Microsoft Cognitive Services ImageAnalysis API

openapi: 3.1.0
info:
  title: Azure AI Vision - Image Analysis REST ImageAnalysis API
  description: 'Azure AI Vision Image Analysis 4.0 REST API. Synchronously analyzes an

    input image and returns combined results: tags, objects, caption,

    denseCaptions, read (OCR), smartCrops, and people detection. Supports

    image stream upload (image/* or application/octet-stream) or a JSON

    body with a publicly reachable URL.


    Authentication uses the subscription key in the Ocp-Apim-Subscription-Key

    header, or a Microsoft Entra ID OAuth 2.0 bearer token (Cognitive

    Services User role).


    The Azure AI Services umbrella also includes Speech, Language, and

    Azure OpenAI; only the Image Analysis surface is fully described here.

    '
  version: 2023-04-01-preview
  contact:
    name: Kin Lane
    email: kin@apievangelist.com
  license:
    name: Microsoft Terms of Use
    url: https://www.microsoft.com/en-us/legal/terms-of-use
servers:
- url: https://{endpoint}
  description: Cognitive Services regional endpoint
  variables:
    endpoint:
      default: westus.api.cognitive.microsoft.com
      description: Per-region Cognitive Services endpoint
security:
- subscription_key: []
- azure_auth: []
tags:
- name: ImageAnalysis
  description: Analyze images for visual features
paths:
  /computervision/imageanalysis:analyze:
    post:
      tags:
      - ImageAnalysis
      summary: Analyze an image
      operationId: imageAnalysis_analyze
      parameters:
      - name: api-version
        in: query
        required: true
        schema:
          type: string
          default: 2023-04-01-preview
      - name: features
        in: query
        schema:
          type: array
          items:
            type: string
            enum:
            - tags
            - caption
            - denseCaptions
            - objects
            - read
            - smartCrops
            - people
        description: Visual features to extract; required if model-name is not provided
      - name: model-name
        in: query
        schema:
          type: string
        description: Custom trained model name; required if features is not provided
      - name: language
        in: query
        schema:
          type: string
          default: en
      - name: smartcrops-aspect-ratios
        in: query
        schema:
          type: string
        description: Comma-separated aspect ratios for smartCrops (0.75-1.8)
      - name: gender-neutral-caption
        in: query
        schema:
          type: boolean
          default: false
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ImageUrl'
          application/octet-stream:
            schema:
              type: string
              format: binary
          image/jpeg:
            schema:
              type: string
              format: binary
          image/png:
            schema:
              type: string
              format: binary
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ImageAnalysisResult'
        default:
          description: Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  schemas:
    DetectedObject:
      type: object
      properties:
        id:
          type: string
        boundingBox:
          $ref: '#/components/schemas/BoundingBox'
        tags:
          type: array
          items:
            $ref: '#/components/schemas/Tag'
    ErrorResponse:
      type: object
      properties:
        error:
          type: object
          properties:
            code:
              type: string
            message:
              type: string
            target:
              type: string
            innererror:
              type: object
    DetectedPerson:
      type: object
      properties:
        boundingBox:
          $ref: '#/components/schemas/BoundingBox'
        confidence:
          type: number
          format: double
    ImageUrl:
      type: object
      required:
      - url
      properties:
        url:
          type: string
          format: uri
          description: Publicly reachable URL of an image
    DenseCaptionsResult:
      type: object
      properties:
        values:
          type: array
          items:
            $ref: '#/components/schemas/DenseCaption'
    ImageAnalysisResult:
      type: object
      properties:
        modelVersion:
          type: string
        metadata:
          $ref: '#/components/schemas/ImageMetadata'
        captionResult:
          $ref: '#/components/schemas/CaptionResult'
        denseCaptionsResult:
          $ref: '#/components/schemas/DenseCaptionsResult'
        tagsResult:
          $ref: '#/components/schemas/TagsResult'
        objectsResult:
          $ref: '#/components/schemas/ObjectsResult'
        peopleResult:
          $ref: '#/components/schemas/PeopleResult'
        readResult:
          $ref: '#/components/schemas/ReadResult'
        smartCropsResult:
          $ref: '#/components/schemas/SmartCropsResult'
    SmartCropsResult:
      type: object
      properties:
        values:
          type: array
          items:
            type: object
            properties:
              aspectRatio:
                type: number
                format: double
              boundingBox:
                $ref: '#/components/schemas/BoundingBox'
    DenseCaption:
      type: object
      properties:
        text:
          type: string
        confidence:
          type: number
          format: double
        boundingBox:
          $ref: '#/components/schemas/BoundingBox'
    CaptionResult:
      type: object
      properties:
        text:
          type: string
        confidence:
          type: number
          format: double
    ImageMetadata:
      type: object
      properties:
        width:
          type: integer
        height:
          type: integer
    ObjectsResult:
      type: object
      properties:
        values:
          type: array
          items:
            $ref: '#/components/schemas/DetectedObject'
    TagsResult:
      type: object
      properties:
        values:
          type: array
          items:
            $ref: '#/components/schemas/Tag'
    ReadResult:
      type: object
      properties:
        content:
          type: string
        pages:
          type: array
          items:
            type: object
        stringIndexType:
          type: string
    BoundingBox:
      type: object
      properties:
        x:
          type: integer
        y:
          type: integer
        w:
          type: integer
        h:
          type: integer
    PeopleResult:
      type: object
      properties:
        values:
          type: array
          items:
            $ref: '#/components/schemas/DetectedPerson'
    Tag:
      type: object
      properties:
        name:
          type: string
        confidence:
          type: number
          format: double
  securitySchemes:
    subscription_key:
      type: apiKey
      in: header
      name: Ocp-Apim-Subscription-Key
      description: Cognitive Services subscription key
    azure_auth:
      type: oauth2
      description: Microsoft Entra ID OAuth 2.0
      flows:
        clientCredentials:
          tokenUrl: https://login.microsoftonline.com/common/oauth2/v2.0/token
          scopes:
            https://cognitiveservices.azure.com/.default: Cognitive Services access