Bing’s CelebsLike.me Finds Your Oscar Doppelganger
As part of its Academy Award Experience, Bing has created a site that lets users upload photos of themselves to find their look-alike celebrities.
After launching its Guide to the Academy Awards last week, Bing has added a new feature to the mix with its CelebsLike.me – a site that finds your look-alike celebrity.
Users can upload a photo of themselves to the site, or share one already online, and Bing will match it to an Oscar-nominated actor, actress or director and include three additional celebrity matches not involved in the Oscars.
The announcement noted that matches are based on facial structure versus details like hair length or color. “That means your matches will share the same facial structure, but perhaps include a mix of gender and races,” writes Bing program manager Ravi Yada.
Bing included a brief explanation of how its CelebLike.me site works, relying on the perceptual intelligence capabilities of Cortana Analytics, in addition to the Bing Satori knowledge graph and image graph.
[blockquote cite = “Bing Search Blog”]The Bing team built one of the largest vision-recognition engines in the world, leveraging face and vision APIs that are part of the perceptual intelligence capabilities of Cortana Analytics. This recognition engine recognizes celebrity faces, like Tom Hanks and Keira Knightley, for example, in web images on a large scale with extremely high accuracy. The engine then links these entities to both the Bing Satori knowledge graph, where we have information about the entity, and Image Graph, where we have knowledge based on visual features and web presence of the image.[/blockquote]
According to Bing, its recognition engine can outperform humans with certain vision tasks and is constantly improving.
Bing directed readers to its “Challenge of Recognizing One Million Celebrities in the Real World” research paper for deeper insight into the mechanics behind the CelebLike.me website.
Opinions expressed in this article are those of the guest author and not necessarily Search Engine Land. Staff authors are listed here.