D
Dimitris A. Mitzias
Researcher at Democritus University of Thrace
Publications - 5
Citations - 106
Dimitris A. Mitzias is an academic researcher from Democritus University of Thrace. The author has contributed to research in topics: Pattern recognition (psychology) & Artificial neural network. The author has an hindex of 3, co-authored 5 publications receiving 103 citations.
Papers
More filters
Journal ArticleDOI
Shape recognition with a neural classifier based on a fast polygon approximation technique
TL;DR: The proposed method is based on a new polygon approximation technique, which extracts suitable feature vectors with specified dimension, which characterizes a given shape, and is characterized by high speed performance, which is desired for real time applications.
Journal ArticleDOI
A novel cellular automata based technique for visual multimedia content encryption
Savvas A. Chatzichristofis,Dimitris A. Mitzias,Georgios Ch. Sirakoulis,Yiannis S. Boutalis,Yiannis S. Boutalis +4 more
TL;DR: A new method for visual multimedia content encryption using Cellular Automata (CA), based on the application of an attribute of the CLF XOR filter, according to which the original content of a cellular neighborhood can be reconstructed following a predetermined number of repeated applications of the filter.
Journal ArticleDOI
A neural multiclassifier system for object recognition in robotic vision applications
TL;DR: A high performance NEural MUlticlassifier System (NEMUS) is presented, which combines multiple classifiers that operate on different feature sets and is characterized by a great degree of modularity and flexibility and is very efficient for demanding and generic pattern recognition applications.
Book ChapterDOI
A high performance neural multiclassifier system for generic pattern recognition applications
TL;DR: A high performance neural multi-classifier system (NEMUS) that is characterized by a great degree of modularity and flexibility is proposed, which is very efficient for demanding and generic pattern recognition applications.
Proceedings ArticleDOI
A Robust Hierarchical Neural Network Methodology for Improved Image Classification Performance
TL;DR: The experimental study illustrates that such an approach, integrating higher order features into a second stage feedforward neural classifier, outperforms other combination methods, like voting combination schemes as well as single neural network classifiers having as inputs all FEMs derived features.