Clustering duplicates in Yandex.Pictures

    Today in the Yandex.Subbotnik club an interesting video has appeared about how Yandex processes images to eliminate duplicates. Alexander Krainov reports: since 2000, he has been involved in projects related to the processing of media data. At Yandex, he is responsible for projects that involve computer vision.

    About the report
    Easily find duplicates among thousands of pictures. More difficult among millions. And it’s very difficult - among billions. The higher the completeness of the algorithm, the more problems. But at the same time, the completeness of clustering of duplicates is the basis of image search quality.

    I think many do not follow this club and it seems to me that after this video there is something to reflect on.
    Anyone who is interested - I ask for a cat.



    Link to the presentation in pdf format.

    Also popular now: