WebPurify Profanity Filter, Image Moderation, and Video Moderation Services

Frequently Asked Questions

Who should use the WebPurify Image Moderation Service?

Anyone who is in need of easy-to-implement, live, fast, and efficient image moderation or sorting services. Our solution can be used to moderate or filter any web-hosted image including avatars, profile pictures, contest entries, photo album pics, etc.

How does the WebPurify Image Moderation Service Work?

  1. You may use our standard criteria and begin submitting images right away or contact WebPurify to create custom moderation criteria.
  2. Simply submit the URL for an image to our HTTP web service.
  3. Our team of experts will quickly moderate your image.
  4. The results of our moderations will be returned to you via a callback URL you provide.

How does WebPurify compare to using crowd sourcing solutions?

  1. A significant concern for many of our clients is the exposure of their images to an unscreened freelance worker who can easily capture and disseminate it with no liability. Privacy in this space is extremely important. With the WebPurify Image Moderation Service, our trained workforce moderates all images.
  2. Many of our clients have arrived at our solution after being disappointed with crowd sourcing solutions. With quality control being nearly impossible, error rates are quite high causing clients to resubmit the same image multiple times which impacts costs.
  3. It is difficult to achieve consistent results with crowd sourcing solutions since guidelines for the unscreened freelance workers such as “nudity” or “sexually explicit” are interpreted differently. With crowd sourcing, the client’s only control over training is the ability to provide written guidelines to the potential moderators. People of various ages and cultures around the world may screen images reviewed for these criteria very differently.
    With WebPurify, we will explore and clearly define your custom criteria with you so that we may effectively train our team for your specific project.
  4. Managing workers requires significant overhead and time. The WebPurify Image Moderation Service eliminates this burden for our clients, providing a simple “fire-and-forget” solution.

What criteria do you use to moderate images?

By default our service flags images that contain our standard criteria;
We define this as any image that may:

  • contain nudity or partial nudity
  • portray hate or hate crimes
  • contain violence
  • contain offensive gestures or language (English Only)
  • contain drugs, drug paraphernalia, or drug use
  • appear blank or broken

However we also provide custom solutions, please email sales@webpurify.com

How long does is take for an image to be moderated?

Results are returned within 5 minutes, 24×7, 365 days a year. Over 90% of requests are returned in as fast as 1 minute. Depending on your needs, custom projects can offer even faster return times.

Who performs the moderation?

Our very qualified workforce that is prepared to handle your requests 24/7 365 days a year.

How can I test the service during development without having to pay for moderations?

We provide two methods for testing. One for testing accuracy and the other for testing integration.

Testing Accuracy:
We provide 100 free moderations for new accounts. Simply sign up for a free trial and integrate our service into your app or use your web browser.

Testing Your Integration:
Our sandbox method, webpurify.sandbox.imgcheck, can be used to verify that your integration is working correctly. All images submitted to our service using this method will bypass our live moderators and be moderated automatically (randomly). The service will hit your callback URL to complete the process. It is important to know that this call may result in false positives as it is bypassing our moderators and simply verifying a successful connection.

Standard Image Moderation Criteria
Does the image:
Standard Video Moderation Criteria
Does the video:
Other Language Label: If a video complies with our moderation criteria but contains languages other than English, we will label it as “Other Language.”