C
Costas Panagiotakis
Researcher at Technological Educational Institute of Crete
Publications - 78
Citations - 1400
Costas Panagiotakis is an academic researcher from Technological Educational Institute of Crete. The author has contributed to research in topics: Cluster analysis & Computer science. The author has an hindex of 20, co-authored 66 publications receiving 1245 citations. Previous affiliations of Costas Panagiotakis include Foundation for Research & Technology – Hellas & University of Crete.
Papers
More filters
Journal ArticleDOI
A speech/music discriminator based on RMS and zero-crossings
TL;DR: The goal was to first develop a system for segmentation of the audio signal, and then classification into one of two main categories: speech or music, and results show that efficiency is exceptionally good, without sacrificing performance.
Journal ArticleDOI
Segmentation and Sampling of Moving Object Trajectories Based on Representativeness
TL;DR: A method for trajectory segmentation and sampling based on the representativeness of the (sub)trajectories in the MOD is proposed, and the effectiveness of the proposed scheme is verified in comparison with other sampling techniques.
Journal ArticleDOI
MRF-based segmentation and unsupervised classification for building and road detection in peri-urban areas of high-resolution satellite images
TL;DR: A novel segmentation algorithm based on a Markov random field model and an extensive data analysis for determining relevant features for the classification problem is given and the reachability of a good classification rate is evaluated using the Random Forest method.
Journal ArticleDOI
Equivalent Key Frames Selection Based on Iso-Content Principles
TL;DR: A key frames selection algorithm based on three iso-content principles (iso-content distance, iso- Content error and iso- content distortion) is presented, so that the selected key frames are equidistant in video content according to the used principle.
Journal ArticleDOI
Natural Image Segmentation Based on Tree Equipartition, Bayesian Flooding and Region Merging
TL;DR: A new region merging method, which incorporates boundary information, is introduced for obtaining the final segmentation map, and results on the Berkeley benchmark data set demonstrate the effectiveness of the proposed methods.