This is the personal web site of Georgios K. Ouzounis, hereafter referred to as the 'author'. The opinions expressed are those of the author and not those of the author's employer and/or volunteer affiliations.

Biographical Note

Georgios K. Ouzounis
obtained a bachelor in Electrical and Electronic Eng. (BEng.) and a M.Phil. degree in computer science from the department of Computing and Electrical Engineering, Heriot Watt University, Edinburgh, Scotland in 1998 and 2001 respectively. He received his Ph.D. on image analysis and connected morphological filters from the Johann Bernoulli Institute ofMathematics and Computing Science, University of Groningen, The Netherlands, in 2009. From January 2008 to September 2009 he worked at the Democritus University of Thrace - 2nd Department of Surgery,University General Hospital of Alexandroupoli, Greece, as a medical image analyst developing 3-D CT segmentation methods for diagnostic purposes of interest to the Urological Clinic. From September 2009 to September 2012 he was appointed as a researcher at the Geospatial Image Analysis Group of the Global Security and Crisis Management Unit - Joint Research Centre, European Commission, in Ispra, Italy, where he worked on the development of advanced VHR satellite and aerial image analysis algorithms. From October 2012 to June 2017 he worked at DigitalGlobe as a form of Digitasenior research scientist developing methods for unsupervised satellite image information mining using hierarchical image representation data structures and deep learning. His works feature the PROTOGEN software suite, developed by the author in its entirety, that powers a number of apps in the Geospatial Big Data (GBDX) platform ecosystem of DigitalGlobe [click here for an example]. From June 2017 to Feb. 2018 he worked in Verisk Analytics as a lead data scientist with focus on image forensics, automated claims image analytics, and computer automobile computer vision applications. Since Feb. 2018 he works in Netgear developing apps in support of the Arlo product.

Georgios K. Ouzounis has invented four major algorithms, the dual-input Max-Tree algorithm, the one-pass method for computing Differential Area Profiles (DAP) by Area Zone Decomposition, the Alpha-Tree and the Extended Connectivity Tree. He was the architect of all computational engines and image analysis algorithms related to the DAP vector fields that were used by the JRC Image Query (IQ) system to populate the very first VHR Global Human Settlement Layer (GHSL).