Ask neural network if your photo is good or not.
Right-click an image on the web and copy the image’s URL. Return to the search box and paste in the URL (Ctrl+V or Command+V).
Ask neural network if your photo is good or not.
Learn more
of any image across the web or use images above
how we taught a neural network to see the beauty?
- 1. We gave neural network an example to follow. To cope with it we asked designers, editors and experienced stock photographers help us generate a training dataset.
- 2. Neural Network have processed positive and negative patterns.
- 3. Heartless algorithm learned to see the beauty of shoots in the same way as you do.
how do we plan
to use the technology?
We are building a stock image search engine. And we want it to be the best search tool for stock image users ever. At the moment we can search across hundreds of millions of stock images and unfortunately not all of them are great. Far from it. And this is where our aesthetic detector comes in handy. There are two very important tasks it can accomplish:
automatic image curation
Neural network would estimate a visual quality of every image and apply aesthetic score to every file. Later on this data would take part in the overall mix of ranking factors and help improve search results by bringing aesthetically better images to the first pages.
bad stock image terminator
There are lots and lots of unforgivingly bad stock photos. Neural network would detect photos with the lowest aesthetic score and literally weed them out from the search results.