def __init__(self, videoPath, azureSpeechServiceKey, predictThreshold,
imageProcessingEndpoint, sendToHubCallback,
speechMapFileName):
self.videoPath = videoPath
self.predictThreshold = predictThreshold
self.imageProcessingEndpoint = imageProcessingEndpoint
self.imageProcessingParams = ""
self.sendToHubCallback = sendToHubCallback
if self.__IsInt(videoPath):
# case of a usb camera (usually mounted at /dev/video* where * is an int)
self.isWebcam = True
self.vs = None
self.speech_map = None
self.speech_voice = 'en-US-GuyNeural'
self.speech_map_filename = speechMapFileName
if speechMapFileName is not None and os.path.isfile(
self.speech_map_filename):
with open(self.speech_map_filename, encoding='utf-8') as f:
json_data = json.load(f)
self.speech_voice = json_data.get('voice')
self.speech_map = json_data.get('map')
self.tts = text2speech.TextToSpeech(azureSpeechServiceKey,
enableMemCache=True,
enableDiskCache=True,
voice=self.speech_voice)
text = self.__localize_text('Starting scanner')
self.tts.play('Starting scanner' if text is None else text)
def __init__(self,
videoPath,
azureSpeechServiceKey,
predictThreshold,
imageProcessingEndpoint,
sendToHubCallback=None):
self.videoPath = videoPath
self.tts = text2speech.TextToSpeech(azureSpeechServiceKey)
self.predictThreshold = predictThreshold
self.imageProcessingEndpoint = imageProcessingEndpoint
self.imageProcessingParams = ""
self.sendToHubCallback = sendToHubCallback
self.tts.play('Starting scanner')
if self.__IsInt(videoPath):
# case of a usb camera (usually mounted at /dev/video* where * is an int)
self.isWebcam = True
self.vs = None
def addArray(array, article):
#rgb = (int(float(array[0])), int(float(array[1])), int(float(array[2])))
rgb = tuple(array)
hex_result = '%02x%02x%02x' % rgb
print(hex_result)
input = hex_result + ', ' + article
item = getClosestColor(input)
recommendation = item
print(recommendation)
value = recommendation[0].split(', ')
color = value[0]
item = value[1]
print("Wear a " + webcolors.hex_to_name('#' + color) + " " + item)
subscription_key = "3dcb81c95f9d46248813f574677f3272"
app = text2speech.TextToSpeech(subscription_key,
webcolors.hex_to_name('#' + color), article)
app.get_token()
app.save_audio("suggestion.wav")
playsound('suggestion.wav')
import text2speech
speech_voice = 'en-AU-Catherine'
azureSpeechServiceKey = ''
tts = text2speech.TextToSpeech(azureSpeechServiceKey,
enableMemCache=False,
enableDiskCache=False,
voice=speech_voice)
tts.play("hello world")
import requests
import io
import os
import numpy as np
# import local devicecheck module
import devicecheck
import hubmanager
import oleddisplay
from iothub_client import IoTHubMessage
import text2speech
oled_display = None
hub = None
IMAGE_CLASSIFY_THRESHOLD = .95
tts = text2speech.TextToSpeech(os.getenv('BingKey'))
# Pull camera images and stream data to image classifier module.
def stream_camera_data(camera):
while True:
stream = io.BytesIO()
camera.capture(stream, format='jpeg')
stream.seek(0)
image = {'imageData': stream}
try:
requests.post('http://image-classifier-service:80/image',
files=image,
hooks={'response': c_request_response})
except Exception as e:
if (object_.name == "Pants"):
width, height = im.size
# Cropped image of above dimension
# (It will not change orginal image)
im2 = im.crop((coord[0] * width, coord[1] * height, coord[2] * width,
coord[3] * height))
im2.save("pant.png")
path = "pant.png"
with io.open(path, 'rb') as image_file:
content = image_file.read()
image = vision.types.Image(content=content)
response = client.image_properties(image=image)
props = response.image_properties_annotation
pantColor = []
for color in props.dominant_colors.colors:
pantColor.append(format(color.color.red))
pantColor.append(format(color.color.green))
pantColor.append(format(color.color.blue))
break
for color in topColor:
print(color)
for color in pantColor:
print(color)
subscription_key = "3dcb81c95f9d46248813f574677f3272"
app = text2speech.TextToSpeech(subscription_key, "purple", "shirt")
app.get_token()
app.save_audio()
playsound('sample.wav')
def __init__(self,
videoPath,
bingSpeechKey,
predictThreshold,
imageProcessingEndpoint="",
imageProcessingParams="",
showVideo=False,
verbose=True,
loopVideo=True,
convertToGray=False,
resizeWidth=0,
resizeHeight=0,
annotate=False,
sendToHubCallback=None):
self.videoPath = videoPath
if self.__IsInt(videoPath):
# case of a usb camera (usually mounted at /dev/video* where * is an int)
self.isWebcam = True
else:
# case of a video file
self.isWebcam = False
self.imageProcessingEndpoint = imageProcessingEndpoint
if imageProcessingParams == "":
self.imageProcessingParams = ""
else:
self.imageProcessingParams = json.loads(imageProcessingParams)
self.showVideo = showVideo
self.verbose = verbose
self.loopVideo = loopVideo
self.convertToGray = convertToGray
self.resizeWidth = resizeWidth
self.resizeHeight = resizeHeight
self.annotate = (self.imageProcessingEndpoint !=
"") and self.showVideo & annotate
self.nbOfPreprocessingSteps = 0
self.autoRotate = False
self.sendToHubCallback = sendToHubCallback
self.vs = None
self.tts = text2speech.TextToSpeech(bingSpeechKey)
self.predictThreshold = predictThreshold
if self.convertToGray:
self.nbOfPreprocessingSteps += 1
if self.resizeWidth != 0 or self.resizeHeight != 0:
self.nbOfPreprocessingSteps += 1
if self.verbose:
print(
"Initialising the camera capture with the following parameters: "
)
print(" - Video path: " + self.videoPath)
print(" - Image processing endpoint: " +
self.imageProcessingEndpoint)
print(" - Image processing params: " +
json.dumps(self.imageProcessingParams))
print(" - Show video: " + str(self.showVideo))
print(" - Loop video: " + str(self.loopVideo))
print(" - Convert to gray: " + str(self.convertToGray))
print(" - Resize width: " + str(self.resizeWidth))
print(" - Resize height: " + str(self.resizeHeight))
print(" - Annotate: " + str(self.annotate))
print(" - Send processing results to hub: " +
str(self.sendToHubCallback is not None))
print()