A
Aggelos K. Katsaggelos
Researcher at Northwestern University
Publications - 999
Citations - 28918
Aggelos K. Katsaggelos is an academic researcher from Northwestern University. The author has contributed to research in topics: Image restoration & Image processing. The author has an hindex of 76, co-authored 946 publications receiving 26196 citations. Previous affiliations of Aggelos K. Katsaggelos include University of Stavanger & Delft University of Technology.
Papers
More filters
Book ChapterDOI
Digital Image Restoration: Classical
TL;DR: This article may be used for research, teaching and private study purposes but any substantial or systematic reproduction, redistribution, reselling, loan or sub-licensing, systematic supply or distribution in any form to anyone is expressly forbidden.
Proceedings ArticleDOI
Iterative regularized error concealment algorithm
TL;DR: In this article, an iterative regularized error concealment algorithm was proposed to solve the problem of coded information loss in compressed images, where the coded image can be degraded due to channel errors, network congestion, and switching system problems.
Patent
System and Method for Randomized Point Set Geometry Verification for Image Identification
TL;DR: In this paper, the geometric consistency between matching interesting points pairs of two images is verified using a topology code distance vector (D) and a decision tree classifier, which may be trained in accordance with previous or historic topology codes.
Journal ArticleDOI
Automatic Classification of A-Lines in Intravascular OCT Images Using Deep Learning and Estimation of Attenuation Coefficients
Grigorios Aris Cheimariotis,Maria Riga,K. Haris,Konstantinos Toutouzas,Aggelos K. Katsaggelos,Nicos Maglaveras +5 more
TL;DR: A novel automatic method for A-line classification that employed convolutional neural networks for classification in its core and comprised the following pre-processing steps: arterial wall segmentation and an OCT-specific transformation and a post-processing step based on the majority of classifications.
Proceedings ArticleDOI
Spectral approximation to point set similarity metric
TL;DR: This work modeled as affinity matrix and the distances between affinity matrices of two point sets are lower bounded by eigenvalue distance, which is invariant to scale, translation and rotation and insensitive to outliners and affine transforms.