M
Michael G. Strintzis
Researcher at Aristotle University of Thessaloniki
Publications - 240
Citations - 6529
Michael G. Strintzis is an academic researcher from Aristotle University of Thessaloniki. The author has contributed to research in topics: Motion estimation & Image segmentation. The author has an hindex of 44, co-authored 240 publications receiving 6319 citations. Previous affiliations of Michael G. Strintzis include Information Technology Institute & University of Pittsburgh.
Papers
More filters
Proceedings ArticleDOI
Ontology based interactive graphic environment for product presentation
TL;DR: An innovative environment for presenting products through the Internet using modern visualization techniques and providing high level of interaction with the user is proposed.
Journal ArticleDOI
Dynamic texture recognition and localization in machine vision for outdoor environments
Vagia Kaltsa,Konstantinos Avgerinakis,Alexia Briassouli,Ioannis Kompatsiaris,Michael G. Strintzis +4 more
TL;DR: Experiments on various challenging benchmark datasets prove the method's efficacy and generality, as remarkable recognition and localization accuracy rates are achieved at a low computational cost, making it appropriate for real world outdoor applications.
Proceedings ArticleDOI
3D reconstruction of indoor and outdoor building scenes from a single image
TL;DR: A novel method is proposed able to automatically generate accurate 3D models of both outdoor buildings and indoor scenes with perspective cues from line segments that are automatically extracted from a single image with an uncalibrated camera.
Real-time compressed-domain spatiotemporal video segmentation
TL;DR: Experimental results on known sequences demonstrate the efficiency of the proposed approach and reveal the potential of employing it in content-based applications such as objectbased video indexing and retrieval.
Journal ArticleDOI
Combined frequency and spatial domain algorithm for the removal of blocking artifacts
TL;DR: The efficient performance of the proposed algorithm is due to the proposition that the shape and the position of the filter kernel are adjusted according to the characteristics of the local image region and secondly, to the employment of the modified improved DCT coefficients by the postprocessing filter.