def set_favorite_item_in_ui():
print("Selected Favorite Item")
favorites_item = favorites_list_queryset.filter(
name=favorites_item_name.get())
favorites_item_selected = parsepy.item(
name=favorites_item[0].name,
upc=favorites_item[0].upc,
imageURL=favorites_item[0].imageURL,
category=favorites_item[0].category)
print(favorites_item_selected, favorites_item_selected.name)
set_item_in_ui(favorites_item_selected, 'upc')
if len(favorites_item_selected.name) > 1:
speaker.say(favorites_item_selected.name)
def search(upc):
new_item = parsepy.item()
# Call the API and put results into a new Item object
params = {'token': BARCODESPIDER_TOKEN, 'upc': upc}
r = requests.get(BARCODESPIDER_URL, params=params)
if r.status_code == 200:
item_attributes = r.json()['item_attributes']
new_item.name = item_attributes['title'] # the product title from the lookup
new_item.upc = upc
new_item.imageURL = item_attributes['image']
else:
new_item.name = "@@ UPC not found"
return new_item
def __init__(self, speaker):
self.speaker = speaker # used to create the beep() sound
self.handle = pvrhino.create(context_path='./models/Irma_Rules_2.rhn',
sensitivity=0.25)
print("sample_rate", self.handle.sample_rate, "frame_len:",
self.handle.frame_length)
self.pa = pyaudio.PyAudio()
self.audio_stream = self.pa.open(
rate=self.handle.sample_rate,
channels=1,
format=pyaudio.paInt16,
input=True,
frames_per_buffer=self.handle.frame_length)
self.recognizer = sr.Recognizer() # obtain audio from the microphone
print('NONSPEAKING', self.recognizer.non_speaking_duration)
print('PAUSE THRESHOLD', self.recognizer.pause_threshold)
self.recognizer.pause_threshold = 0.5 # default 0.8
self.recognizer.operation_timeout = 2
self.recognizer.energy_threshold = 3000
with sr.Microphone() as source:
self.recognizer.adjust_for_ambient_noise(source)
# Thread and flags
self.ON = True
self.running = True
self.wakeword_flag = False
self.voice_item = parsepy.item()
self.voice_item.upc = ' '
self.voice_item.imageURL = ' '
self.voice_item.name = ' '
self.command = 'None'
self.wakeword_thread = threading.Thread(target=self.wakeword_run,
name="wakeword_thread")
self.wakeword_thread.start()
print('WakeWord Initialized')
def raise_new_item_window():
global current_item
current_item = parsepy.item()
new_item_window.deiconify()
from io import BytesIO
from tkinter import *
import requests
from PIL import ImageTk, Image
from parse_rest.connection import register
from parse_rest.user import User
import parsepy
import voice_command
register(APP_ID, API_KEY, master_key=None)
user = User.login(USER, PASSWORD)
current_item = parsepy.item()
last_name = " "
def start(barcode, wake, speaker, detected_object):
# Root: Define the tkinter root.
root = Tk()
root.title('IRMA Refrigerator Management System')
root.geometry("900x800")
# root.attributes("-fullscreen", True)
# root.columnconfigure(0, weight=1)
# root.rowconfigure(0, weight=1)
# Frame: Define a frame that covers the entire root window.
root_frame = Frame(root, padx=3, pady=3)
root_frame.grid(column=0, row=0, sticky=(N, W, E, S))
def detection_loop(self):
print("detection loop started")
while self.ON:
# Read frame from camera connection
frame = self.camera.read_frame()
in_height, in_width, in_channels = frame.shape
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame_resized = cv2.resize(frame_rgb, (self.width, self.height))
input_data = np.expand_dims(frame_resized, axis=0)
# Normalize pixel values if using a floating model (i.e. if model is non-quantized)
if self.floating_model:
input_data = (np.float32(input_data) - 127.5) / 127.5
print('Floating model')
# Perform the actual detection by running the model with the image as input
self.interpreter.set_tensor(self.input_details[0]['index'], input_data)
self.interpreter.invoke()
# Retrieve detection results
boxes = self.interpreter.get_tensor(self.output_details[0]['index'])[0] # Bounding box coordinates of detected objects
classes = self.interpreter.get_tensor(self.output_details[1]['index'])[0] # Class index of detected objects
scores = self.interpreter.get_tensor(self.output_details[2]['index'])[0] # Confidence of detected objects
# Loop over all detections and draw detection box if confidence is above minimum threshold
ilist = [51, 52, 53, 54, 55, 56, 57, 58, 59, 60]
object_name = ' '
top_score = 0
top_name = ' '
last_name = ' '
for i in range(len(scores)):
if ((int(classes[i]) in ilist) and (scores[i] > self.min_conf_threshold) and (scores[i] <= 1.0)):
# Get bounding box coordinates and draw box
# Interpreter can return coordinates that are outside of image dimensions, need to force them to be within image using max() and min()
ymin = int(max(0, boxes[i][0]) * in_height)
xmin = int(max(0, boxes[i][1]) * in_width)
ymax = int(min(1, boxes[i][2]) * in_height)
xmax = int(min(1, boxes[i][3]) * in_width)
cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), (10, 255, 0), 1)
# Draw label into **input frame**
object_name = self.labels[int(classes[i])] # Look up object name from "labels" array using class index
item_txt = '%s: %d%%' % (object_name, int(scores[i] * 100)) # Example: 'person: 72%'
labelSize, baseLine = cv2.getTextSize(item_txt, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2) # Get font size
label_ymin = max(ymin, labelSize[1] + 10) # Make sure not to draw label too close to top of window
cv2.rectangle(frame,
(xmin, label_ymin - labelSize[1] - 10),
(xmin + labelSize[0], label_ymin + baseLine - 10),
(255, 255, 255),
cv2.FILLED) # Draw white box to put label text in
cv2.putText(frame, item_txt,
(xmin, label_ymin - 7),
cv2.FONT_HERSHEY_SIMPLEX,
0.5, (0, 0, 0), 2) # Draw label text
# Draw circle in center
xcenter = xmin + (int(round((xmax - xmin) / 2)))
ycenter = ymin + (int(round((ymax - ymin) / 2)))
cv2.circle(frame, (xcenter, ycenter), 5, (0, 0, 255), thickness=-1)
if scores[i] > top_score:
top_score = scores[i]
top_name = self.labels[int(classes[i])]
# Print info
print('Object ', str(classes[i]), ': ', object_name, 'score:', scores[i])
# SELECT WHICH ITEM GETS SAVED
if top_name != last_name:
last_name = top_name
object_item = parsepy.item()
object_item.name = top_name
object_item.upc = ' '
object_item.imageURL = ' '
print("writing new object", object_item.name)
self.new_item = object_item
self.obj_flag = True
# All the results have been drawn on the frame, so it's time to display it.
if SHOW_DETECTION_VIDEO and in_height > 0:
out_scale_fct = 1
frame = cv2.resize(frame, (int(in_width * out_scale_fct), int(in_height * out_scale_fct)))
frame = cv2.normalize(frame, frame, 0, 255, cv2.NORM_MINMAX)
cv2.imshow('Objects', frame)
cv2.moveWindow('Objects', 10, 10)
cv2.waitKey(200)