def detect_document(path):
"""Detects document features in an image."""
client = vision.ImageAnnotatorClient()
with io.open(path, 'rb') as image_file:
content = image_file.read()
image = vision.types.Image(content=content)
response = client.document_text_detection(image=image)
for page in response.full_text_annotation.pages:
for block in page.blocks:
block_words = []
for paragraph in block.paragraphs:
block_words.extend(paragraph.words)
print(u'Paragraph Confidence: {}\n'.format(
paragraph.confidence))
block_text = ''
block_symbols = []
for word in block_words:
block_symbols.extend(word.symbols)
word_text = ''
for symbol in word.symbols:
word_text = word_text + symbol.text
print(u'\tSymbol text: {} (confidence: {})'.format(
symbol.text, symbol.confidence))
print(u'Word text: {} (confidence: {})\n'.format(
word_text, word.confidence))
block_text += ' ' + word_text
print(u'Block Content: {}\n'.format(block_text))
print(u'Block Confidence:\n {}\n'.format(block.confidence))
def test_batch_annotate_images(self):
# Setup Expected Response
expected_response = {}
expected_response = image_annotator_pb2.BatchAnnotateImagesResponse(
**expected_response
)
# Mock the API response
channel = ChannelStub(responses=[expected_response])
patch = mock.patch("google.api_core.grpc_helpers.create_channel")
with patch as create_channel:
create_channel.return_value = channel
client = vision_v1p1beta1.ImageAnnotatorClient()
# Setup Request
requests = []
response = client.batch_annotate_images(requests)
assert expected_response == response
assert len(channel.requests) == 1
expected_request = image_annotator_pb2.BatchAnnotateImagesRequest(
requests=requests
)
actual_request = channel.requests[0][1]
assert expected_request == actual_request
def __init__(self, result):
self.client = vision.ImageAnnotatorClient()
self.result = {}
self.address_val = {}
self.licence_id = {}
self.result = result
self.ssn = {}
self.name = {}
self.date = {}
self.pay_Val = Queue()
self.keys = []
self.values = []
self.dict = {}
self.date = {}
self.conf_keys, self.conf_values = [], []
self.conf_result = {}
self.emp_name, self.employee_name = {}, {}
self.emp_address, self.employee_address = {}, {}
self.description = []
self.text_val = []
self.location_json = ''
self.regular1, self.regular2, self.regular3, self.regular4, self.regular5, self.regular6, self.regular7, self.regular8, self.regular9, self.regular10 = {}, {}, {}, {}, {}, {}, {}, {}, {}, {}
self.tax1, self.tax2, self.tax3, self.tax4, self.tax5, self.tax6, self.tax7, self.tax8, self.tax9, self.tax10 = {}, {}, {}, {}, {}, {}, {}, {}, {}, {}
self.deduction1, self.deduction2, self.deduction3, self.deduction4, self.deduction5, self.deduction6, self.deduction7, self.deduction8, self.deduction9, self.deduction10, self.deduction11, self.deduction12, self.deduction13, self.deduction14, self.deduction15 = {}, {}, {}, {}, {}, {}, {}, {}, {}, {}, {}, {}, {}, {}, {}
self.pay_start_date, self.pay_end_date, self.pay_date = {}, {}, {}
def annotate_image(imagePath):
apiClient = auth.get_Api_client()
# Instantiates a client
client = vision.ImageAnnotatorClient(credentials=apiClient._credentials)
# The name of the image file to annotate
# file_name = os.path.join(os.path.dirname(__file__), imagePath)
file_name = imagePath
# Loads the image into memory
with io.open(file_name, 'rb') as image_file:
content = image_file.read()
image = types.Image(content=content)
features = [
types.Feature(type=types.Feature.LABEL_DETECTION, max_results=8),
types.Feature(type=types.Feature.LOGO_DETECTION, max_results=8),
types.Feature(type=types.Feature.TEXT_DETECTION, max_results=8),
types.Feature(type=types.Feature.WEB_DETECTION, max_results=15),
# types.Feature(type=types.Feature., max_results=8),
]
request = {
'image': image,
'features': features,
}
response = client.annotate_image(request)
respStr = MessageToJson(response)
responseObj = json.loads(respStr)
return responseObj
def detect_document_uri(uri):
"""Detects document features in the file located in Google Cloud
Storage."""
