Restb.ai Watermark Detection

FREEMIUM
От Restb.ai | Обновлено 10 месяцев назад | Visual Recognition
Популярность

9.2 / 10

Задержка

951ms

Уровень обслуживания

100%

Обзор Restb.ai Watermark Detection

Подписчики: 4
Ресурсы:
Сайт продукта Условия использования
Создатель API:
avatar
Restb.ai
restb
Оценить API:
Войдите, чтобы оценить API

ПРОЧТИ МЕНЯ

Our Watermark Detection solution is used to detect artificially added watermarks, logos, and text in images. The artificially added items can be opaque or almost completely transparent. An example use case for this API would be to use the data to automatically find and filter / flag images that contain a competitor’s watermark or copyrighted material.

Restb.ai Watermark Detection

This is the RESTful API for our AI Computer Vision Solution for Watermark Detection. This solution allows clients to detect if an image contains artificially added watermarks, logos, or text.

Basics

Apart from the standard RapidAPI security headers, the following parameter must be sent in order for this API to function correctly:

  • image_url | form – this should be a fully qualified, publicly-accessible URL to an image, which should be passed in the form body

Response

If you successfully send a valid request, you will receive a response similar to the example below:

{
    "error": "false",
    "correlation_id": "26adaf72-63cf-44c1-932c-91da3b839157",
    "version": "2",
    "time": "2018-10-31T16:02:30.107742",
    "response": {
        "solutions": {
            "re_logo": {
                "detections": [
                    {
                        "label": "watermark"
                    }
                ]
            }
        }
    }
}

The response can be broken down as follows:

  • error – indicates whether there was an error or not (will still result in an HTTP 200 response code even if there was an error)
  • correlation_id – a randomly generated identifier for identification and support purposes
  • time – a system timestamp (UTC)
  • response.solutions – the solutions wrapper
  • re_logo – internal identifier for our “Watermarks Detection” solution
  • detections – a list of detected watermarks, logos, and/or text, each encapsulated within a dictionary object with a label key; valid values are watermark, logo, and/or text

Error Handling

These are the different error situations that can occur:

  • HTTP 429 – too many concurrent requests
  • HTTP 200 | error_id: 001 – invalid image_url provided
  • HTTP 200 | error_id: 007 – internal system error

You should implement a retry strategy (ideally with exponential back-off) if you receive one of the above errors. For example, retry up to 3 times with a progressively longer sleep time between attempts.

Limits

Please view our pricing plans to see monthly API allowances and corresponding rate limits.

Enterprise contracts are available if you desire:

  • Increased allowance of requests
  • Greater concurrency
  • Guaranteed support response times
  • Higher platform availability
  • Custom models

For any of these, please contact us.

Working with images

In general, smaller images of approximately 800x600 resolution work the most optimally on the platform. Unnecessarily large images should be resized for optimal platform performance before being sent to Restb.ai’s API service. Not resizing images doesn’t necessarily yield better results, and also takes longer to download and process. When resizing the image, note that using lossy compression formats (such as JPEG) can drop the quality of the image, so be sure to take care to preserve quality during the resize operation. Also, we recommend the use of bicubic interpolation / resampling when resizing images for the best results. The shortest edge of an image should ideally be no less than about 600 pixels. Note that due to computational limitations, we cannot process images that are more than 2^29 pixels, although anything higher than 800x600 is unnecessary.

We support standard image formats, including but not exclusively limited to JPEG, GIF, TIFF, and/or PNG. Non-standard formats are not supported by the platform and may result in 001 errors being returned.

While using the image_url parameter please remember to properly escape / url-encode the URL; they can often contain reserved characters that must be escaped to be properly passed in as a parameter (especially ?, &, /, and = characters).

Оценки: 5 - Голосов: 1