Amazon Rekognition · JSON Structure

Amazon Rekognition Detect Text Response Structure

DetectTextResponse schema from Amazon Rekognition

Type: object Properties: 2
Celebrity RecognitionComputer VisionContent ModerationCustom LabelsDeep LearningFace LivenessFacial RecognitionImage AnalysisMachine LearningObject DetectionText DetectionVideo Analysis

DetectTextResponse is a JSON Structure definition published by Amazon Rekognition, describing 2 properties. It conforms to the https://json-structure.org/meta/core/v0/# meta-schema.

Properties

TextDetections TextModelVersion

Meta-schema: https://json-structure.org/meta/core/v0/#

JSON Structure

Raw ↑
{
  "$schema": "https://json-structure.org/meta/core/v0/#",
  "$id": "https://raw.githubusercontent.com/api-evangelist/amazon-rekognition/refs/heads/main/json-structure/amazon-rekognition-detect-text-response-structure.json",
  "name": "DetectTextResponse",
  "description": "DetectTextResponse schema from Amazon Rekognition",
  "type": "object",
  "properties": {
    "TextDetections": {
      "type": "array",
      "description": "An array of text detected in the input image.",
      "items": {
        "type": "object",
        "properties": {
          "DetectedText": {
            "type": "string",
            "example": "Hello World"
          },
          "Type": {
            "type": "string",
            "enum": [
              "LINE",
              "WORD"
            ]
          },
          "Id": {
            "type": "int32"
          },
          "ParentId": {
            "type": "int32"
          },
          "Confidence": {
            "type": "float"
          },
          "Geometry": {
            "type": "object",
            "properties": {
              "BoundingBox": {
                "$ref": "#/components/schemas/BoundingBox"
              }
            }
          }
        }
      }
    },
    "TextModelVersion": {
      "type": "string",
      "example": "3.1"
    }
  }
}