client = vision.ImageAnnotatorClient()
image = vision.types.Image()
image.source.image_uri = uri
response = client.document_text_detection(image=image)
for page in response.full_text_annotation.pages:
for block in page.blocks:
block_words = []
for paragraph in block.paragraphs:
block_words.extend(paragraph.words)
print(u'Paragraph Confidence: {}\n'.format(
paragraph.confidence))
block_text = ''
block_symbols = []
for word in block_words:
block_symbols.extend(word.symbols)
word_text = ''
for symbol in word.symbols:
word_text = word_text + symbol.text
print(u'\tSymbol text: {} (confidence: {})'.format(
symbol.text, symbol.confidence))
print(u'Word text: {} (confidence: {})\n'.format(
word_text, word.confidence))
block_text += ' ' + word_text
print(u'Block Content: {}\n'.format(block_text))
print(u'Block Confidence:\n {}\n'.format(block.confidence))
def test_batch_annotate_images_exception(self):
# Mock the API response
channel = ChannelStub(responses=[CustomException()])
client = vision_v1p1beta1.ImageAnnotatorClient(channel=channel)
# Setup request
requests = []
with pytest.raises(CustomException):
client.batch_annotate_images(requests)
def detect_web(path):
"""Detects web annotations given an image."""
client = vision_v1p1beta1.ImageAnnotatorClient()
with io.open(path, 'rb') as image_file:
content = image_file.read()
image = vision_v1p1beta1.types.Image(content=content)
# how doe we get this
response = client.web_detection(image=image)
annotations = response.web_detection
for label in annotations.best_guess_labels:
print('\nBest guess label: {}'.format(label.label))
best_g.append(format(label.label))
# def report(annotations):
"""Prints detected features in the provided web annotations."""
if annotations.pages_with_matching_images:
print('\n{} Pages with matching images retrieved'.format(
len(annotations.pages_with_matching_images)))
for page in annotations.pages_with_matching_images:
print('Url : {}'.format(page.url))
# if annotations.best_guess_labels:
# for label in annotations.best_guess_labels:
# print('\nBest guess label: {}'.format(label.label))
if annotations.full_matching_images:
print ('\n{} Full Matches found: '.format(
len(annotations.full_matching_images)))
for image in annotations.full_matching_images:
print('Url : {}'.format(image.url))
if annotations.partial_matching_images:
print ('\n{} Partial Matches found: '.format(
len(annotations.partial_matching_images)))
for image in annotations.partial_matching_images:
print('Url : {}'.format(image.url))
if annotations.web_entities:
print ('\n{} Web entities found: '.format(
len(annotations.web_entities)))
for entity in annotations.web_entities:
print('Score : {}'.format(entity.score))
print('Description: {}'.format(entity.description))
if (entity.score>0.90):
web_scores.append(entity.description)
def web_entities(path):
client = vision.ImageAnnotatorClient()
with io.open(path, 'rb') as image_file:
content = image_file.read()
image = vision.types.Image(content=content)
response = client.web_detection(image=image)
for entity in response.web_detection.web_entities:
print('\n\tScore : {}'.format(entity.score))
print(u'\tDescription: {}'.format(entity.description))
def test_batch_annotate_images_exception(self):
# Mock the API response
channel = ChannelStub(responses=[CustomException()])
patch = mock.patch('google.api_core.grpc_helpers.create_channel')
with patch as create_channel:
create_channel.return_value = channel
client = vision_v1p1beta1.ImageAnnotatorClient()
# Setup request
requests = []
with pytest.raises(CustomException):
client.batch_annotate_images(requests)
def sample_batch_annotate_images():
# Create a client
client = vision_v1p1beta1.ImageAnnotatorClient()
# Initialize request argument(s)
request = vision_v1p1beta1.BatchAnnotateImagesRequest(
)
# Make the request
response = client.batch_annotate_images(request=request)
# Handle the response
print(response)
def detect_web(path):
"""Detects web annotations given an image."""
client = vision.ImageAnnotatorClient()
with io.open(path, 'rb') as image_file:
content = image_file.read()
image = vision.types.Image(content=content)
response = client.web_detection(image=image)
annotations = response.web_detection
if annotations.best_guess_labels:
for label in annotations.best_guess_labels:
print('\nBest guess label: {}'.format(label.label))
if annotations.pages_with_matching_images:
print('\n{} Pages with matching images found:'.format(
len(annotations.pages_with_matching_images)))
for page in annotations.pages_with_matching_images:
print('\n\tPage url : {}'.format(page.url))
if page.full_matching_images:
print('\t{} Full Matches found: '.format(
len(page.full_matching_images)))
for image in page.full_matching_images:
print('\t\tImage url : {}'.format(image.url))
if page.partial_matching_images:
print('\t{} Partial Matches found: '.format(
len(page.partial_matching_images)))
for image in page.partial_matching_images:
print('\t\tImage url : {}'.format(image.url))
if annotations.web_entities:
print('\n{} Web entities found: '.format(len(
annotations.web_entities)))
for entity in annotations.web_entities:
print('\n\tScore : {}'.format(entity.score))
print(u'\tDescription: {}'.format(entity.description))
if annotations.visually_similar_images:
print('\n{} visually similar images found:\n'.format(
len(annotations.visually_similar_images)))
for image in annotations.visually_similar_images:
print('\tImage url : {}'.format(image.url))
def detect_web_uri(uri):
"""Detects web annotations in the file located in Google Cloud Storage."""
