I
Ioannis Pitas
Researcher at Aristotle University of Thessaloniki
Publications - 826
Citations - 26338
Ioannis Pitas is an academic researcher from Aristotle University of Thessaloniki. The author has contributed to research in topics: Facial recognition system & Digital watermarking. The author has an hindex of 76, co-authored 795 publications receiving 24787 citations. Previous affiliations of Ioannis Pitas include University of Bristol & University of York.
Papers
More filters
Proceedings ArticleDOI
Morphological shape representation
TL;DR: A new approach for shape representation is described which provides a general scheme for object description and unifies some of the existing representation techniques, based on the use of simple geometric objects which are intuitively used by humans in their perception of shapes and on mathematical morphology.
Journal ArticleDOI
Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms
TL;DR: Wang et al. as discussed by the authors proposed a graph attention layer (GAL) for road pothole detection, which can be easily deployed in any existing CNN to optimize image feature representations for semantic segmentation.
Proceedings ArticleDOI
Frontal face authentication using variants of dynamic link matching based on mathematical morphology
TL;DR: The comparison with other frontal face authentication algorithms developed within M2VTS project indicates that morphological dynamic link architecture with discriminatory power coefficients is ranked as the best algorithm in terms of the EER.
Journal ArticleDOI
Camera Motion Estimation Using a Novel Online Vector Field Model in Particle Filters
TL;DR: A novel stochastic vector field model is proposed, which can handle smooth motion patterns derived from long periods of stable camera motion and can also cope with rapid camera motion changes and periods when the camera remains still.
Proceedings ArticleDOI
Person de-identification in activity videos
TL;DR: 2D Gaussian filtering is applied to obfuscate the human body silhouettes that implicate information about the person ID and how the use of filtering affects the person identification and action recognition performance in different camera setups formed by an arbitrary number of cameras.