Analyse Images With Computer Vision Service Flashcards
The computer vision service and Abel software engineers to create intelligent Solutions that extract information from images; a common task in many artificial intelligence scenarios
Computer vision:
Computer vision is one of the core areas of artificial intelligence and Focuses on creating Solutions that enable applications to see the world and make sense of it.
Some potential uses for computer vision include:
Content organisation Caroline identify people or objects and photos and organise them based on that identification. Photo recognitions applications like this are commonly used in photo storage and social media applications.
Text extraction Caroline and lies images in PDF documents that contain texts and extract the text into a structured format.
Spatial analysis: identify people or objects such as cars in a space and map there in movement within that space
To nai application and images with an array of pixel values.
These numeric values can be used as features to train machine learning models that make predictions about the image and its contents.
Training machine learning models from scratch can be very time-intensive and require a large amount of data. Microsoft computer vision service gives you access to free train computer vision capabilities
Image analysis on azure: The computer vision service is a cognitive service in Microsoft azure that provides free build computer vision capabilities.
The service can analyse images and return detail information about an image and the objects it depicts
As your resources for computer vision:
To use the computer vision service you need to create a resource for thin your as your subscription. You can use either of the following resource types:
Computer vision turn on a specified resource for the computer vision service will stop users resourcetype if you don’t intend to use any other cognitive services or if you want to track utilisation and costs for your computer vision Resource separately.
Cognitive Services: a general cognitive services resource that includes computer vision along with many other cognitive services; such as text Analytics text translator and others. Use as a resource type if you plan to use multiple cognitive services and want to simplify administration and development.
The Resource you choose to create will provide two pieces of information that you will need to use it:
A key that is used to authenticate client applications.
And Endpoint that provides HTTP address at which a resource can be accessed.
Note if you create a cognitive services resource client applications use the same key and Endpoint regardless of the specific service they are using
Analysing images with computer vision service:
After you’ve created a suitable resource in your subscription you can submit images to the computer vision service to perform a wide range of analytical tasks.
Tasks may range from describing an image
Tagging visual features
Detecting objects
Detecting Brian’s new line to taking faces
Categorising and image
Detecting domain specific content
Optical character recognition
Describing an image on new line computer vision has the ability to analyse and emerged evaluate the objects that are detected and generate a human readable phrase or sentence that can describe what was detected in the image. Depending on the image contents the service may return multiple results or phrases.
Each phrase will have an associated confidence score indicating how confident the algorithm is in the supplied description.
The highest confidence phrases will be listed first
Example:
A black and white photo of a city
A black and white photo of a large city
A large white building in a city
Detecting objects:
The object detection capability is similar to tagging in that the service can identify common objects but rather than tagging or providing tags for the recognised objects only the service can also return what’s known as box coordinates. Not only will you get the type of object but you will also receive a set of coordinates that indicates the top left with and height of the object detected which you can use to identify the object the location of the object and the image.
Detecting brands:
This feature provides the ability to identify commercial brands. This service has an existing database of thousands of globally recognised logos from commercial brands of products.
When you call on the service and pass it an image that performs a detection task and determines if any of the identified objects in the images are recognised brands.
The syllabus Compares the brand’s against its starter base of populous burning clothing consumer electronics and many more categories. If a known brand is detected the service Returns a response that contains the brand name a confident score from 0 to 1 indicating how positive the identification is and a bounding box or coordinates for where the image for where in the image of the detected brand was found
Detecting faces:
The computer vision service can detect and analyse human faces in an image including the ability to determine age and a bounding box rectangle for the location of the faces.
The facial analysis capabilities of the computer vision service are a subset of those provided by the dedicated face service. If you need basic face detection and analysis combined with general image analysis capabilities you can use the computer vision service; but for more comprehensive facial analysis and facial recognition functionality use the face service.
Categorising an image: Computer vision can categorise images based on their contents.
The service uses a parent slash child hierarchy with a current limited set of categories. When analysing an image detected objects are compared to the existing categories to determine the best way to provide the categorisation.
As an example of one of the parent categories is people. This example image is of a person on a roof is assigned to the category of people
A slightly different categorisation is Returned for the following image which is assigned to the category people slash group because there are multiple people in the image the example photo being a photo of multiple people
Detecting domain specific content: Celebrities: the service includes a model that has been trained to identify thousands of well-known celebrities from the world of sports entertainment and business.
Landmarks turn on the service can identify famous landmarks such as the Taj Mahal and the Statue of Liberty
Optimal character recognition:
The computer vision service can use optical character recognition or a RC capabilities to detect printed and handwritten text and images.
This capability is explored in the read text with with the computer vision service module on Microsoft
Additional capabilities:
In addition to these capabilities to computer vision service can:
Detect image types-for example identifying clip art images or line art drawings.
Detect image colour schemes-specific specifically identifying the dominant foreground background and over all colours in an image.
Generate thumbnails-creating small versions of images.
Moderate content-detecting images that contain adult content or depict violent or gory scenes
