def publish_to_describer(image_string):
"""Takes an image file name and publishes it to twitter with ComputerVision description"""
# Generate the Image URL and local location
remote_image_url = config.online_image_folder + image_string
image_location = config.local_image_folder + image_string
# Authenticate with Twitter
auth = tweepy.OAuthHandler(config.consumer_key, config.consumer_secret)
auth.set_access_token(config.access_token, config.access_token_secret)
api = tweepy.API(auth)
api.verify_credentials()
print("Twitter Authentication OK")
# Connect to ComputerVision
subscription_key = config.subscription_key
endpoint = config.endpoint
computervision_client = ComputerVisionClient(
endpoint, CognitiveServicesCredentials(subscription_key))
description_results = computervision_client.describe_image(
remote_image_url)
# Get the captions (descriptions) from the response, with confidence level
tweet = ''
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))
tweet = caption.text
# Upload image
media = api.media_upload(image_location)
# Post tweet with image
api.update_status(status=tweet, media_ids=[media.media_id])
def describe_image(client: ComputerVisionClient, remote_url: str):
"""
Describe image contents - remote
"""
print(f"Calling description API for image {remote_url}")
description_results = client.describe_image(remote_url)
print("Recieved image description:")
if (len(description_results.captions) == 0):
print("No description received")
else:
for caption in description_results.captions:
print(f"'{caption.text}' with confidence:\
{caption.confidence * 100}")
def My_Description(url):
SUBSCRIPTION_KEY = os.getenv('OCR_SUBSCRIPTION_KEY')
ENDPOINT = os.getenv('OCR_ENDPOINT')
CV_CLIENT = ComputerVisionClient(
ENDPOINT, CognitiveServicesCredentials(SUBSCRIPTION_KEY))
description_results = CV_CLIENT.describe_image(url)
output = ""
for caption in description_results.captions:
output += "'{}' with confidence {:.2f}% \n".format(
caption.text, caption.confidence * 100)
return output
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)
def makeAPI(remote_image_url):
MINIMAL_CONFIDENCE = 70
image_tags = []
if 'COMPUTER_VISION_SUBSCRIPTION_KEY' in os.environ:
subscription_key = os.environ['COMPUTER_VISION_SUBSCRIPTION_KEY']
else:
print(
"\nSet the COMPUTER_VISION_SUBSCRIPTION_KEY environment variable.\n**Restart your shell or IDE for changes to take effect.**"
)
sys.exit()
if 'COMPUTER_VISION_ENDPOINT' in os.environ:
endpoint = os.environ['COMPUTER_VISION_ENDPOINT']
else:
print(
"\nSet the COMPUTER_VISION_ENDPOINT environment variable.\n**Restart your shell or IDE for changes to take effect.**"
)
sys.exit()
computervision_client = ComputerVisionClient(
endpoint, CognitiveServicesCredentials(subscription_key))
'''Describes the contents of a remote image with the confidence score'''
description_results = computervision_client.describe_image(
remote_image_url)
for caption in description_results.captions:
if ((caption.confidence * 100) >= MINIMAL_CONFIDENCE):
image_tags.append([caption.text, caption.confidence * 100])
'''Describes the category of a remote image with the confidence score'''
remote_image_features = ["categories"]
categorize_results_remote = computervision_client.analyze_image(
remote_image_url, remote_image_features)
for category in categorize_results_remote.categories:
if ((category.score * 100) >= MINIMAL_CONFIDENCE):
image_tags.append([category.name, category.score * 100])
'''Returns a tag (key word) for each thing in the image'''
tags_result_remote = computervision_client.tag_image(remote_image_url)
for tag in tags_result_remote.tags:
if ((tag.confidence * 100) >= MINIMAL_CONFIDENCE):
image_tags.append([tag.name, tag.confidence * 100])
image_tags = sortingTags(image_tags)
return image_tags
import json
with open('../03_aws .seacret.json') as f:
seacret = json.load(f)
KEY = seacret['key']
ENDPOINT = seacret['endpoint']
computervision_client = ComputerVisionClient(ENDPOINT,
CognitiveServicesCredentials(KEY))
remote_image_url = "https://raw.githubusercontent.com/Azure-Samples/cognitive-services-sample-data-files/master/ComputerVision/Images/landmark.jpg"
print("===== Describe an image - remote =====")
# Call API
description_results = computervision_client.describe_image(remote_image_url)
# Get the captions (descriptions) from the response, with confidence level
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))
'''
Categorize an Image - remote
This example extracts (general) categories from a remote image with a confidence score.
