Visual Search Engines

The search engines we normally use are text based, like Google. You type in some text and the search engine retrieves the most relevant documents for that query term. The query text can be in the form of audio, “Siri, tell me about Albert Einstein”, which opens the Wikipedia page of Albert Einstein. Similarly, there can be visual search engines in which the query term is an image and the search engine finds similar looking images, or related images. Google supports visual search currently, but I don’t have the statistics as to what number of people actually use it.

Business Proposition

Say, I’m looking for a jacket, I find one that I like but, I want a few tweaks in it. Now these tweaks can be done using voice commands, ‘make the pink a little brighter’, ‘I want poke-balls on the hat’ or using gestures on touch screen devices. In the yester-years when people went to shops to get clothes stitched this was the norm, you get the clothes you like, and get them stitched the way you want. You had absolute full control over everything, the kind of cloth, the kind of stitch and what not! Even today, top designer’s sketch their designs but now they can use interactive technology using GAN’s to make the designs look more realistic.

Nowadays, everyone wants their clothing, phone and accessories to be customized and GAN’s provide a way to do so. GAN’s are not as realistic looking as humans might expect them to. To somehow fix this, consider adding this to Clarifai’s amazing technology stack and just imagine what wonders can happen!

This will open a new chain of data science problems:

  1. Predictive analytics and predictors:
    1. To produce the kind of clothing one user wants or not (should the clothing company take the risk of producing the entire product?)
  2. To recommend what kind of tweaks a person might like based other similar users

This will start a chain of businesses:

  1. Cheap clothing and printing ……
  2. Fabrics made to order …..

And so many more things that I don’t know about because of my limited knowledge about the clothing industry.

There isn’t a better age to be more unique!


blog comments powered by Disqus


08 October 2016