签名
name_list = read_name_list('./dataset')
# 打开摄像头并开始读取画面
cameraCapture = cv2.VideoCapture('recognize_faces2.mp4')
success, frame = cameraCapture.read()
while success and cv2.waitKey(1) == -1:
success, frame = cameraCapture.read()
# 图像灰度化
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# 检测人脸：scaleFactor是放大比例（此参数必须大于1）；minNeighbors是重复识别次数（此参数用来调整精确度，越大则越精确）
faces = face_cascade.detectMultiScale(gray,
scaleFactor=1.3,
minNeighbors=8)
for (x, y, w, h) in faces:
origin = gray[x:x + w, y:y + h]
# origin是原图，self.img_size是输出图像的尺寸，interpolation是插值方法
origin = cv2.resize(origin, (self.img_size, self.img_size),
interpolation=cv2.INTER_LINEAR)
# 利用模型对cv2识别出的人脸进行比对
label, prob = self.model.predict(origin)
# 如果模型认为概率高于70%则显示为模型中已有的label
if prob > 0.7:
show_name = name_list[label]
else:
show_name = 'unknown'
# 框出人脸
frame = cv2.rectangle(frame, (x, y), (x + w, y + h),
(255, 0, 0), 1)
# 显示人名
cv2.putText(frame, show_name, (x, y - 20),
cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2)
cv2.imshow("Recognizing...", frame)
# 释放摄像头
cameraCapture.release()
# 关闭所有窗口
cv2.destroyAllWindows()
def test_onBatch(path):
model = Model()
model.load()
index = 0
img_list, label_lsit, counter = read_file(path)
for img in img_list:
picType, prob = model.predict(img)
if picType != -1:
index += 1
print(labbel[picType], prob)
else:
print("invaild person")
return index
def test_onePicture(path):
model = Model()
model.load()
img = cv2.imread(path)
img = cv2.resize(img, (64, 64))
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
picType, prob = model.predict(img)
if picType != -1:
name_list = read_name_list(
'C:\\Users\\jimmychen\\Desktop\\chernger\\chernger_faceRecognition\\dataset'
)
print(name_list[picType], prob)
else:
print(" Don't know this person")
def test_onePicture(path):
model = Model()
model.load()
img = cv2.imread(path)
img = cv2.resize(img, (128, 128))
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
picType, prob = model.predict(img)
if picType != -1:
# name_list = read_name_list('D:\myProject\pictures\dataset')
name_list = read_name_list(
r'D:/my_laboratory/face_detection20180516/dataset')
print(name_list[picType], prob)
else:
print(" Don't know this person")
def __init__(self):
self.model = Model()
#self.model.load()
self.img_size = 128
if os.path.exists("images\\yjd_sc"):
shutil.rmtree("images\\yjd_sc")
if os.path.exists("images\\yjd_deal"):
shutil.rmtree("images\\yjd_deal")
if os.path.exists("dataset\\yjd_21_NEU_boy_001231"):
shutil.rmtree("dataset\\yjd_21_NEU_boy_001231")
os.mkdir("images\\yjd_sc")
os.mkdir("images\\yjd_deal")
os.mkdir("dataset\\yjd_21_NEU_boy_001231")
def test_onBatch(path):
model = Model()
model.load()
index = 0
img_list, label_lsit, counter = read_file(path)
for img in img_list:
picType, prob = model.predict(img)
if picType != -1:
index += 1
name_list = read_name_list('./image/trainfaces')
print(name_list[picType])
else:
print(" Don't know this person")
return index
class Camera_reader(object):
#在初始化camera的时候建立模型，并加载已经训练好的模型
def __init__(self):
self.model = Model()
self.model.load()
self.img_size = 128
def build_camera(self):
#opencv文件中人脸级联文件的位置，用于帮助识别图像或者视频流中的人脸
face_cascade = cv2.CascadeClassifier(
'/usr/local/lib/python2.7/site-packages/opencv-3.2.0/data/haarcascades/haarcascade_frontalface_alt.xml'
)
#读取dataset数据集下的子文件夹名称
name_list = read_name_list(
'/home/hezhiqiang/PycharmProjects/pictures/dataset')
#打开摄像头并开始读取画面
cameraCapture = cv2.VideoCapture(0)
nextCaptureTime = time.time()
faces = []
if not cameraCapture.isOpened():
print('Capture failed because of camera')
success, frame = cameraCapture.read()
while 1:
# while success and cv2.waitKey(1) == -1:
# print '1'
success, frame = cameraCapture.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) #图像灰化
