Related Experiment Video
Updated: May 9, 2026

Automatic Identification of Dendritic Branches and their Orientation
Published on: September 17, 2021
Toward image phylogeny forests: automatically recovering semantically similar image relationships
Zanoni Dias1, Siome Goldenstein, Anderson Rocha
1Institute of Computing, University of Campinas, Campinas, SP 13083-852, Brazil. zanoni@ic.unicamp.br
Abstract:
In the past few years, several near-duplicate detection methods appeared in the literature to identify the cohabiting versions of a given document online. Following this trend, there are some initial attempts to go beyond the detection task, and look into the structure of evolution within a set of related images overtime. In this paper, we aim at automatically identify the structure of relationships underlying the images, correctly reconstruct their past history and ancestry information, and group them in distinct trees of processing history. We introduce a new algorithm that automatically handles sets of images comprising different related images, and outputs the phylogeny trees (also known as a forest) associated with them. Image phylogeny algorithms have many applications such as finding the first image within a set posted online (useful for tracking copyright infringement perpetrators), hint at child pornography content creators, and narrowing down a list of suspects for online harassment using photographs.
Related Concept Videos
Phylogenetic Trees
Phylogenetic Trees
Phylogeny
Evolutionary Relationships through Genome Comparisons
Microbial Phylogeny
Causes of Similarity-Dissimilarity Effect

