How to build a Visual Search Application

Often it’s easier to show a physical example or image than it is to try to describe an item with words that a search engine can effectively use. That’s because some users might lack the knowledge or understanding to accurately describe an item.


To perform a visual search instead of asking for something by voice or text, you show what you are looking for. As the old saying goes, “A picture is worth a thousand words.”

In this video, Solutions Architect Tobias Borjeson shows how to build a visual search application using Amazon SageMaker, an AWS DeepLens, a deep-learning enabled video camera. We’ll use Amazon SageMaker to create a model for visual search and to build a fast index containing reference items to be searched. We’ll then extend this into the physical world by demonstrating how to directly search for items visually similar to physical objects in real time via an AWS DeepLens device.

Watch the video now to find out how to build your own solution


What Will You Create

Whatever your next idea, we’ll help you make it a reality. Get building in three simple steps!

Sign up for an AWS Account

There are no upfront charges or any term commitments to create an AWS account and signing up gives you immediate access to the AWS Free Tier.

Follow the Step by Step Instructions

Use the provided resources to replicate a similar solution to the one built by our experts. Get further training in specific areas using the resources that can be found on each Demo Page.


Build your own solution

Elaborate your solution further with your personal touch!