# if nextCaptureTime < time.time():
# nextCaptureTime = time.time() + 0.1
faces = face_cascade.detectMultiScale(gray, 1.3, 5) #识别人脸
for (x, y, w, h) in faces:
ROI = gray[x:x + w, y:y + h]
ROI = cv2.resize(ROI, (self.img_size, self.img_size),
interpolation=cv2.INTER_LINEAR)
label, prob = self.model.predict(ROI) #利用模型对cv2识别出的人脸进行比对
if prob > 0.7: #如果模型认为概率高于70%则显示为模型中已有的label
show_name = name_list[label]
else:
show_name = 'Stranger'
cv2.putText(frame, show_name, (x, y - 20),
cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2) #显示名字
frame = cv2.rectangle(frame, (x, y), (x + w, y + h),
(255, 0, 0), 2) #在人脸区域画一个正方形出来
cv2.imshow("MyWindow", frame)
if cv2.waitKey(1) & 0xFF == 27: break
cameraCapture.release()
cv2.destroyAllWindows()
def test_onBatch(path):
model = Model()
model.load()
index = 0
img_list, label_lsit, counter = read_file(path)
for img in img_list:
picType, prob = model.predict(img)
if picType != -1:
index += 1
name_list = read_name_list('D:\myProject\pictures\dataset')
print name_list[picType]
else:
print " Don't know this person"
return index
def test_onBatch(path):
model= Model()
model.load()
index = 0
img_list, label_lsit, counter = read_file(path)
for img in img_list:
picType,prob = model.predict(img)
if picType != -1:
index += 1
name_list = read_name_list('/Users/gaoxingyun/Documents/uw/courses/Sp19/EE576_CV/project/faceRecognition/dataset')
print (name_list[picType])
else:
print (" Don't know this person")
return index
def test_onePicture(path):
model = Model()
model.load()
img = cv2.imread(path)
#print(img)
img = cv2.resize(img, (128, 128))
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
picType, prob = model.predict(img)
if picType != -1:
#print(picType,prob)
#name_list = read_name_list('../myAIlab/pictures/dataset')
#print(name_list[picType],prob)
print(labbel[picType], prob)
else:
print("invaild person")
def onePicture(path):
model = Model()
model.load()
img = cv2.imread(path)
img = cv2.resize(img, (92, 112))
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
picType, prob = model.predict(img)
if picType != -1:
name_list = read_name_list('res')
print(name_list)
print(picType)
print(name_list[picType], prob)
print("done")
else:
print(" Don't know this person")
def test_Pictures(path):
model = Model()
model.load()
for child_dir in os.listdir(path):
if endwith(child_dir, 'jpg'): # 找到以jpg结尾的文件路径
str = os.path.join(path, child_dir) # 具体的图片文件的路径
img = cv2.imread(str)
resized_img = cv2.resize(img, (128, 128),
interpolation=cv2.INTER_CUBIC)
img = cv2.cvtColor(resized_img, cv2.COLOR_BGR2GRAY)
picType, prob = model.predict(img)
if picType != -1:
name_list = read_name_list('pictures/dataset')
print(name_list[picType], prob)
else:
print(" Don't know this person")
class Camera_reader(object):
# 在初始化camera的时候建立模型，并加载已经训练好的模型
def __init__(self):
self.model = Model()
self.model.load()
self.img_size = 128
def build_camera(self):
# opencv文件中人脸级联文件的位置，用于帮助识别图像或者视频流中的人脸
face_cascade = cv2.CascadeClassifier(
r'C:\Users\01436179\PycharmProjects\pyhton_face\haarcascade_frontalface_alt.xml'
)
# 读取dataset数据集下的子文件夹名称
name_list = read_name_list(
r'C:\Users\01436179\PycharmProjects\pyhton_face\dataset')
# 打开摄像头并开始读取画面
cameraCapture = cv2.VideoCapture(0)
success, frame = cameraCapture.read()
while success and cv2.waitKey(1) == -1:
success, frame = cameraCapture.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# 图像灰化
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
# 识别人脸
for (x, y, w, h) in faces:
ROI = gray[x:x + w, y:y + h]
ROI = cv2.resize(ROI, (self.img_size, self.img_size),
interpolation=cv2.INTER_LINEAR)
label, prob = self.model.predict(ROI)
# 利用模型对cv2识别出的人脸进行比对
if prob > 0.7:
# 如果模型认为概率高于70%则显示为模型中已有的label
show_name = name_list[label]
