class ReceptionRobot():
# N_EPOCH = 50
N_EPOCH = 100
BATCH_SIZE = 96
# RECOGNITION_IMAGE_SIZE = (32, 32)
RECOGNITION_IMAGE_SIZE = (64, 64)
SAVE_IMAGE_SIZE = (64, 64)
PERSON_IMAGES_NUM = 10
PLATFORM = Platform.macos.value
def __init__(self):
self.load_face_recognition_model()
self.app = QApplication(sys.argv)
def run(self):
""" Start face recognize system.
"""
self.say("おはようございます")
self.capture()
def capture(self):
""" Capture video. Wait to detect face.
"""
def loop_func(**kwargs):
current_persons = self.recognize(kwargs.get('face_imgs'))
kwargs.get('past_recognized_persons').append(current_persons)
if len(kwargs.get('past_recognized_persons')) > 3:
kwargs.get('past_recognized_persons').pop(0)
# continuous person filtering.
person_ids = Person.objects().distinct(field='_id')
for persons in kwargs.get('past_recognized_persons')[-3:]:
tmp_person_ids = []
for person in persons:
tmp_person_ids.append(person._id)
person_ids = list(set(person_ids) & set(tmp_person_ids))
for person_id in person_ids:
self.greet(Person.objects(_id=person_id).first())
face_capture.FaceCapture.capture(
loop_func=loop_func,
continue_condition_func=lambda **kwargs: False,
break_condition_func=lambda **kwargs: False,
)
def recognize(self, imgs: [np.array((None, None, 3))]):
""" Recognize detected face.
Args:
img: numpy.array(), (?, ?, 3)
unknown size of rgb image.
Returns:
persons: [person.Person()]
"""
person_id_indexes = \
self.face_recognizer.recognize(imgs)
persons = []
for person_id_index in person_id_indexes:
person_id = self.face_recognizer.person_ids[person_id_index]
person = Person.objects(_id=person_id).first()
persons.append(person)
return persons
def greet(self, person: Person):
""" Greet to recognized person.
"""
self.say("こんにちは。{}さん".format(person.nickname))
@classmethod
def say(cls, message, speaker="kyoko"):
""" Speak with MacOSX talk application
"""
# print(os.path.dirname(__file__))
cls.print(message)
if cls.PLATFORM == Platform.macos.value:
cls.say_macos(message, speaker=speaker)
elif cls.PLATFORM == Platform.linux.value:
cls.say_linux(message, speaker=speaker)
@classmethod
def say_macos(cls, message, speaker="kyoko"):
talk_application = 'default'
# talk_application = 'open-jtalk'
# Text to voice.
voice_output_dir = os.path.dirname(__file__) + "/voices/"
if talk_application == 'default':
voice_filename = "{voice_output_dir}{message}.aiff".format(
voice_output_dir=voice_output_dir, message=message
)
say_command = "say -v {speaker} {message} -o {voice_dir}{message}.aiff".format(
speaker=speaker, message=message, voice_dir=voice_output_dir)
elif talk_application == 'open-jtalk':
dict_dir = '/usr/local/Cellar/open-jtalk/1.09/dic'
voice_dir = '/usr/local/Cellar/open-jtalk/1.09/voice/mei' \
'/mei_normal.htsvoice'
voice_filename = "{voice_outut_dir}{message}.wav".format(
voice_outut_dir=voice_output_dir, message=message
)
say_command = 'open_jtalk -x {dict_dir} -m {voice_dir} ' \
'-ow {voice_filename} ' \
'{message}'.format(
message=message, dict_dir=dict_dir, voice_dir=voice_dir,
voice_filename=voice_filename)
print(say_command)
else:
return False
# Convert to robotic voice.
pitch = 350
tempo = 1.15
sox_convert_command = "sox {voice_filename} " \
"{voice_dir}{message}.wav " \
"echo 0.8 0.8 5 0.7 " \
"echo 0.8 0.7 6 0.7 " \
"echo 0.8 0.7 10 0.7 " \
"echo 0.8 0.8 12 0.7 " \
"echo 0.8 0.88 30 0.7 " \
"pitch {pitch} tempo {tempo}".format(
message=message, pitch=pitch, tempo=tempo,
voice_dir=voice_output_dir, voice_filename=voice_filename,
)
play_command = "play {voice_dir}{message}.wav".format(
message=message, voice_dir=voice_output_dir)
# if not os.path.exists("{voice_dir}{message}.wav"):
os.system(say_command)
os.system(sox_convert_command)
os.system(play_command)
@classmethod
def say_linux(cls):
""" Linux platform say method.
