Machine Learning based Descriptive Metadata Generation for Library Archives - Dhanushka Samarakoon
From Mike Wetta
As libraries and cultural heritage organizations continue to acquire and digitize cultural and historical treasures, in the hopes of making them available to the general public, it is important to create quality descriptive metadata to increase the visibility of content. Creating quality metadata is a time-consuming process, and not all organizations may have enough metadata experts to describe the content quickly & accurately. This talk will discuss using Machine Learning technology to simplify descriptive metadata generation for historical images. I will share information about the current technology landscape, with a particular focus on the tools, techniques, and outcomes of the related projects.
Dhanushka Samarakoon is the Head of Library Technology, for the University of Miami Libraries. He provides leadership, management, budgetary oversight, and expertise to develop and execute the long-term technology strategy in support of the Libraries’ mission. He supervises the departments responsible for the Libraries Enterprise applications, computing infrastructure, and Audio/Video & event support. He earned his Master of Library Science from Emporia State University and the Bachelor of Information Technology from the Sri Lanka Institute of Information Technology.