client = vision.ImageAnnotatorClient()
image = vision.types.Image()
image.source.image_uri = uri
response = client.web_detection(image=image)
annotations = response.web_detection
if annotations.best_guess_labels:
for label in annotations.best_guess_labels:
print('\nBest guess label: {}'.format(label.label))
if annotations.pages_with_matching_images:
print('\n{} Pages with matching images found:'.format(
len(annotations.pages_with_matching_images)))
for page in annotations.pages_with_matching_images:
print('\n\tPage url : {}'.format(page.url))
if page.full_matching_images:
print('\t{} Full Matches found: '.format(
len(page.full_matching_images)))
for image in page.full_matching_images:
print('\t\tImage url : {}'.format(image.url))
if page.partial_matching_images:
print('\t{} Partial Matches found: '.format(
len(page.partial_matching_images)))
for image in page.partial_matching_images:
print('\t\tImage url : {}'.format(image.url))
if annotations.web_entities:
print('\n{} Web entities found: '.format(len(
annotations.web_entities)))
for entity in annotations.web_entities:
print('\n\tScore : {}'.format(entity.score))
print(u'\tDescription: {}'.format(entity.description))
if annotations.visually_similar_images:
print('\n{} visually similar images found:\n'.format(
len(annotations.visually_similar_images)))
for image in annotations.visually_similar_images:
print('\tImage url : {}'.format(image.url))
def web_entities_include_geo_results_uri(uri):
client = vision.ImageAnnotatorClient()
image = vision.types.Image()
image.source.image_uri = uri
web_detection_params = vision.types.WebDetectionParams(
include_geo_results=True)
image_context = vision.types.ImageContext(
web_detection_params=web_detection_params)
response = client.web_detection(image=image, image_context=image_context)
for entity in response.web_detection.web_entities:
print('\n\tScore : {}'.format(entity.score))
print(u'\tDescription: {}'.format(entity.description))
def web_entities_include_geo_results(path):
client = vision.ImageAnnotatorClient()
with io.open(path, 'rb') as image_file:
content = image_file.read()
image = vision.types.Image(content=content)
web_detection_params = vision.types.WebDetectionParams(
include_geo_results=True)
image_context = vision.types.ImageContext(
web_detection_params=web_detection_params)
response = client.web_detection(image=image, image_context=image_context)
for entity in response.web_detection.web_entities:
print('\n\tScore : {}'.format(entity.score))
print(u'\tDescription: {}'.format(entity.description))
def annotate_image_batch(imagePathes):
apiClient = auth.get_Api_client()
# Instantiates a client
client = vision.ImageAnnotatorClient(credentials=apiClient._credentials)
features = [
types.Feature(type=types.Feature.LABEL_DETECTION),
types.Feature(type=types.Feature.LOGO_DETECTION),
types.Feature(type=types.Feature.TEXT_DETECTION),
types.Feature(type=types.Feature.WEB_DETECTION),
# types.Feature(type=types.Feature., max_results=8),
]
requests = []
for imagePath in imagePathes:
pass
# The name of the image file to annotate
file_name = imagePath
# Loads the image into memory
with io.open(file_name, 'rb') as image_file:
content = image_file.read()
image = types.Image(content=content)
request = {
'image': image,
'features': features,
}
requests.append(request)
responses = []
i = 0
batch = 10
while i < len(requests):
to = min(i + batch, len(requests))
resp = client.batch_annotate_images(requests[i:to])
i = i + batch
for response in resp.responses:
respStr = MessageToJson(response)
tt = json.loads(respStr)
responses.append(tt)
return responses
def detect_safe_search_uri(uri):
"""Detects unsafe features in the file located in Google Cloud Storage or
on the Web."""
client = vision.ImageAnnotatorClient()
image = vision.types.Image()
image.source.image_uri = uri
response = client.safe_search_detection(image=image)
safe = response.safe_search_annotation
# Names of likelihood from google.cloud.vision.enums
likelihood_name = ('UNKNOWN', 'VERY_UNLIKELY', 'UNLIKELY', 'POSSIBLE',
'LIKELY', 'VERY_LIKELY')
print('Safe search:')
print('adult: {}'.format(likelihood_name[safe.adult]))
print('medical: {}'.format(likelihood_name[safe.medical]))
print('spoofed: {}'.format(likelihood_name[safe.spoof]))
print('violence: {}'.format(likelihood_name[safe.violence]))
print('racy: {}'.format(likelihood_name[safe.racy]))
def test_batch_annotate_images(self):
# Setup Expected Response
expected_response = {}
expected_response = image_annotator_pb2.BatchAnnotateImagesResponse(
**expected_response)
# Mock the API response
channel = ChannelStub(responses=[expected_response])
client = vision_v1p1beta1.ImageAnnotatorClient(channel=channel)
# Setup Request
requests = []
response = client.batch_annotate_images(requests)
assert expected_response == response
assert len(channel.requests) == 1
expected_request = image_annotator_pb2.BatchAnnotateImagesRequest(
requests=requests)
actual_request = channel.requests[0][1]
assert expected_request == actual_request
def detect_safe_search(path):
"""Detects unsafe features in the file."""
