Yandex to automate user-generated image moderation

Russian machine learning firm Yandex Data Factory today announced a new product which automatically analyses images and photographs online.

The product, called Automatic Image Moderation, can scan images, and learn to distinguish appropriate from inappropriate content. This will be particularly useful for websites with large volumes of user-generated images, to help them scan and remove inappropriate content.

As the definition of ‘inappropriate’ varies from country to country and from service to service, so will the value of this program grow.

Besides scanning for such content, Automatic Image Moderation will also leverage Yandex’s global web index to recognize duplicate images.

The first company to use the service is an international online dating service, which says the program cut its image moderation costs and improved the process’s overall accuracy, ultimately reducing fake profiles.

“Websites that deal with user-generated content on a daily basis are painfully aware of the issues and difficulties surrounding content moderation. But typically these services mitigate the risk by hiring human moderators, sometimes supported by crowdsourced APIs, who manually sort through user-generated content and images,” said Jane Zavalishina, CEO of Yandex Data Factory.

Zavalishina continues: “This approach is costly, time-consuming, and inefficient as it cannot be easily scaled to meet load demand. Available automatic image classification APIs are generic and cannot be readily tailored to a website’s specific issues or requirements. By using custom machine learning service to automate image moderation, these websites are able to tackle their individual image-related needs in a highly-reliable and cost-effective way.”