Get started
Yandex Vision

Method batchAnalyze

Analyzes a batch of images and returns results with annotations.

HTTP request

POST https://vision.api.cloud.yandex.net/vision/v1/batchAnalyze

Body parameters

{
  "analyzeSpecs": [
    {
      "features": [
        {
          "type": "string",

          // `analyzeSpecs[].features[]` includes only one of the fields `classificationConfig`, `textDetectionConfig`
          "classificationConfig": {
            "model": "string"
          },
          "textDetectionConfig": {
            "languageCodes": [
              "string"
            ],
            "model": "string"
          },
          // end of the list of possible fields`analyzeSpecs[].features[]`

        }
      ],
      "mimeType": "string",

      // `analyzeSpecs[]` includes only one of the fields `content`, `signature`
      "content": "string",
      "signature": "string",
      // end of the list of possible fields`analyzeSpecs[]`

    }
  ],
  "folderId": "string"
}
Field Description
analyzeSpecs[] object

Required. A list of specifications. Each specification contains the file to analyze and features to use for analysis.

Restrictions:

  • Supported file formats: JPEG, PNG.
  • Maximum file size: 1 MB.
  • Image size should not exceed 20M pixels (length x width).

The number of elements must be in the range 1-8.
analyzeSpecs[].
features[]		 object

Required. Requested features to use for analysis.

Max count of requested features for one file is 8.

The number of elements must be in the range 1-8.
analyzeSpecs[].
features[].
type		 string
Type of requested feature.
  • TEXT_DETECTION: Text detection (OCR) feature.
  • CLASSIFICATION: Classification feature.
  • FACE_DETECTION: Face detection feature.
  • IMAGE_COPY_SEARCH: Image copy search.
analyzeSpecs[].
features[].
classificationConfig		 object
Required for the CLASSIFICATION type. Specifies configuration for the classification feature.
analyzeSpecs[].features[] includes only one of the fields classificationConfig, textDetectionConfig
analyzeSpecs[].
features[].
classificationConfig.
model		 string

Model to use for image classification.

The maximum string length in characters is 256.
analyzeSpecs[].
features[].
textDetectionConfig		 object
Required for the TEXT_DETECTION type. Specifies configuration for the text detection (OCR) feature.
analyzeSpecs[].features[] includes only one of the fields classificationConfig, textDetectionConfig
analyzeSpecs[].
features[].
textDetectionConfig.
languageCodes[]		 string

Required. List of the languages to recognize text. Specified in ISO 639-1 format (for example, ru).

The number of elements must be in the range 1-8. The maximum string length in characters for each value is 3.
analyzeSpecs[].
features[].
textDetectionConfig.
model		 string

Model to use for text detection. Possible values:

  • page (default) — this model is suitable for detecting multiple text entries in an image.
  • line — this model is suitable for cropped images with one line of text.

The maximum string length in characters is 50.
analyzeSpecs[].
mimeType		 string

MIME type of content (for example, application/pdf).

The maximum string length in characters is 255.
analyzeSpecs[].
content		 string (byte)
analyzeSpecs[] includes only one of the fields content, signature

Image content, represented as a stream of bytes. Note: As with all bytes fields, protobuffers use a pure binary representation, whereas JSON representations use base64.

The maximum string length in characters is 10485760.
analyzeSpecs[].
signature		 string
analyzeSpecs[] includes only one of the fields content, signature

The maximum string length in characters is 16384.
folderId string

ID of the folder to which you have access. Required for authorization with a user account (see UserAccount resource). Don't specify this field if you make the request on behalf of a service account.

The maximum string length in characters is 50.

Response

HTTP Code: 200 - OK

{
  "results": [
    {
      "results": [
        {
          "error": {
            "code": "integer",
            "message": "string",
            "details": [
              "object"
            ]
          },

          // `results[].results[]` includes only one of the fields `textDetection`, `classification`, `faceDetection`, `imageCopySearch`
          "textDetection": {
            "pages": [
              {
                "width": "string",
                "height": "string",
                "blocks": [
                  {
                    "boundingBox": {
                      "vertices": [
                        {
                          "x": "string",
                          "y": "string"
                        }
                      ]
                    },
                    "lines": [
                      {
                        "boundingBox": {
                          "vertices": [
                            {
                              "x": "string",
                              "y": "string"
                            }
                          ]
                        },
                        "words": [
                          {
                            "boundingBox": {
                              "vertices": [
                                {
                                  "x": "string",
                                  "y": "string"
                                }
                              ]
                            },
                            "text": "string",
                            "confidence": "number",
                            "languages": [
                              {
                                "languageCode": "string",
                                "confidence": "number"
                              }
                            ],
                            "entityIndex": "string"
                          }
                        ],
                        "confidence": "number"
                      }
                    ]
                  }
                ],
                "entities": [
                  {
                    "name": "string",
                    "text": "string"
                  }
                ]
              }
            ]
          },
          "classification": {
            "properties": [
              {
                "name": "string",
                "probability": "number"
              }
            ]
          },
          "faceDetection": {
            "faces": [
              {
                "boundingBox": {
                  "vertices": [
                    {
                      "x": "string",
                      "y": "string"
                    }
                  ]
                }
              }
            ]
          },
          "imageCopySearch": {
            "copyCount": "string",
            "topResults": [
              {
                "imageUrl": "string",
                "pageUrl": "string",
                "title": "string",
                "description": "string"
              }
            ]
          },
          // end of the list of possible fields`results[].results[]`

        }
      ],
      "error": {
        "code": "integer",
        "message": "string",
        "details": [
          "object"
        ]
      }
    }
  ]
}
Field Description
results[] object

Request results. Results have the same order as specifications in the request.
results[].
results[]		 object

Results for each requested feature. Feature results have the same order as in the request.
results[].
results[].
error		 object
Return error in case of error during the specified feature processing.

