VDMS: An Efficient Big-Visual-Data Access for Machine Learning Workloads
We introduce the Visual Data Management System (VDMS), a data management solution that enables efficient access of big-visual-data to support visual analytics. This is achieved by searching for relevant visual data via metadata stored as a graph, as well as enabling faster access to visual data through new machine-friendly storage formats. VDMS differs from existing large scale photo serving, video streaming, and textual big-data data management systems due to its primary focus on supporting machine learning and data analytics pipelines that use visual data, and in its treatment of visual data such as images, videos, and feature vectors as first class entities. We describe how to use VDMS via its user friendly interface as well as how it enables rich and efficient vision analytics through a machine learning pipeline for processing medical images. We show the improved performance of 2x in complex queries over a comparable set-up.
READ FULL TEXT