Navigating and Discovering Educational Materials through Visual Similarity Search

Full text available as:

PDF (Accepted Manuscript) - Repository staff only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader Download (347Kb) | Request Copy from OU Author

Abstract

We describe the development and implementation of visual multimedia similarity search within a platform for social exchange of educational experiences and material to provide services for finding related media. The SocialLearn project develops tools to support the building and exploration of personal learning networks. With the ever-increasing volumes of educational resources being made available, it is a challenge to find new material and forge appropriate learning pathways. Visual search can help when it is difficult to describe your interests in words (“search terms”) or when you want to browse for inspiration without a specific result in mind. In this paper we present the usage scenarios for visual search within education and describe the design and implementation of visual similarity search within the SocialLearn platform. The outcomes from this work are not only directly useful for the SocialLearn project but also for others who are interested in the challenges of using multimedia for education.