def __init__(self, parent=None):
super(JHFaceGUI, self).__init__(parent)
self.data_builder = data_builder.DataBuilder(
global_variables.DATA_PATH)
self.face_cascade = cv2.CascadeClassifier(
global_variables.CASCADE_PATH)
self.num_of_faces = 0
self.recognizer = recognizer.Recognizer(
self.data_builder, recognizer.FACE_RECOGNIZER_LBPH)
self.recognizer_enable = False
self.setupUi(self)
self.nameLineEdit.setText('')
self.capture = cv2.VideoCapture(0)
self.capture.set(cv2.CAP_PROP_FRAME_WIDTH, self.cameraLabel.width())
self.capture.set(cv2.CAP_PROP_FRAME_HEIGHT, self.cameraLabel.height())
_, self.current_image = self.capture.read()
self.addDataButton.clicked.connect(self.add_data)
self.trainButton.clicked.connect(self.train)
self.recognizeButton.clicked.connect(self.toggle_recognizer)
self.thresholdLineEdit.textChanged.connect(self.set_threshold)
self.timer = QtCore.QTimer()
self.timer.timeout.connect(self.display_video_stream)
self.timer.start(30)
def __init__(self):
QMainWindow.__init__(self)
self.setWindowFlags(QtCore.Qt.WindowStaysOnTopHint
| QtCore.Qt.FramelessWindowHint
| QtCore.Qt.X11BypassWindowManagerHint)
self.setAttribute(Qt.WA_NoSystemBackground, True)
self.setAttribute(Qt.WA_TranslucentBackground, True)
# x, y, width, height
self.setGeometry(*config.BOARD_POINT, config.BOARD_SIZE,
config.BOARD_SIZE)
self.setWindowOpacity(0.8)
self.is_white = True
self.white_checkbox = QAction('White', checkable=True, checked=True)
self.white_checkbox.triggered.connect(self.set_white)
self.black_checkbox = QAction('Black', checkable=True)
self.black_checkbox.triggered.connect(self.set_black)
self.recognizer = recognizer.Recognizer()
self.point_from = None
self.point_to = None
# init engine
self.engine # noqa
def recognizer(self):
self.progress_bar()
self.TProgressbar1['value'] = 0
root.update_idletasks()
#os.system("C:\\Users\\acer\\AppData\\Local\\Temp\\cnn.py\\recognizer.py")
obj=recognizer.Recognizer()
self.TProgressbar1['value'] = 0
def __init__(self, draw_widget, btAddr):
super(DrawingRecognizer, self).__init__()
self.draw_widget = draw_widget
self.connectingWiimote(btAddr)
self.initUI()
self.recognition = recognizer.Recognizer()
self.setSavedTemplates()
self.transformation = pt()
# start WiiControler recognition
self.gameInterface()
def main():
rospy.init_node("main")
speaker = speak.Speaker()
speaker.intro()
rec = recognizer.Recognizer()
res = rec.start_recognizer()
if res[0] == "HELLO ":
num_of_right_answers = 0
num_of_wrong_answers = 0
while (num_of_right_answers < 15) or (num_of_wrong_answers < 3):
answer = speaker.game()
rec = recognizer.Recognizer()
res = rec.start_recognizer()
if answer.lower() == res[:-1].lower:
speaker.correct_answer()
num_of_right_answers += 1
else:
speaker.wrong_answer()
num_of_wrong_answers += 1
else:
speaker.shutdown()
def __init__(self, flags):
# flags[0] = quit
# flags[1] = add user
# flags[2] = camera on or off
self.flags = flags
self.to_scan = 0
self.db_update = 0
self.face_thread = None
self.db_thread = None
self.db = database.Database('python', 'Hinoob22')
self.recognizer = recognizer.Recognizer()
self.faces = set()
self.faceCascade = cv2.CascadeClassifier(
"haarcascade_frontalface_default.xml")
def run(args):
if args['mode'] == 'train':
## preprocessing steps
preprocess.preprocess_train('./cars/cars_train',
'./cars/devkit/cars_train_annos.mat')
preprocess.preprocess_test('./cars/cars_test',
'./cars/devkit/cars_test_annos.mat')
split_test_val.test_with_labels(
'./cars/cars_test', './cars/devkit/cars_test_annos_withlabels.mat')
split_test_val.val_test_split()
train.start(train_path, val_path)
elif args['mode'] == 'test':
car_detector = det.Detector()
car_recognizer = rec.Recognizer()
images_dir = os.listdir(args['data'] + "/test/")
for imagepath in images_dir:
no_of_cars, car_boxes = car_detector.test_model(args['data'] +
"/test/" +
imagepath)
print('car_boxes', car_boxes[0])
if no_of_cars > 0:
print(imagepath)
image_ = image.load_img(args['data'] + "/test/" + imagepath)
image_ = image.img_to_array(image_)
height, width, ch = image_.shape
