Adapter - Azure Vision
This page describes version 2.0.7 of the adapter.
Overview
This adapter uses the Microsoft Azure Vision service to analyze an image by providing captions that explain the image, and also categorizing the contents of the image.
Details on the functionality provided by the Azure Vision API can be found at Azure Vision.
Properties
| Name | Display | Is Required | Comments | Type | Default Value | Maximum Value | Minimum Value | Maximum Length | Minimum Length |
|---|---|---|---|---|---|---|---|---|---|
| visionSubscriptionKey | Vision Subscription Key | True | Subscription Key for the Vision API. | password | 1024 | 1 | |||
| visionApiUrl | Vision Api URL | True | URL to the Vision API. | string | 1024 | 1 |
Commands
Analyze Image (analyzeImage)
Return information about the visual content found in an image.
Request Properties
| Name | Display | Description | Is Required | Type |
|---|---|---|---|---|
| image | image | Input image. | True | string |
Response Properties
| Name | Description | Type |
|---|---|---|
| requestId | Request Id uniquely identifies each request made to the Azure Api. | string |
| captions | An array of captions that describe the input image. | array |
| captions.text | The text that describes the input image. | string |
| captions.confidence | The confidence score that rates how close the caption fits the image. | string |
| descriptionTags | Description Tags. | array |
| descriptionTags.text | The text value of the Description Tag. | string |
| tags | An array of tags detected in the image. | array |
| tags.name | The name of the tag detected in the image. | string |
| tags.hint | A hint associated with the tag detected in the image. | string |
| tags.confidence | The confidence score that denotes how well the tag describes the image. | string |
| categories | An array of categories detected in the image. | array |
| categories.name | The name of the category detected in the image. | string |
| categories.score | The score that denotes how well the category describes the image. | string |
| faces | An array of faces detected in the image. | array |
| faces.age | The approximate age of the detected face. | string |
| faces.gender | The gender of the detected face. | string |
| faces.height | The height of the face rectangle. | string |
| faces.width | The width of the face rectangle. | string |
| faces.top | The top point of the face rectangle. | string |
| faces.left | The left point of the face rectangle. | string |
Recognize Text (recognizeText)
Detect the text in an image and extract into machine readable words.
Request Properties
| Name | Display | Description | Is Required | Type |
|---|---|---|---|---|
| image | Image | Input image. | True | string |
Response Properties
| Name | Description | Type |
|---|---|---|
| regions | An array of regions in the image. | array |
| regions.regionText | The concatenated text for this region. | string |
Release History
| Version | Type | Description | Tracking # | Date |
|---|---|---|---|---|
| 2.0.1 | Initial | First release in the Adapter Type store. | ||
| 2.0.5 | Maintenance | Updated third-party components and improved maintainability. | NAP-11518 | |
| 2.0.6 | Maintenance | Updated third-party components and improved maintainability. | NAP-23945 | 2022-11-30 |
| 2.0.7 | Maintenance | Updated third-party components and improved maintainability. | NAP-27635 | 2024-07-31 |