Visual Fashion Recognition: a Demo
At IxorThink we are currently working on a visual fashion recognition system using deep learning. We are developing this model a Belgian company which makes it possible to link online and television content to brands and e-shops.
While there is an immense product database available , AI is needed to recommend products based on scene images or celebrity pictures. The AI model should help to link these scene images to the correct product images used for content marketing. The difficulty lays in correctly recognizing pieces of clothing while ignoring the background, lighting, etc. While some research exists in this area, even existing state-of-the-art models have difficulties reaching desirable results.
The model developed at IxorThink combines recent research on siamese networks and triplet loss functions achieving impressing results. You can read more about the technicalities of the designed model in one of our previous blog posts about Triplet Learning.
Time for a demo!
At IxorThink we are constantly trying to improve our methods to create state-of-the-art solutions. As a software-company we can provide stable and fully developed solutions. Feel free to contact us for more information.