N
Nikos Papamarkos
Researcher at Democritus University of Thrace
Publications - 120
Citations - 3005
Nikos Papamarkos is an academic researcher from Democritus University of Thrace. The author has contributed to research in topics: Color quantization & Self-organizing map. The author has an hindex of 30, co-authored 120 publications receiving 2894 citations.
Papers
More filters
Journal ArticleDOI
Hand gesture recognition using a neural network shape fitting technique
TL;DR: A new method for hand gesture recognition that is based on a hand gesture fitting procedure via a new Self-Growing and Self-Organized Neural Gas (SGONG) network is proposed and has been extensively tested with success.
Journal ArticleDOI
A new signature verification technique based on a two-stage neural network classifier
Haris Baltzakis,Nikos Papamarkos +1 more
TL;DR: A new technique for off-line signature recognition and verification based on global, grid and texture features and implemented in a special two stage Perceptron OCON (one-class-one-network) classification structure.
Journal ArticleDOI
Adaptive color reduction
TL;DR: The proposed adaptive color reduction (ACR) technique achieves color reduction using a tree clustering procedure using a self-organized neural network classifier (NNC) which is fed by image color values and additional local spatial features.
Journal ArticleDOI
A new approach for multilevel threshold selection
Nikos Papamarkos,Basilis Gatos +1 more
TL;DR: A hill-clustering technique is applied to the image histogram in order to approximately determine the peak locations of the histogram, which gives the global minimum of each rational function, which corresponds to a multilevel threshold value.
Journal ArticleDOI
Segmentation of historical machine-printed documents using Adaptive Run Length Smoothing and skeleton segmentation paths
TL;DR: Use of a novel Adaptive Run Length Smoothing Algorithm (ARLSA) in order to face the problem of complex and dense document layout, and detection of noisy areas and punctuation marks that are usual in historical machine-printed documents.