Presentation slides about Perceptual Hashing in Audiovisual preservation work-flows presented at the Association of Moving Image Archivists annual conference, 2017. From paper proposal: Perceptual hashing is a method of identifying related content using computer analysis; the goal being to eliminate the (often impossible) necessity of having a person look at every item one-by-one to make comparisons. Perceptual hashes function in a similar sense to standard checksums, except instead of comparing hashes to establish exact matches between files at the bit level, they establish similarity of content as would be perceived by a viewer or listener. I will present an overview of the concepts of perceptual hashing, with a particular focus on the hashing contained in the MPEG-7 standard, as well as ongoing research into the integration of perceptual hashing in archival workflows being conducted at a medium sized broadcast archive. Topics addressed will include how perceptual hashing was implemented, why certain decisions were made, successes and failures of the research and potential benefits. An HTML based slide deck.
Metrics
25 File views/ downloads
112 Record Views
Details
Title
Automation and Similarity: An Introduction to Perceptual Hashing
Creators
ANDREW J WEAVER (Author) - Washington State University, UNKNOWN
Conference
Association of Moving Image Archivists Annual Conference (2017)
Academic Unit
Libraries
Identifiers
99900502973401842
Copyright
In copyright ; openAccess ; http://rightsstatements.org/vocab/InC/1.0/ ; http://purl.org/eprint/accessRights/OpenAccess