Skip to main content

ImageAnnotator_CreateImageAnnotation

ImageAnnotator_CreateImageAnnotation

Path Parameters
  • user string required

    The user id.

Request Body required
  • parent string

    The parent this image annotation belongs to.

  • annotation object
    • name string

      The annotation resource name.

    • resource string

      The annotated image.

    • annotations object
      • textAnnotations object[]

        The texts detected in the image.

        • property object

          Additional information detected on the structural component.

          • languages object[]

            A list of detected languages together with confidence.

            • languageCode string

              The BCP-47 language code, such as "en-US" or "sr-Latn".

            • confidence float

              Confidence of detected language. Range [0, 1].

        • boundingBox object

          A bounding polygon for the detected image annotation.

          • vertices object[]

            The bounding polygon vertices.

            • x int32

              X coordinate.

            • y int32

              Y coordinate.

        • text string

          UTF-8 text detected by the OCR.

        • confidence float

          Confidence of the OCR results for the paragraph. Range [0, 1].

      • labelAnnotations object[]

        The labels detected in the image.

        • name string

          The label resource name.

        • score float

          Overall score of the result. Range [0, 1].

        • topicality float

          The relevancy of the annotation. Range [0, 1].

      • entityAnnotations object[]

        The entites detected in the image.

        • name string

          The entity resource name.

        • score float

          Overall score of the result. Range [0, 1].

        • boundingBox object

          A bounding polygon for the detected image annotation.

          • vertices object[]

            The bounding polygon vertices.

            • x int32

              X coordinate.

            • y int32

              Y coordinate.

      • knowledgeGraphAnnotations object[]

        The Animeshon Graph Knowledge-Base resources detected in the image.

        • resource string

          The Animeshon Graph Knowledge-Base resource name.

        • score float

          Overall score of the result. Range [0, 1].

        • boundingBox object

          A bounding polygon for the detected image annotation.

          • vertices object[]

            The bounding polygon vertices.

            • x int32

              X coordinate.

            • y int32

              Y coordinate.

      • webSearchAnnotations object[]

        The WebSearch resources (pages and images) detected in the image.

        • url string

          The result image URL.

        • score float

          Overall relevancy score for the image.

      • safeSearchAnnotation object
        • adult enum

          Possible values: [UNKNOWN, VERY_UNLIKELY, UNLIKELY, POSSIBLE, LIKELY, VERY_LIKELY]

          Represents the adult content likelihood for the image. Adult content may contain elements such as nudity, pornographic images or cartoons, or sexual activities.

        • racy enum

          Possible values: [UNKNOWN, VERY_UNLIKELY, UNLIKELY, POSSIBLE, LIKELY, VERY_LIKELY]

          Likelihood that the request image contains racy content. Racy content may include (but is not limited to) skimpy or sheer clothing, strategically covered nudity, lewd or provocative poses, or close-ups of sensitive body areas.

        • violence enum

          Possible values: [UNKNOWN, VERY_UNLIKELY, UNLIKELY, POSSIBLE, LIKELY, VERY_LIKELY]

          Likelihood that this image contains violent content.

        • medical enum

          Possible values: [UNKNOWN, VERY_UNLIKELY, UNLIKELY, POSSIBLE, LIKELY, VERY_LIKELY]

          Likelihood that this is a medical image.

        • juvenile enum

          Possible values: [UNKNOWN, VERY_UNLIKELY, UNLIKELY, POSSIBLE, LIKELY, VERY_LIKELY]

          Likelihood that the request image contains one or more individuals decipted as juveniles. Juvenile content may contain elements such as school-aged children, preschoolers, toddlers, infants, and newborns. The target age considered as juvenile is from 0 to 14~16 years old.

    • createTime date-time

      The timestamp at which the annotation was created.

    • updateTime date-time

      The latest timestamp at which the annotation was updated.

Responses

OK

Schema
  • name string

    The annotation resource name.

  • resource string

    The annotated image.

  • annotations object
    • textAnnotations object[]

      The texts detected in the image.

      • property object

        Additional information detected on the structural component.

        • languages object[]

          A list of detected languages together with confidence.

          • languageCode string

            The BCP-47 language code, such as "en-US" or "sr-Latn".

          • confidence float

            Confidence of detected language. Range [0, 1].

      • boundingBox object

        A bounding polygon for the detected image annotation.

        • vertices object[]

          The bounding polygon vertices.

          • x int32

            X coordinate.

          • y int32

            Y coordinate.

      • text string

        UTF-8 text detected by the OCR.

      • confidence float

        Confidence of the OCR results for the paragraph. Range [0, 1].

    • labelAnnotations object[]

      The labels detected in the image.

      • name string

        The label resource name.

      • score float

        Overall score of the result. Range [0, 1].

      • topicality float

        The relevancy of the annotation. Range [0, 1].

    • entityAnnotations object[]

      The entites detected in the image.

      • name string

        The entity resource name.

      • score float

        Overall score of the result. Range [0, 1].

      • boundingBox object

        A bounding polygon for the detected image annotation.

        • vertices object[]

          The bounding polygon vertices.

          • x int32

            X coordinate.

          • y int32

            Y coordinate.

    • knowledgeGraphAnnotations object[]

      The Animeshon Graph Knowledge-Base resources detected in the image.

      • resource string

        The Animeshon Graph Knowledge-Base resource name.

      • score float

        Overall score of the result. Range [0, 1].

      • boundingBox object

        A bounding polygon for the detected image annotation.

        • vertices object[]

          The bounding polygon vertices.

          • x int32

            X coordinate.

          • y int32

            Y coordinate.

    • webSearchAnnotations object[]

      The WebSearch resources (pages and images) detected in the image.

      • url string

        The result image URL.

      • score float

        Overall relevancy score for the image.

    • safeSearchAnnotation object
      • adult enum

        Possible values: [UNKNOWN, VERY_UNLIKELY, UNLIKELY, POSSIBLE, LIKELY, VERY_LIKELY]

        Represents the adult content likelihood for the image. Adult content may contain elements such as nudity, pornographic images or cartoons, or sexual activities.

      • racy enum

        Possible values: [UNKNOWN, VERY_UNLIKELY, UNLIKELY, POSSIBLE, LIKELY, VERY_LIKELY]

        Likelihood that the request image contains racy content. Racy content may include (but is not limited to) skimpy or sheer clothing, strategically covered nudity, lewd or provocative poses, or close-ups of sensitive body areas.

      • violence enum

        Possible values: [UNKNOWN, VERY_UNLIKELY, UNLIKELY, POSSIBLE, LIKELY, VERY_LIKELY]

        Likelihood that this image contains violent content.

      • medical enum

        Possible values: [UNKNOWN, VERY_UNLIKELY, UNLIKELY, POSSIBLE, LIKELY, VERY_LIKELY]

        Likelihood that this is a medical image.

      • juvenile enum

        Possible values: [UNKNOWN, VERY_UNLIKELY, UNLIKELY, POSSIBLE, LIKELY, VERY_LIKELY]

        Likelihood that the request image contains one or more individuals decipted as juveniles. Juvenile content may contain elements such as school-aged children, preschoolers, toddlers, infants, and newborns. The target age considered as juvenile is from 0 to 14~16 years old.

  • createTime date-time

    The timestamp at which the annotation was created.

  • updateTime date-time

    The latest timestamp at which the annotation was updated.