ImageCaptioningQuickstart.py

'''
Computer Vision Quickstart for Microsoft Azure Cognitive Services. 
Uses local and remote images in each example.
Prerequisites:
    - Install the Computer Vision SDK:
      pip install --upgrade azure-cognitiveservices-vision-computervision
    - Install PIL:
      pip install --upgrade pillow
    - Create folder and collect images: 
      Create a folder called "images" in the same folder as this script.
      Go to this website to download images:
        https://github.com/Azure-Samples/cognitive-services-sample-data-files/tree/master/ComputerVision/Images
      Add the following 7 images (or use your own) to your "images" folder: 
        faces.jpg, gray-shirt-logo.jpg, handwritten_text.jpg, landmark.jpg, 
        objects.jpg, printed_text.jpg and type-image.jpg
Run the entire file to demonstrate the following examples:
    - Describe Image
    - Categorize Image
    - Tag Image
References:
    - SDK: https://docs.microsoft.com/en-us/python/api/azure-cognitiveservices-vision-computervision/azure.cognitiveservices.vision.computervision?view=azure-python
    - Documentaion: https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/index
    - API: https://westus.dev.cognitive.microsoft.com/docs/services/computer-vision-v3-2/operations/5d986960601faab4bf452005
'''

# <snippet_imports_and_vars>
# <snippet_imports>
from azure.cognitiveservices.vision.computervision import ComputerVisionClient
from azure.cognitiveservices.vision.computervision.models import OperationStatusCodes
from azure.cognitiveservices.vision.computervision.models import VisualFeatureTypes
from msrest.authentication import CognitiveServicesCredentials

from array import array
import os
from PIL import Image
import sys
import time
# </snippet_imports>

'''
Authenticate
Authenticates your credentials and creates a client.
'''
# <snippet_vars>
subscription_key = "PASTE_YOUR_COMPUTER_VISION_SUBSCRIPTION_KEY_HERE"
endpoint = "PASTE_YOUR_COMPUTER_VISION_ENDPOINT_HERE"
# </snippet_vars>
# </snippet_imports_and_vars>

# <snippet_client>
computervision_client = ComputerVisionClient(endpoint, CognitiveServicesCredentials(subscription_key))
# </snippet_client>
'''
END - Authenticate
'''

'''
Quickstart variables
These variables are shared by several examples
'''
# Images used for the examples: Describe an image, Categorize an image, Tag an image, 
# Detect faces, Detect adult or racy content, Detect the color scheme, 
# Detect domain-specific content, Detect image types, Detect objects
images_folder = os.path.join (os.path.dirname(os.path.abspath(__file__)), "images")
# <snippet_remoteimage>
remote_image_url = "https://moderatorsampleimages.blob.core.windows.net/samples/sample16.png"
# </snippet_remoteimage>
'''
END - Quickstart variables
'''

'''
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 = os.path.join (images_folder, "faces.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 ( not description_result.captions):
    print("No description detected.")
else:
    for caption in description_result.captions:
        print("'{}' with confidence {:.2f}%".format(caption.text, caption.confidence * 100))
print()
'''
END - Describe an Image - local
'''

# <snippet_features_remote>
print("===== Analyze an image - remote =====")
# Select the visual feature(s) you want.
remote_image_features = ['description','tags']
# </snippet_features_remote>

# <snippet_analyze>
# Call API with URL and features
results_remote = computervision_client.analyze_image(remote_image_url , remote_image_features)

# Describe image
# Get the captions (descriptions) from the response, with confidence level
print("Description of remote image: ")
if ( not results_remote.description):
    print("No description detected.")
else:
    for caption in results_remote.description.captions:
        print("'{}' with confidence {:.2f}%".format(caption.text, caption.confidence * 100))
print()

# Return tags
# Print results with confidence score
print("Tags in the remote image: ")
if (len(results_remote.tags) == 0):
    print("No tags detected.")
else:
    for tag in results_remote.tags:
        print("'{}' with confidence {:.2f}%".format(tag.name, tag.confidence * 100))


# </snippet_analyze>


'''
Tag an Image - local
This example returns a tag (key word) for each thing in the image.
'''
print("===== Tag an Image - local =====")
# Open local image file
local_image = open(local_image_path, "rb")
# Call API local image
tags_result_local = computervision_client.tag_image_in_stream(local_image)

# Print results with confidence score
print("Tags in the local image: ")
if (len(tags_result_local.tags) == 0):
    print("No tags detected.")
else:
    for tag in tags_result_local.tags:
        print("'{}' with confidence {:.2f}%".format(tag.name, tag.confidence * 100))
print()
'''
END - Tag an Image - local
'''

print("End of Computer Vision quickstart.")