Tommy Hilfiger uses Machine Learning to identify fashion trends in the runways

Machine Learning - Fashion

When fashion meets Artificial Intelligence

Tommy Hilfiger, one of the largest companies in the fashion industry, takes inspiration from the world's most famous runways to design, produce and launch their new collections to the market. This task has been traditionally done by industry and fashion experts. However, Tommy Hilfiger asked the question "Could we include Artificial Intelligence in our design process"?


Image recognition to identify fashion trends

This article was written inspired by the original story published here.
Tommy Hilfiger partnered with IBM and used Watson's Visual recognition api, a Machine Learning model that classifies and recognises objects in images or video to automatically analyse over 600.000 publicly available runway pictures and try to identify current fashion trends.

On top of that, another model was trained by feeding it over 15.000 Tommy Hilfiger images to create clusters of data and with the help of Artificial Intelligence get a better understanding of its own designs.


Help! Robots are already taking our jobs!

Not quite... All this new data and insights were given to the students of the Fashion Institute of Technology as source of inspiration so that they could come up with creative design ideas for Tommy Hilfiger. As powerful as Machine Learning is now, it cannot yet substitute the creative process a human mind can do. Below you can see a sketch of one of the designs that made it to the final of this process


Machine Learning coat

Taking innovation one step even further

To go one step further, the students of the FIT decided to also integrate in this design color changing fibers that responded to the overall sentiment analysis of a given social media feed. This is easily achieved by feeding the social media feed to Watson's Natural Language Understanding api which in turns analyses text meaning and structure and returns the overall sentiment and emotion found in the feed. With this information, the color from the fibers in the jacket can be changed in real time, assigning pale colours to sad emotions and bright colours to happy ones.


MLab, the Machine Learning specialists at your service!

If Machine Learning inspires you and you think you would like to implement a use case in your organisation, please get in touchWe are vendor agnostic and we will recommend and integrate the technology that adapts the best to your needs. If non available technologies satisfy your needs, we can always train a custom model tailored to your project.


Disclaimer: MLab was not involved in the development of this project. We simply publish this case study as a source of inspiration on what Machine Learning can achieve.