client = vision.ImageAnnotatorClient()
with io.open(path, 'rb') as image_file:
content = image_file.read()
image = vision.types.Image(content=content)
response = client.safe_search_detection(image=image)
safe = response.safe_search_annotation
# Names of likelihood from google.cloud.vision.enums
likelihood_name = ('UNKNOWN', 'VERY_UNLIKELY', 'UNLIKELY', 'POSSIBLE',
'LIKELY', 'VERY_LIKELY')
print('Safe search:')
print('adult: {}'.format(likelihood_name[safe.adult]))
print('medical: {}'.format(likelihood_name[safe.medical]))
print('spoofed: {}'.format(likelihood_name[safe.spoof]))
print('violence: {}'.format(likelihood_name[safe.violence]))
print('racy: {}'.format(likelihood_name[safe.racy]))
def classify_image(image_name):
os.environ["GOOGLE_APPLICATION_CREDENTIALS"]="/Users/chappers/Documents/DataScience/0_Method_DS/MethodDS-KaggleKat-8b57553f8dbf.json"
# ### Start of Code to classify the image utilising the Google Vision API
# Instantiates a client
client = vision_v1p1beta1.ImageAnnotatorClient()
# The name of the image file to annotate
file_name = os.path.join(
os.path.dirname('__file__'),
image_name)
# Loads the image into memory
with io.open(file_name, 'rb') as image_file:
content = image_file.read()
image = types.Image(content=content)
# Performs label detection on the image file
response = client.label_detection(image=image)
labels = response.label_annotations
# create str_search to be used in the EBAY API call for KEYWORDS
str_search = str(labels[0].description)
# ### Code to utilise the Best Guess Label within Google Vision API
web_scores=[]
best_g=[]
def detect_web(path):
"""Detects web annotations given an image."""
client = vision_v1p1beta1.ImageAnnotatorClient()
with io.open(path, 'rb') as image_file:
content = image_file.read()
image = vision_v1p1beta1.types.Image(content=content)
# how doe we get this
response = client.web_detection(image=image)
annotations = response.web_detection
for label in annotations.best_guess_labels:
print('\nBest guess label: {}'.format(label.label))
best_g.append(format(label.label))
# def report(annotations):
"""Prints detected features in the provided web annotations."""
if annotations.pages_with_matching_images:
print('\n{} Pages with matching images retrieved'.format(
len(annotations.pages_with_matching_images)))
for page in annotations.pages_with_matching_images:
print('Url : {}'.format(page.url))
# if annotations.best_guess_labels:
# for label in annotations.best_guess_labels:
# print('\nBest guess label: {}'.format(label.label))
if annotations.full_matching_images:
print ('\n{} Full Matches found: '.format(
len(annotations.full_matching_images)))
for image in annotations.full_matching_images:
print('Url : {}'.format(image.url))
if annotations.partial_matching_images:
print ('\n{} Partial Matches found: '.format(
len(annotations.partial_matching_images)))
for image in annotations.partial_matching_images:
print('Url : {}'.format(image.url))
if annotations.web_entities:
print ('\n{} Web entities found: '.format(
len(annotations.web_entities)))
for entity in annotations.web_entities:
print('Score : {}'.format(entity.score))
print('Description: {}'.format(entity.description))
if (entity.score>0.90):
web_scores.append(entity.description)
# report(annotate('IMG_2934.jpg'))
detect_web('IMG_2934.jpg')
for rows in range(0,len(web_scores)):
str_search=(str_search+" , "+ web_scores[rows])
# ### Creating keyword string to pass to EBAY API
# Create the Keyword String to then feed into the Ebay API, note the use of brackets and comma's, according to API
# documentation, this then results in items being returned with any of words seperated by comma's, ie. OR logic
keyword_string = best_g[0]
# kstring = keyword_string.split(" ")
keyword_string = str("(" + keyword_string + ")")
keyword_string = keyword_string.replace(" ",",")
return keyword_string
def get_texts_from_bytes(self, content):
client = vision.ImageAnnotatorClient()
image = vision.types.Image(content=content)
response = client.document_text_detection(image=image)
texts = response.text_annotations
return texts, response