'''
print("===== Categorize an image - remote =====")
# Select the visual feature(s) you want.
For our demonstration we will analyze the following image which we will also
display momentarily:
Location: {}
Path: {}
Filename: {}""".format(url1, url2, url3))
domain = "landmarks"
language = "en"
max_descriptions = 3
mlpreview(url)
try:
analysis = client.describe_image(url, max_descriptions, language)
except Exception as e:
catch_exception(e, url)
mlask(end="\n")
for caption in analysis.captions:
print(
fill("With confidence of {} found {}".format(
round(caption.confidence, 2), caption.text)) + "\n")
# Image to Text Example
mlask()
url1 = "https://azurecomcdn.azureedge.net/"
def getNewDataFromMS(self, cleanedData):
data_algorithm = []
self.Aux.deleteDataFromFolder('./Data/Response/')
computervision_client = ComputerVisionClient(
self.VISION_ENDPOINT,
CognitiveServicesCredentials(self.VISION_KEY))
ta_credential = AzureKeyCredential(self.TEXT_KEY)
text_analytics_client = TextAnalyticsClient(
endpoint=self.TEXT_ENDPOINT, credential=ta_credential)
for row in cleanedData:
try:
# PIC ANALYTICS
remote_image_url = row['algorithm']['photo']
remote_image_url_ed = row['algorithm']['photo_ed']
description_results = computervision_client.describe_image(
remote_image_url)
if len(description_results.captions) > 0:
tags = description_results.tags
row['results']['TagsInPic'] = tags
row['results']['NumOfObjectsInPic'] = len(tags)
if len(tags) <= 5:
row['results']['CLASS_fewObjects'] = True
elif len(tags) >= 20:
row['results']['CLASS_manyObjects'] = True
else:
row['results']['CLASS_normalObjects'] = True
for caption in description_results.captions:
confidence = caption.confidence * 100
if confidence > 50:
row['results']['hasContent'] = 'yes'
row['results']['content'].append(caption.text)
else:
row['results']['hasContent'] = 'unsure'
break
# get the picture category
remote_image_features = ["categories"]
categorize_results_remote = computervision_client.analyze_image(
remote_image_url, remote_image_features)
if len(categorize_results_remote.categories) > 0:
for category in categorize_results_remote.categories:
if category.score * 100 > 50:
row['results']['imageCategory'].append(
category.name)
else:
row['results']['imageCategory'].append(
'unsure')
# get all objects in picture
detect_objects_results_remote = computervision_client.detect_objects(
remote_image_url)
for objects in detect_objects_results_remote.objects:
if objects.object_property == 'person' and objects.confidence * 100 > 50:
row['results']['hasHuman'] = True
# check if a face of the person is visible
remote_image_features = ["faces"]
detect_faces_results_remote = computervision_client.analyze_image(
remote_image_url, remote_image_features)
if len(detect_faces_results_remote.faces) > 0:
row['results']['hasFace'] = True
# Color scheme
remote_image_features = ["color"]
detect_color_results_remote = computervision_client.analyze_image(
remote_image_url, remote_image_features)
detect_color_results_remote_ed = computervision_client.analyze_image(
remote_image_url_ed, remote_image_features)
picColor = detect_color_results_remote
if not picColor.color.is_bw_img:
row['results']['hasColor'] = True
background = picColor.color.dominant_color_background
row['colors']['background'] = background
foreground = picColor.color.dominant_color_foreground
row['colors']['foreground'] = foreground
dominantColors = detect_color_results_remote_ed.color.dominant_colors
row['colors']['dominantColors'] = dominantColors
accentColor = picColor.color.accent_color
row['colors']['accentColor'] = accentColor
if background == 'Black' and foreground == 'Black':
row['results']['isBright'] = False
if len(dominantColors) > 2:
row['results']['hasManyDomColors'] = True
answer = self.Aux.getHue(accentColor)
hue = answer[1]
row['colors']['hue'] = hue
warmHue = answer[0]
if warmHue:
row['results']['hasWarmHueAccent'] = True
# TEXT ANALYTICS
title = [row['algorithm']['title']]
# sentiment and length TITLE
sentimentTitle = self.getLengthSentiment(
title, text_analytics_client)
row['results']['lengthOfTitle'] = sentimentTitle[0]
if sentimentTitle[0] >= 47:
row['results']['CLASS_longTitle'] = True
elif sentimentTitle[0] <= 22:
row['results']['CLASS_shortTitle'] = True
else:
