Microsoft Azure Ocr API

openapi: 3.2.0
info:
  version: 2020-08-01-preview
  title: Microsoft Azure AccessControlClient AccessConnector Ocr API
tags:
- name: Ocr
paths:
  /ocr:
    post:
      description: Optical Character Recognition (OCR) detects printed text in an image and extracts the recognized characters into a machine-usable character stream.   Upon success, the OCR results will be returned. Upon failure, the error code together with an error message will be returned. The error code can be one of InvalidImageUrl, InvalidImageFormat, InvalidImageSize, NotSupportedImage,  NotSupportedLanguage, or InternalServerError.
      operationId: microsoftAzureRecognizeprintedtext
      parameters:
      - $ref: '#/components/parameters/DetectOrientation'
      - $ref: ../../../Common/Parameters.json#/parameters/ImageUrl
      - $ref: '#/components/parameters/OcrLanguage'
      responses:
        '200':
          description: The OCR results in the hierarchy of region/line/word. The results include text, bounding box for regions, lines and words.textAngleThe angle, in degrees, of the detected text with respect to the closest horizontal or vertical direction. After rotating the input image clockwise by this angle, the recognized text lines become horizontal or vertical. In combination with the orientation property it can be used to overlay recognition results correctly on the original image, by rotating either the original image or recognition results by a suitable angle around the center of the original image. If the angle cannot be confidently detected, this property is not present. If the image contains text at different angles, only part of the text will be recognized correctly.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OcrResult'
        default:
          description: Error response.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ComputerVisionError'
      x-ms-examples:
        Successful Ocr request:
          $ref: ./examples/SuccessfulOcrWithUrl.json
      summary: Microsoft Azure Post Ocr
      tags:
      - Ocr
components:
  parameters:
    OcrLanguage:
      name: language
      in: query
      description: The BCP-47 language code of the text to be detected in the image. The default value is 'unk'
      required: false
      x-ms-parameter-location: method
      x-ms-enum:
        name: OcrLanguages
        modelAsString: false
      schema:
        type: string
        enum:
        - unk
        - zh-Hans
        - zh-Hant
        - cs
        - da
        - nl
        - en
        - fi
        - fr
        - de
        - el
        - hu
        - it
        - ja
        - ko
        - nb
        - pl
        - pt
        - ru
        - es
        - sv
        - tr
        - ar
        - ro
        - sr-Cyrl
        - sr-Latn
        - sk
        default: unk
    DetectOrientation:
      name: detectOrientation
      in: query
      description: 'Whether detect the text orientation in the image. With detectOrientation=true the OCR service tries to detect the image orientation and correct it before further processing (e.g. if it''s upside-down). '
      required: true
      x-ms-parameter-location: method
      schema:
        type: boolean
        default: true
  schemas:
    OcrRegion:
      type: object
      description: A region consists of multiple lines (e.g. a column of text in a multi-column document).
      properties:
        boundingBox:
          type: string
          description: Bounding box of a recognized region. The four integers represent the x-coordinate of the left edge, the y-coordinate of the top edge, width, and height of the bounding box, in the coordinate system of the input image, after it has been rotated around its center according to the detected text angle (see textAngle property), with the origin at the top-left corner, and the y-axis pointing down.
        lines:
          type: array
          items:
            $ref: '#/components/schemas/OcrLine'
    OcrWord:
      type: object
      description: Information on a recognized word.
      properties:
        boundingBox:
          type: string
          description: Bounding box of a recognized word. The four integers represent the x-coordinate of the left edge, the y-coordinate of the top edge, width, and height of the bounding box, in the coordinate system of the input image, after it has been rotated around its center according to the detected text angle (see textAngle property), with the origin at the top-left corner, and the y-axis pointing down.
        text:
          type: string
          description: String value of a recognized word.
    OcrResult:
      type: object
      properties:
        language:
          type: string
          description: The BCP-47 language code of the text in the image.
        textAngle:
          type: number
          format: double
          description: The angle, in degrees, of the detected text with respect to the closest horizontal or vertical direction. After rotating the input image clockwise by this angle, the recognized text lines become horizontal or vertical. In combination with the orientation property it can be used to overlay recognition results correctly on the original image, by rotating either the original image or recognition results by a suitable angle around the center of the original image. If the angle cannot be confidently detected, this property is not present. If the image contains text at different angles, only part of the text will be recognized correctly.
        orientation:
          type: string
          description: Orientation of the text recognized in the image. The value (up,down,left, or right) refers to the direction that the top of the recognized text is facing, after the image has been rotated around its center according to the detected text angle (see textAngle property).
        regions:
          type: array
          description: An array of objects, where each object represents a region of recognized text.
          items:
            $ref: '#/components/schemas/OcrRegion'
    OcrLine:
      type: object
      description: An object describing a single recognized line of text.
      properties:
        boundingBox:
          type: string
          description: Bounding box of a recognized line. The four integers represent the x-coordinate of the left edge, the y-coordinate of the top edge, width, and height of the bounding box, in the coordinate system of the input image, after it has been rotated around its center according to the detected text angle (see textAngle property), with the origin at the top-left corner, and the y-axis pointing down.
        words:
          type: array
          description: An array of objects, where each object represents a recognized word.
          items:
            $ref: '#/components/schemas/OcrWord'
    ComputerVisionError:
      type: object
      required:
      - code
      - message
      properties:
        code:
          type: string
          description: The error code.
          enum:
          - InvalidImageUrl
          - InvalidImageFormat
          - InvalidImageSize
          - NotSupportedVisualFeature
          - NotSupportedImage
          - InvalidDetails
          - NotSupportedLanguage
          - BadArgument
          - FailedToProcess
          - Timeout
          - InternalServerError
          - Unspecified
          - StorageException
          x-ms-enum:
            name: ComputerVisionErrorCodes
            modelAsString: false
        message:
          type: string
          description: A message explaining the error reported by the service.
        requestId:
          type: string
          description: A unique request identifier.
x-ms-parameterized-host:
  hostTemplate: '{endpoint}'
  useSchemePrefix: false
  parameters:
  - $ref: '#/components/parameters/Endpoint'