class ImageProcessor(object):
def __init__(self):
self.computervision_client = ComputerVisionClient(
endpoint, CognitiveServicesCredentials(subscription_key))
def get_img_captions(self, image_path):
local_image = open(image_path, "rb")
local_image_description = self.computervision_client.describe_image_in_stream(
local_image)
captions = []
if (len(local_image_description.captions) == 0):
print("No captions detected.")
else:
for caption in local_image_description.captions:
captions.append(caption.text)
return captions
def get_img_objects(self, image_path):
local_image = open(image_path, "rb")
local_image_objects = self.computervision_client.detect_objects_in_stream(
local_image)
objects = []
if len(local_image_objects.objects) == 0:
print("No objects detected.")
else:
for obj in local_image_objects.objects:
objects.append((obj.object_property, obj.rectangle.x, obj.rectangle.x + obj.rectangle.w, \
obj.rectangle.y, obj.rectangle.y + obj.rectangle.h))
dims = (local_image_objects.metadata.width,
local_image_objects.metadata.height)
return (objects, dims)
def caption(update: 'telegram.Update',
context: 'telegram.ext.CallbackContext') -> None:
"""Uses NLP to generate a caption for an image."""
try:
if update.message and update.message.reply_to_message:
message: 'telegram.Message' = update.message.reply_to_message
else:
return
file: telegram.File = context.bot.getFile(message.photo[-1].file_id)
buffer = BytesIO(file.download_as_bytearray())
buffer.seek(0)
api_key = config["AZURE_KEY"]
endpoint = 'https://tgbot.cognitiveservices.azure.com/'
computervision_client = ComputerVisionClient(
endpoint, CognitiveServicesCredentials(api_key))
description_results = computervision_client.describe_image_in_stream(
buffer)
caption = description_results.captions[0].text
confidence = description_results.captions[0].confidence
text = f"{caption}.\n*Confidence:* {round(confidence * 100, 2)}%"
text = "%s%s" % (text[0].upper(), text[1:])
message.reply_text(text=text)
except AttributeError:
update.message.reply_text(text="*Usage:* `/caption`\n"
"Type /caption in response to an image.\n")
def index():
if request.method == 'GET':
# User is requesting the form
return render_template('form.html')
elif request.method == 'POST':
# User has sent us data
image = request.files['image']
client = ComputerVisionClient(
COGSVCS_CLIENTURL, CognitiveServicesCredentials(COGSVCS_KEY))
result = client.describe_image_in_stream(image)
message = 'No dog found. How sad. :-('
if 'dog' in result.tags:
message = 'There is a dog! Wonderful!!'
return render_template('result.html', message=message)
def describe(image_path):
endpoint = os.getenv("COMPUTER_VISION_ENDPOINT")
subscription_key = os.getenv("COMPUTER_VISION_SUBSCRIPTION_KEY")
computervision_client = ComputerVisionClient(
endpoint, CognitiveServicesCredentials(subscription_key))
if (not os.path.isfile(image_path)):
description_results = computervision_client.describe_image(image_path)
else:
with open(image_path, "rb") as image:
description_results = computervision_client.describe_image_in_stream(
image)
if (len(description_results.captions) == 0):
return ("", 0)
else:
return (description_results.captions[0].text,
description_results.captions[0].confidence * 100)
class CognitiveModel:
def __init__(self, image_file: str):
self.subscription_key = "a3747513ff724c229b41274483acb06f"
self.endpoint = "https://cvision-crushyna.cognitiveservices.azure.com/"
self.computervision_client = ComputerVisionClient(
self.endpoint, CognitiveServicesCredentials(self.subscription_key))
self.image_file = image_file
self.description = None
def get_image_desc(self) -> str:
"""
Describe an Image - remote
This example describes the contents of an image with the confidence score.
"""
# print("===== Describe an image - remote =====")
# Call API
logging.info("Opening image file as binary file")
local_image = open(self.image_file, 'rb')
logging.info("Streaming data to Azure Server")
description_results = self.computervision_client.describe_image_in_stream(
local_image)
# Get the captions (descriptions) from the response, with confidence level
if len(description_results.captions) == 0:
no_desc = "No description detected."
logging.warning(no_desc)
self.description = no_desc
return no_desc
else:
for caption in description_results.captions:
logging.info(f"Description found: {caption.text}")
desc_found = "'{}' with confidence {:.2f}%".format(
caption.text, caption.confidence * 100)
self.description = desc_found
return desc_found
print("No description detected.")
else:
for caption in description_results.captions:
print("'{}' with confidence {:.2f}%".format(caption.text,
caption.confidence * 100))
print()
'''
Describe an Image - local
This example describes the contents of an image with the confidence score.
