Visual SearchOur goal is to create solutions that are so simple to use, so fast and convenient, that customers prefer them to traditional search methods. Sunil Ramesh
Visual Search
Our Augmented Reality technology helps our customers use visual information for search, discovery and shopping by overlaying relevant information over camera-phone views of the world around them.
It is often easier to search with a picture than it is to type. Our deep learning and computer vision solutions enable customers to recognize objects in camera-phone views and to search for associated products on Amazon. We also support barcode, QR code, credit card and gift card recognition, making it easier for our customers to complete their shopping missions on mobile devices.
Visual Search also powers solutions that let customers search for products based on visual attributes such as color, shape or even texture. These solutions allow our customers to easily find the shoes, dresses or watches they like based on just the appearance of the product.
Visual search solutions are ideally suited to mobile applications. Our technology powers visual search in several apps for the Amazon family of companies.
Our continuous scan technology is at the heart of Amazon’s augmented reality efforts and allows customers to seamlessly scan products of interest, discovering useful information about them.
Visual Search also develops computer vision solutions that support Amazon initiatives along the entire product delivery pipeline: from the time a new product is photographed and added to our catalog to the time an item is bought and shipped to the customer.
Our research and development efforts span these major areas:
• Deep Learning algorithms for Computer Vision
• Image matching and classification
• OCR, text recognition, and geospatial recognition
• Robust distributed computing infrastructure
• UX for Augmented Reality applications
One of our core capabilities is to efficiently search for the products that best match a user’s query image – even when the query image was taken without much care, and with a low-end camera.
This solution relies on large-scale, distributed techniques for:
• Deep Learning
• Image retrieval
• Feature compression
• Object detection and tracking
• 3D Object detection
• Hardware optimized computation
• Deployment of solutions at scale
