Show simple item record

dc.contributor.authorThomson, Diana
dc.contributor.authorHandrick, Nick
dc.date.accessioned2020-05-11T21:27:33Z
dc.date.available2020-05-11T21:27:33Z
dc.date.issued2018-04
dc.identifier.urihttp://digital.library.wisc.edu/1793/80100
dc.descriptionColor poster with text and images.en_US
dc.description.abstractNeural networks are an exciting and evolving branch of machine learning, but they are not limited to just artificial intelligence. Recently, they have been used to compress and even add digital watermarks, or copyright signatures, to digital images. Typically, neural networks use real numbers for their computations, but researchers have also experimented with using complex numbers and quaternions as the basis of these networks. Our research investigates the use of quaternion-valued neural networks implemented in Java for the purposes of digital image compression and watermarking. The benefits of using quaternion-valued over real-valued neural networks include faster network training time, better color compression/recovery, and less processing power/memory required for the computation.en_US
dc.description.sponsorshipUniversity of Wisconsin--Eau Claire Office of Research and Sponsored Programs.en_US
dc.language.isoen_USen_US
dc.relation.ispartofseriesUSGZE AS589;
dc.subjectPostersen_US
dc.subjectMathematicsen_US
dc.subjectDigital imagesen_US
dc.subjectNeural networksen_US
dc.titleDigital Color Image Compression : With Real and Complex Artificial Neural Networksen_US
dc.typePresentationen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

  • Student Research Day
    Posters of collaborative student/faculty research presented at Student Research Day

Show simple item record