row['results']['CLASS_normalTitle'] = True
row['results']['sentimentTitle'] = sentimentTitle[1]
if sentimentTitle[1] == 'positive':
row['results']['CLASS_positiveTitle'] = True
elif sentimentTitle[1] == 'neutral':
row['results']['CLASS_neutralTitle'] = True
else:
row['results']['CLASS_negativeTitle'] = True
row['results']['sentiScoresTitle'] = sentimentTitle[
2] # pos neu neg share
# get Key Phrases in TITLE
phrasesTitle = self.getPhrases(title, text_analytics_client)
keyPhrasesTitle = []
for phrase in phrasesTitle:
phrase.replace('-', ' ')
wordList = re.sub("[^\w]", " ", phrase).split()
keyPhrasesTitle.append(wordList)
flattenedKeyPhrasesTitle = list(
self.Aux.flatten(keyPhrasesTitle))
row['results']['keyPhrasesTitle'] = flattenedKeyPhrasesTitle
# analyze TEXT
text = [row['algorithm']['text']]
# sentiment and length TEXT
sentimentText = self.getLengthSentiment(
text, text_analytics_client)
row['results']['lengthOfText'] = sentimentText[0]
if sentimentText[0] >= 131:
row['results']['CLASS_longText'] = True
elif sentimentText[0] <= 100:
row['results']['CLASS_shortText'] = True
else:
row['results']['CLASS_normalText'] = True
row['results']['sentimentText'] = sentimentText[1]
if sentimentText[1] == 'positive':
row['results']['CLASS_positiveText'] = True
elif sentimentText[1] == 'neutral':
row['results']['CLASS_neutralText'] = True
else:
row['results']['CLASS_negativeText'] = True
row['results']['sentiScoresText'] = sentimentText[2]
# get Key Phrases TEXT
phrasesText = self.getPhrases(text, text_analytics_client)
keyPhrasesText = []
for phrase in phrasesText:
phrase.replace('-', ' ')
wordList = re.sub("[^\w]", " ", phrase).split()
keyPhrasesText.append(wordList)
flattenedKeyPhrasesText = list(
self.Aux.flatten(keyPhrasesText))
row['results']['keyPhrasesText'] = flattenedKeyPhrasesText
# analyze TITLE TEXT and Picture
picTags = row['results']['TagsInPic']
phrases = flattenedKeyPhrasesText + flattenedKeyPhrasesTitle
matchPic = self.Aux.textMatch(phrases, picTags)
row['results']['TextMatchPic'] = matchPic[1]
# analyze creator and TITLE TEXT
creator = row['algorithm']['creator']
matchCreator = self.Aux.textMatch(phrases, creator)
row['results']['CreatorMatchTitle'] = matchCreator[1]
# analyze OCR in picture
picUrl = row['algorithm']['photo'].lstrip("'")
OCRTags = self.getOCRTags(picUrl)
if len(OCRTags) > 0:
row['results']['OCRTags'] = OCRTags
TextMatchOCR = self.Aux.textMatch(phrases, OCRTags)
row['results']['OCRMatches'] = TextMatchOCR[0]
row['results']['TextMatchPicOCR'] = TextMatchOCR[1]
# check HYPOTHESIS
if row['results']['hasHuman'] and row['results']['hasColor'] and row['results']['isBright'] and \
not row['results']['CLASS_negativeTitle'] and \
row['results']['CLASS_positiveText'] and row['results']['hasWarmHueAccent']:
row['results']['H1_Emotion'] = True
if not row['results']['CLASS_manyObjects'] and not row['results']['CLASS_longTitle'] and \
not row['results']['CLASS_longText'] and \
row['results']['CLASS_neutralText'] and not row['results']['CLASS_negativeTitle']:
row['results']['H2_ClearMassage'] = True
if row['results']['CreatorMatchTitle'] and row['results'][
'TextMatchPicOCR']:
row['results']['H3_Trust'] = True
data_algorithm.append(row)
except Exception as E:
print('Project cannot be analyzed by Algrorithm ' + str(E))
return data_algorithm
from azure.cognitiveservices.vision.computervision.models import VisualFeatureTypes
url = 'https://pbs.twimg.com/media/ECx6hK-WwAAPzeE.jpg'
analise_de_imagem = client.analyze_image(url, visual_features = [VisualFeatureTypes.tags])
for tag in analise_de_imagem.tags:
print(tag)
analise_de_celebridades = client.analyze_image_by_domain("celebrities", url, "en")
for celebridade in analise_de_celebridades.result["celebrities"]:
print(celebridade['name'])
print(celebridade['confidence'])
descricacao = client.describe_image(url,3,"en")
descricacao
for caption in descricacao.captions:
print(caption.text)
print(caption.confidence)
"""# Streaming + Vision API"""
import json
api.get_user('jcalvesol').id_str
famosos_id = []
for famoso in famosos:
famoso_id = api.get_user(famoso).id_str
# Download the query image from the url
downloaded_faces_image = requests.get(query_image_url)
img = Image.open(BytesIO(downloaded_faces_image.content))