else:
show_name = 'Stranger'
cv2.putText(frame, show_name, (x, y - 20),
cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2)
# 显示名字
frame = cv2.rectangle(frame, (x, y), (x + w, y + h),
(255, 0, 0), 2)
# 在人脸区域画一个正方形出来
cv2.imshow("Camera", frame)
cameraCapture.release()
cv2.destroyAllWindows()
class Camera_reader(object):
#在初始化camera的时候建立模型，并加载已经训练好的模型
def __init__(self):
self.model = Model()
self.model.load()
self.img_size = 128
classname = 0
titlename = "untitled (hzy_order) - Sublime Text (UNREGISTERED)"
#获取句柄
self.hwnd = win32gui.FindWindow(classname, titlename)
print("得到句柄")
def build_camera(self):
#opencv文件中人脸级联文件的位置，用于帮助识别图像或者视频流中的人脸C:\\Users\\jan\\AppData\\Local\\Programs\\Python\\Python36\\Lib\\site-packages\\cv2\\data\\
face_cascade = cv2.CascadeClassifier(
'C:\\Users\\jan\\AppData\\Local\\Programs\\Python\\Python36\\Lib\\site-packages\\cv2\\data\\haarcascade_frontalface_alt.xml'
)
#读取dataset数据集下的子文件夹名称
name_list = read_name_list('E:\\WWW\\faceRecognition\\dataset')
#打开摄像头并开始读取画面
cameraCapture = cv2.VideoCapture(0)
success, frame = cameraCapture.read()
while success and cv2.waitKey(1) == -1:
success, frame = cameraCapture.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) #图像灰化
faces = face_cascade.detectMultiScale(gray, 1.3, 5) #识别人脸
for (x, y, w, h) in faces:
ROI = gray[x:x + w, y:y + h]
ROI = cv2.resize(ROI, (self.img_size, self.img_size),
interpolation=cv2.INTER_LINEAR)
label, prob = self.model.predict(ROI) #利用模型对cv2识别出的人脸进行比对
if prob > 0.7: #如果模型认为概率高于70%则显示为模型中已有的label
show_name = name_list[label]
win32gui.SetForegroundWindow(self.hwnd)
print("got you %s " % show_name)
win32gui.ShowWindow(self.hwnd, win32con.SW_MAXIMIZE)
else:
show_name = 'Stranger'
#cv2.putText(frame, show_name, (x, y - 20), cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2) #显示名字
#frame = cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2) #在人脸区域画一个正方形出来
time.sleep(3)
#cv2.imshow("Camera", frame)
cameraCapture.release()
cv2.destroyAllWindows()
class Camera_reader(object):
#在初始化camera的时候建立模型，并加载已经训练好的模型
def __init__(self):
self.model = Model()
self.model.load()
self.img_size = 128
def build_camera(self):
#opencv文件中人脸级联文件的位置，用于帮助识别图像或者视频流中的人脸
face_cascade = cv2.CascadeClassifier(
'C:\\Face recognition\\classifier\\haarcascade_frontalface_alt2.xml'
)
#读取dataset数据集下的子文件夹名称
name_list = read_name_list('C:\\Face recognition\\data')
#打开摄像头并开始读取画面
cap = cv2.VideoCapture(0)
ret, frame = cap.read() #读取一帧视频
while ret and cv2.waitKey(10) == -1:
ret, frame = cap.read()
try:
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) #图像灰化
faces = face_cascade.detectMultiScale(
gray, scaleFactor=1.2, minNeighbors=3,
minSize=(32, 32)) #识别人脸,******
for (x, y, w, h) in faces:
ROI = gray[y - 10:y + h + 10, x - 10:x + w + 10]
ROI = cv2.resize(ROI, (self.img_size, self.img_size),
interpolation=cv2.INTER_LINEAR)
label, prob = self.model.predict(ROI) #利用模型对cv2识别出的人脸进行比对
if prob > 0.90: #如果模型认为概率高于95%则显示为模型中已有的label
show_name = name_list[label]
else:
show_name = 'Stranger'
cv2.putText(frame, show_name, (x, y - 20),
cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2) #显示名字
frame = cv2.rectangle(frame, (x, y), (x + w, y + h),
(255, 0, 0), 2) #在人脸区域画一个正方形
cv2.imshow("Camera", frame)
except:
continue
cap.release()
cv2.destroyAllWindows()
return show_name
def test_onePicture(path):
# 加载模型
model = Model()
model.load()
# 读取图片
img = cv2.imread(path)
# 重置图片尺寸为：128*128
img = cv2.resize(img, (128, 128))
# 图片灰度化
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# labelIndex为概率最高的label的索引号, prob为对应概率
labelIndex, prob = model.predict(img)
if labelIndex != -1:
name_list = read_name_list('./dataset')
print(name_list[labelIndex], prob)
else:
print("Don't know this person.")