The error result of the operation in case of failure or cancellation.
results[].
results[].
error.
code		 integer (int32)

Error code. An enum value of google.rpc.Code.
results[].
results[].
error.
message		 string

An error message.
results[].
results[].
error.
details[]		 object

A list of messages that carry the error details.
results[].
results[].
textDetection		 object
Text detection (OCR) result.
results[].results[] includes only one of the fields textDetection, classification, faceDetection, imageCopySearch
results[].
results[].
textDetection.
pages[]		 object

Pages of the recognized file.

For JPEG and PNG files contains only 1 page.
results[].
results[].
textDetection.
pages[].
width		 string (int64)

Page width in pixels.
results[].
results[].
textDetection.
pages[].
height		 string (int64)

Page height in pixels.
results[].
results[].
textDetection.
pages[].
blocks[]		 object

Recognized text blocks in this page.
results[].
results[].
textDetection.
pages[].
blocks[].
boundingBox		 object

Area on the page where the text block is located.
results[].
results[].
textDetection.
pages[].
blocks[].
boundingBox.
vertices[]		 object

The bounding polygon vertices.
results[].
results[].
textDetection.
pages[].
blocks[].
boundingBox.
vertices[].
x		 string (int64)

X coordinate in pixels.
results[].
results[].
textDetection.
pages[].
blocks[].
boundingBox.
vertices[].
y		 string (int64)

Y coordinate in pixels.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[]		 object

Recognized lines in this block.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
boundingBox		 object

Area on the page where the line is located.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
boundingBox.
vertices[]		 object

The bounding polygon vertices.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
boundingBox.
vertices[].
x		 string (int64)

X coordinate in pixels.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
boundingBox.
vertices[].
y		 string (int64)

Y coordinate in pixels.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[]		 object

Recognized words in this line.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[].
boundingBox		 object

Area on the page where the word is located.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[].
boundingBox.
vertices[]		 object

The bounding polygon vertices.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[].
boundingBox.
vertices[].
x		 string (int64)

X coordinate in pixels.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[].
boundingBox.
vertices[].
y		 string (int64)

Y coordinate in pixels.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[].
text		 string

Recognized word value.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[].
confidence		 number (double)

Confidence of the OCR results for the word. Range [0, 1].
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[].
languages[]		 object

A list of detected languages together with confidence.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[].
languages[].
languageCode		 string

Detected language code.
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[].
languages[].
confidence		 number (double)

Confidence of detected language. Range [0, 1].
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
words[].
entityIndex		 string (int64)

Id of recognized word in entities array
results[].
results[].
textDetection.
pages[].
blocks[].
lines[].
confidence		 number (double)

Confidence of the OCR results for the line. Range [0, 1].
results[].
results[].
textDetection.
pages[].
entities[]		 object

Recognized entities
results[].
results[].
textDetection.
pages[].
entities[].
name		 string

Entity name
results[].
results[].
textDetection.
pages[].
entities[].
text		 string

Recognized entity text
results[].
results[].
classification		 object
Classification result.
results[].results[] includes only one of the fields textDetection, classification, faceDetection, imageCopySearch
results[].
results[].
classification.
properties[]		 object

Properties extracted by a specified model.

For example, if you ask to evaluate the image quality, the service could return such properties as good and bad.
results[].
results[].
classification.
properties[].
name		 string

Property name.
results[].
results[].
classification.
properties[].
probability		 number (double)

Probability of the property, from 0 to 1.
results[].
results[].
faceDetection		 object
Face detection result.
results[].results[] includes only one of the fields textDetection, classification, faceDetection, imageCopySearch
results[].
results[].
faceDetection.
faces[]		 object

An array of detected faces for the specified image.
results[].
results[].
faceDetection.
faces[].
boundingBox		 object

Area on the image where the face is located.
results[].
results[].
faceDetection.
faces[].
boundingBox.
vertices[]		 object

The bounding polygon vertices.
results[].
results[].
faceDetection.
faces[].
boundingBox.
vertices[].
x		 string (int64)

X coordinate in pixels.
results[].
results[].
faceDetection.
faces[].
boundingBox.
vertices[].
y		 string (int64)

Y coordinate in pixels.
results[].
results[].
imageCopySearch		 object
Image Copy Search result.
results[].results[] includes only one of the fields textDetection, classification, faceDetection, imageCopySearch
results[].
results[].
imageCopySearch.
copyCount		 string (int64)

Number of image copies
results[].
results[].
imageCopySearch.
topResults[]		 object

Top relevance result of image copy search
results[].
results[].
imageCopySearch.
topResults[].
imageUrl		 string

url of image
results[].
results[].
imageCopySearch.
topResults[].
pageUrl		 string

url of page that contains image
results[].
results[].
imageCopySearch.
topResults[].
title		 string

page title that contains image
results[].
results[].
imageCopySearch.
topResults[].
description		 string

image description
results[].
error		 object

Return error in case of error with file processing.

The error result of the operation in case of failure or cancellation.
results[].
error.
code		 integer (int32)

Error code. An enum value of google.rpc.Code.
results[].
error.
message		 string

An error message.
results[].
error.
details[]		 object

A list of messages that carry the error details.