Microsoft Object Detection
Microsoft Object Detection detects objects, faces, and landmarks using Azure Computer Vision. The service detects objects within images and returns the Metadata of objects contained in the image in the form of a list of Tags. For example, if a person is present in the image, tags may include facial features, such as nose, ear, lip, etc. The Best Caption that best describes the image and gives the context of the image is also returned.
Consider the example below of a blonde woman; the image has been categorized as a "people_portrait", and the caption was returned as "a woman with blonde hair".
Furthermore, Face Detection has supplied the gender and the estimated age of the woman.
It is also specified that the image does not contain any racy or offensive material.
Supported Content Types
- Images
If you need to use a different type of content, you can use the AIForged Pdf Converter.
Possible use cases
- Detect faces and estimate the age of a person.
- Detect emotions and ages on faces.
- Identify the setting/nature of a picture.
- Determine whether an image can contain offensive material.
- Get a count of similar objects (e.g. counting cars).
Service Setup
- Open the Project Detail View of the project you would like to add the service to.
- Click on the Add Service button in the command bar.\ (2).png>)
Select the Microsoft Object Detection Service.
A new Service Configuration Wizard will open:\ (When navigating the Wizard, please make sure to use the Next Step button in the command bar to save any changes made).
Step 1 - Service Config (Displays the service setting, you can change it as required).
- Click the “Next” Action in the Action Bar to save the Service.
- Step 2 - Verification. No verification required.
Service Configuration Settings
The Microsoft OCR Service can be configured by the user as a flexible solution. The following Settings are available:
Setting | Type | Required Type | Description |
---|---|---|---|
ArchivingStrategy | Optional | Days before documents get deleted. | |
AccessKey | Optional | Override the Access Key to the configured Microsoft cloud service. | |
BaseURL | Optional | Override the URL to the configured Microsoft cloud service. | |
BatchSize | Hidden | Processing batch size. | |
DocumentProcessedStatus | Optional | Document status used to denote that a document has been processed. | |
Enabled | Hidden | Enable or disable the service. | |
ExecuteBeforeProcess | When set up as a child service, specify whether this service should be executed before the parent service gets executed. | ||
ExecuteAfterProcess | When set up as a child service, specify whether this service should be executed after the parent service gets executed. | ||
Language | Optional | Hint at the language to use when performing OCR. | |
Password | Optional | Used for service authentication. Custom Code can be used to set the password. Can be set per document. | |
RemoveComments | Optional | Remove human comments from a document. |
Add and Process Documents
- In the Microsoft Object Detection Service click on Inbox button.
- Select the Status you want to upload and use Status None or Received for new documents that have not been processed yet.
- Select an optional category if you know the category for the document, if you don’t want to select one just click on “No selection”.
- Find the files on your Local machine and upload them. The demo's test files can be found at the following link: Click here
- After all the documents have been uploaded you can check the documents to be processed, click on Processed Checked to process the documents.
It is recommended to only process a few documents at a time, especially if it is a new service to properly test if you receive the results you want before processing everything.
View Processed Documents
- In the Microsoft Object Detection Service click on Outbox button.
- You can view your Processing results by opening a processed doc for verification.