"""
@classmethod
def print(cls, message):
""" Print message to application interface.
Args:
message:
Returns:
"""
print(message)
def load_face_recognition_model(self):
# person.Person.objects().distinct('_id')
# self.face_recognizer = FaceRecognizer.objects(
# n_epoch=self.N_EPOCH,
# batch_size=self.BATCH_SIZE,
# image_size=self.RECOGNITION_IMAGE_SIZE,
# person_ids=Person.ascendind_ids(),
# ).first()
# if self.face_recognizer is None:
# return None
person_ids = [obj._id for obj in Person.objects]
self.face_recognizer = FaceRecognizer(
n_epoch=self.N_EPOCH,
batch_size=self.BATCH_SIZE,
image_size=self.RECOGNITION_IMAGE_SIZE,
person_ids=person_ids,
person_num=len(person_ids)
)
self.face_recognizer.generate_filename()
print(self.face_recognizer.filename)
self.face_recognition_model = \
self.face_recognizer.load_model()
return self.face_recognition_model
@classmethod
def save_person_capture(cls, max_faces=100):
""" save person with video capture.
"""
nickname, last_name, first_name, company = \
cls.ask_personality()
cls.say("{}さんのことを覚えたいので5秒ほどビデオを撮りますね。".format(nickname))
cls.say("はい。とりまーす！")
def face_yield(face, faces):
if len(faces) > cls.PERSON_IMAGES_NUM:
yield face
yield face
all_face_imgs = face_capture.FaceCapture.capture(
loop_func=lambda **kwargs: True,
continue_condition_func=lambda **kwargs: len(
kwargs.get('face_positions')) > 1,
break_condition_func=lambda **kwargs:
len(kwargs.get('all_face_imgs')) > cls.PERSON_IMAGES_NUM)
person_obj = Person(
nickname=nickname,
last_name=last_name,
first_name=first_name,
company=company,
)
person_obj.set_face_imgs(all_face_imgs, cls.SAVE_IMAGE_SIZE)
cls.say("今{}さんのこと覚えてます。1分くらいかかるかもしれません。".format(
nickname))
# cls.say("たぶん大丈夫ですが、僕はロボットなのでデータの保存に失敗すると"
# "全て忘れてしまうので...")
person_obj.save()
cls.say("{}さんのことバッチリ覚えました！またお会いしましょう。".format(
nickname))
# cls.say("あ、でも一回寝ないと顔で思い出せない作りになっているので、"
# "また明日以降あったときはご挨拶させてもらいますね。")
@classmethod
def ask_personality(cls):
app = QApplication(sys.argv)
window = Window(title='Opus',
labels=['ニックネーム', '姓', '名', '会社名'])
# cls.say("はじめまして。私は人工知能のオーパスです。")
# cls.say("あなたのことを知りたいので名前と会社名を教えてください。"
# "ニックネームには、私に呼ばれたい名前を入れてください。")
cls.say("名前を教えてね。")
app.exit(app.exec_())
# cls.say("私に呼ばれたい名前を入れてください")
# nickname = input()
# cls.say("{} さん ですね。よろしくお願いします。".format(nickname))
# cls.say("あと苗字と名前、所属会社を教えてください。")
# cls.say("まずは苗字をお願いします。")
# last_name = input()
# cls.say("次に名前")
# first_name = input()
# cls.say("最後に所属会社をお願いします。")
# company = input()
# cls.say("{}の{} {}さんですね。登録しておきます。".format(
# company, last_name, first_name))
# return nickname, last_name, first_name, company
texts = window.texts
return texts
@classmethod
def memorize_face(self):
""" Learn face model.
Returns:
"""
# FaceRecognizer.fit(n_epoch=5)
FaceRecognizer.fit(
n_epoch=self.N_EPOCH, batch_size=self.BATCH_SIZE,
image_size=self.RECOGNITION_IMAGE_SIZE,)