# For each face returned use the face rectangle and draw a red box.
print()
print('Drawing rectangle around face(s)... see popup for results.')
draw = ImageDraw.Draw(img)
for face in detected_faces.faces: # list[FaceDescription]
draw.rectangle(getRectangle(face), outline='red')
# Display the image in the users default image browser.
img.show()
# Call API to describe image
description_result = computer_vision_client.describe_image(query_image_url)
# Get the captions (descriptions) from the response, with confidence level
print()
print("Description of 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))
print()
# Detect domain-specific content, celebrities, in image
# Call API with content type (celebrities) and URL
detect_domain_celebrity_result = computer_vision_client.analyze_image_by_domain(
class AnalyzeDocument():
def __init__(self):
self.api_key = ""
self.endpoint = ""
self.location = ""
self.max_num_retries = 2
self.res_file_ = '../template/resources/'
self.text_translator_ = TextTranslator()
# self.load_config('../template/config.json')
# self.basic_trans_ = BasicTranslation()
# if not self.api_key or not self.endpoint:
# raise Exception('Please set/export API key')
# self.authentication()
# image = Image.open(self.res_file_ + 'de-OP-Bericht-001.jpeg').convert('RGB')
# image = open(self.res_file_ + 'de-OP-Bericht-001.jpeg', "rb")
# self.azure_ocr_image(image,"en")
def load_config(self, file_path):
file_ = open(file_path)
data = json.load(file_)
self.api_key = data['api_keys']['vision']
self.endpoint = data['endpoints']['vision']
self.location = data['locations']['vision']
def authentication(self,config_path):
config_path += '/analytics/template/config.json'
self.load_config(config_path)
if not self.api_key or not self.endpoint:
raise Exception('Please set/export API key')
self.text_translator_.authentication(config_path=config_path)
self.computervision_client = ComputerVisionClient(self.endpoint,
CognitiveServicesCredentials(self.api_key))
def run_example(self):
remote_image_url = "https://raw.githubusercontent.com/Azure-Samples/cognitive-services-sample-data-files/master/ComputerVision/Images/landmark.jpg"
print("===== Describe an image - remote =====")
# Call API
description_results = self.computervision_client.describe_image(remote_image_url)
# Get the captions (descriptions) from the response, with confidence level
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))
def azure_ocr_by_url(self,url):
pass
def azure_ocr_image(self, image, lan_to, lan_from=None):
description_results = self.computervision_client.recognize_printed_text_in_stream(image,language='de')
if not lan_from:
lan_from = description_results.language
translated_text_ = ""
for region in description_results.regions:
region_line_ = ""
for line in region.lines:
s = ""
for word in line.words:
s += word.text + " "
region_line_ += s
# translated_text_ += self.basic_trans_.translate_text(region_line_,lan_from,lan_to)
translated_text_ += self.text_translator_.translate_text(region_line_,lan_from,lan_to)
# print(translated_text_)
return translated_text_
def azure_ocr_pdf(self,pdf):
pass
def upload_document(self,file):
pass
else:
print("Teeth is not visible")
plt.imshow(dst)
plt.axis("off")
_ = plt.title(name, size="x-large", y=-0.1)
plt.show()
tags_result_remote = computervision_client.tag_image(linkedinphoto)
print("Tags in the remote image")
if(len(tags_result_remote.tags)==0):
print("No tags detected")
else:
for tag in tags_result_remote.tags:
print("'{}' with confidence {:.2f}%".format(tag.name, tag.confidence*100))
print("===== Describe an image - remote =====")
# Call API
description_results = computervision_client.describe_image(linkedinphoto )
# Get the captions (descriptions) from the response, with confidence level
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))
#codes taken from
#https://github.com/mauckc/mouth-open
#https://github.com/omar178/Emotion-recognition
#https://github.com/atulapra/Emotion-detection