'''
print("===== Describe an Image - local =====")
# Open local image file
local_image_path = "Images/Landmark.jpg"
local_image = open(local_image_path, "rb")
# Call API
description_result = computervision_client.describe_image_in_stream(
local_image)
# Get the captions (descriptions) from the response, with confidence level
print("Description of local image: ")
if len(description_result.captions) == 0:
print("No description detected.")
else:
for caption in description_result.captions:
print("'{}' with confidence {:.2f}%".format(caption.text,
caption.confidence * 100))
'''
END - Describe an Image - local
'''
CognitiveServicesCredentials(KEY))
rootFilePath = os.path.dirname(
os.path.realpath('__file__')) + '/' # Get the Root File Path
camera = PiCamera() # Create an instance of the PiCamera
# Take a photo
photoFilename = takePicture()
# Get an image to get a description
#remote_image_url = "https://petecodes.co.uk/images/skateboard.png"
#Alternate
#remote_image_url = "https://raw.githubusercontent.com/Azure-Samples/cognitive-services-sample-data-files/master/ComputerVision/Images/landmark.jpg"
'''
Describe an Image - local
This example describes the contents of an image with the confidence score.
'''
print("===== Describe an image - local =====")
# Call API
description_results = computervision_client.describe_image_in_stream(
open(photoFilename, 'rb'))
# Get the captions (descriptions) from the response, with confidence level
print("Description of image: ")
if (len(description_results.captions) == 0):
print("No description detected.")
else:
for caption in description_results.captions:
print("'{}' with confidence {:.2f}%".format(caption.text,
caption.confidence * 100))
analysis = client.analyze_image_by_domain_in_stream(domain, image, language)
for landmark in analysis.result["landmarks"]:
print(landmark["name"])
print(landmark["confidence"])
#-----------------TEXT DESCRIPTION OF IMAGE-------------#
print("#-----------------TEXT DESCRIPTION OF IMAGE-------------#")
image = open(path, 'rb')
domain = "landmarks"
# url = "http://www.public-domain-photos.com/free-stock-photos-4/travel/san-francisco/golden-gate-bridge-in-san-francisco.jpg"
language = "en"
max_descriptions = 3
analysis = client.describe_image_in_stream(image, max_descriptions, language)
for caption in analysis.captions:
print(caption.text)
print(caption.confidence)
#-----------------TEXT FROM IMAGE-------------#
print("#-----------------TEXT FROM IMAGE-------------#")
# import models
from azure.cognitiveservices.vision.computervision.models import TextOperationStatusCodes
import time
image = open(path, 'rb')
# url = "https://smhttp-ssl-39255.nexcesscdn.net/wp-content/uploads/2016/01/Handwritten-note-on-Presidential-stationery-900x616.jpg"
raw = True
custom_headers = None
f.write('\n'+namePara+'$'+str(1)+'$')
f.close()
while True:
#ultSonic.calculateDistance()
if(ultSonic.calculateDistance() <= 10):
camera.start_preview()
sleep(5)
camera.capture('/home/pi/Desktop/image.jpg')
camera.stop_preview()
buffer = io.BytesIO()
buffer.write(open(imagePath, 'rb').read())
buffer.seek(0)
print("===== Detect Objects - remote =====")
print("===== Describe an image - remote =====")
# Call API
description_results = computervision_client.describe_image_in_stream(image=buffer)
print("Description of remote image: ")
if (len(description_results.captions) == 0):
print("No description detected.")
else:
for caption in description_results.captions:
print("'{}' with confidence {:.2f}%".format(caption.text, caption.confidence * 100))
print(api.detect_food_in_text(caption.text).json())
name = api.detect_food_in_text(caption.text).json()['annotations']
if len(name)!=0:
name2 = name[0]['annotation']
if name2!="":
print(name2)
putInFridge(name2)
print("New entry added to the fridge")
sleep(2)