if no_of_cars > 1:
for cars in range(0, no_of_cars):
print('cars', cars)
rec_image = image_[int(car_boxes[cars][0] *
height):int(car_boxes[cars][2] *
height),
int(car_boxes[cars][1] *
width):int(car_boxes[cars][3] *
width)]
result = car_recognizer.load_images_predict(rec_image)
print("found {} in the above image".format(result))
else:
rec_image = image_[int(car_boxes[0][0] *
height):int(car_boxes[0][2] *
height),
int(car_boxes[0][1] *
width):int(car_boxes[0][3] * width)]
result = car_recognizer.load_images_predict(rec_image)
print("found {} in the above image".format(result))
def main():
mic = r.Recognizer()
# En esta línea se obtiene el texto bien sea por voz o por texto
text = "Cuántos departamentos tiene Colombia".lower()
tokens = text.split(' ') # tokenizacion del texto
pln = p.NLP(text) # Procesamiento del texto
entities = e.get_entities(text) # Obtencion de las entidades
POS = pln.getPosDoc() # Obtencion de las partes del habla
no_stop = pln.getNoStopToken() # Obtencion de las palabras de parada
if 'ADJ' in POS:
# Obtencion de todas las posibles palabras candidatas a ser tablas o campos
for lista in POS['ADJ']:
POS['NOUN'].append(lista)
if 'NOUN' in POS: # Si obtenemos palabras candidatas realizaremos el procesamiento
nouns = POS['NOUN']
tables = pdb.get_Possible_Table(nouns) # Obtencion de posibles tablas
fields = pdb.get_Possible_Fields(nouns) # Obtencion de posibles campos
# Método para saber si es una pregunta especial o no
special_question = pdb.get_special_question(nouns, entities)
if not special_question:
print(fields, entities)
if fields and entities:
# Después de realizar todo el procesamiento de la frase, enviamos lo obtenido a una consulta
db.consulta(entities[0][1], fields[0], tokens)
else:
print("No podemos realizar tu consulta")
else:
if c.how_many in tokens:
size = db.depCol() # Consulta de preguntas especiales
print("Colombia tiene {} departamentos".format(size))
else:
db.depCol() # Consulta de preguntas especiales
else:
print("No hemos podido procesar tu frase")
from flask import Flask
from flask import request
import recognizer
temp_dir = 'temp'
app = Flask(__name__)
r = recognizer.Recognizer(temp_dir=temp_dir)
r.load_models()
@app.route('/upload', methods=['POST'])
def rec():
if request.method == 'POST':
data = request.data
f = open(temp_dir + '/test.wav', 'wb')
f.write(data)
f.close()
response = r.recognize()
return str(response)
return 'who'
if __name__ == '__main__':
app.run()
def __init__(self, flags):
self.flags = flags
self.to_scan = 0
self.face_thread = None
self.recognizer = recognizer.Recognizer()
time.sleep(10)
def __init__(self, keep_run=[False]):
self.keep_running = keep_run
self.faceCascade = cv2.CascadeClassifier(
"haarcascade_frontalface_default.xml")
self.recognizer = recognizer.Recognizer()
t2(1,2,3) - t5(4,2,3),
t2(1,2,4) - t13(2,3,4),
t3(1,2,3) - t10(4,1,3),
t3(1,2,4) - t12(4,2,1),
t3(1,3,4) - t3(4,2,3),
t4(1,2,3) - t7(3,1,4),
t4(1,2,4) - t5(1,2,3),
t4(1,3,4) - t8(4,2,3),
t4(2,3,4) - t6(2,3,4),
t5(1,2,4) - t6(3,1,4),
t5(1,3,4) - t7(2,3,4),
t6(1,2,3) - t9(1,2,4),
t7(1,2,3) - t9(1,3,4),
t7(1,2,4) - t8(1,2,3),
t8(1,2,4) - t11(3,4,2),
t8(1,3,4) - t9(2,4,3),
t9(1,2,3) - t11(3,1,4),
t10(1,2,3) - t12(1,3,4),
t10(1,2,4) - t11(1,2,3),
t10(2,3,4) - t13(4,2,1),
t11(1,2,4) - t13(1,3,4),
t12(1,2,3) - t13(1,2,3)
end
"""
R = recognizer.Recognizer()
ans1 = R.recognize(data1)
ans2 = R.recognize(data2)
ans3 = R.recognize_snappy('m004(1,1)')
"""
This files contains examples and tests of the recognizers
"""
import cv2
import os
import sys
dir_path = os.path.dirname(os.path.realpath(__file__))
sys.path.append(dir_path)
import recognizer as rc
# intuitive implementation of Recognizer
recognizer = rc.Recognizer(.6, rc.SMART_RECOGNITION)
while True:
recognizer.next_frame(data_on_frame=True, show_frame=True)
if cv2.waitKey(1) != -1:
break
recognizer.close_window()
def __init__(self):
"""Initialize a DemoApp object"""
self.init_gui()
self.__recognizer = recognizer.Recognizer()
self.__recognizer.add_listener(self.final_result)
