The ever-increasing number of gadgets being used to create digital content, as well as the easiness in sharing, editing, and republishing this content, brings the problem of dealing with a large amount of digital objects (e.g., images or videos) whose content is very similar. Some issues faced by investigators of digital crimes when analysing this type of data include finding the original source of a suspect image, for instance, and the responsible for first publishing it. It is also challenging to determine how a set of similar objects are related to each other. In this talk, I will briefly introduce the research field of multimedia phylogeny, which aims at automatically finding the underlying relationship among groups of digital objects with similar content. This relationship is represented by a tree structure, inspired by the phylogenetic trees in Biology. I will present the state-of-art approaches to reconstruct phylogenetic trees for different media types, and also discuss some challenges faced by this research field.
Marina A. Oikawa received the B.Sc. degree in computer science from Federal University of Pará, Brazil, in 2006, and the Master and PhD degrees in Engineering from Nara Institute of Science and Technology, Japan, in 2010 and 2013, respectively. Currently, she is a Postdoc at Institute of Computing, University of Campinas, RECOD Lab. Her main research interests include digital forensics, computer vision, augmented reality, and computer graphics.
Responsável: Prof. Ariadne M. B. R. Carvalho
Fone: (19) 3521-5864
Instituto de Computação, Unicamp