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
Posted ContentDOI
Geometric deep learning on brain shape predicts sex and age
TL;DR: A deep-learning based method to analyze cortical folding patterns in a data-driven way that alleviates this reliance on manual feature definition and uses convolutional neural network architecture adapted to the surface representation of the cortical ribbon.
Journal ArticleDOI
Shape Error Concealment Based on a Shape-Preserving Boundary Approximation
TL;DR: This paper considers a geometric shape representation consisting of the object boundary, which can be extracted from the α-plane, and proposes a spatial error concealment technique for recovering lost shape data.
Proceedings ArticleDOI
A phone-viseme dynamic Bayesian network for audio-visual automatic speech recognition
TL;DR: This work extends and improves a recently introduced dynamic Bayesian network based audio-visual automatic speech recognition (AV-ASR) system to model the audio and visual streams as being composed of separate, yet related, sub-word units.
Patent
Method and apparatus for characterizing a video segment and determining if a first video segment matches a second video segment
TL;DR: In this paper, a method and apparatus for determining if a first video segment matches a second video segment is provided, where each video segment to be compared has an associated metric (H R ), which is a function over time as the conditional entropy between frame F k and previous frame f k−1.
Proceedings ArticleDOI
Efficient motion compensated frame rate upconversion using multiple interpolations and median filtering
TL;DR: A method is proposed which reduces upconversion artifacts by combining multiple intermediate interpolations utilizing median filtering, and an efficient block based motion estimation method which makes use of motion vectors extracted from an H.264 bitstream is used.