An EU founded project in the H2020 framework (3M€ 2015-2018). This project is about how to make a VR game without knowing gaming technologies. It targets for archaelogists that own 3D models and want to make a VR tour, but they do not know how. We are using web technologies for remotely updating the game, and desktop technologies for compiling the game. My role is to integrate all code contributions from several people into a solid product. Project main site: http://digiart-project.eu Product release site: http://digiart.mklab.iti.gr DigiArt seeks to provide a new, cost efficient solution to the capture, processing and display of cultural artefacts. It offers innovative 3D capture systems and methodologies, including aerial capture via drones, automatic registration and modelling techniques to speed up post-capture processing (which is a major bottleneck), semantic image analysis to extract features from digital 3D representations, a “story telling engine” offering a pathway to a deeper understanding of art, and also augmented/virtual reality technologies offering advanced abilities for viewing, or interacting with the 3D models. The 3D data captured by the scanners and drones, using techniques such as laser detection and ranging (LIDAR), are processed through robust features that cope with imperfect data. Semantic analysis by automatic feature extraction is used to form hyper-links between artefacts. These links are employed to connect the artefacts in what the project terms “the internet of historical things”, available anywhere, at any time, on any web-enabled device. The contextual view of art is very much enhanced by the “story telling engine” that is developed within the project. The system presents the artefact, linked to its context, in an immersive display with virtual and/or with augmented reality. Linkages and information are superimposed over the view of the item itself. The major output of the project is the toolset that will be used by museums to create such a revolutionary way of viewing and experiencing artefacts. These tools leverage the interdisciplinary skill sets of the partners to cover the complete process, namely data capture, data processing, story building, 3D visualization and 3D interaction, offering new pathways to deeper understanding of European culture. Via its three demonstration activities, the project establishes the viability of the approach in three different museum settings, offering a range of artefacts posing different challenges to the system.
Dimitrios Ververidis has contributed a chapter into this book.
This comprehensive reference text is a collection of important research findings on the latest developments in network modeling for optimization of smart cities. Such models can be used from outlining the fundamental concepts of urban development to the description and optimization of physical networks, such as power, water or telecommunications. Networks help us understand city economics and various aspects of human interactions within cities with particular applications in quality of life and the flow of people and goods. Finally, the natural environment and even the climate of cities can be modeled and managed as networks. [Ref. Book chapters 1] [Go to publisher]
In this paper we propose a set of Electromyogram (EMG)
based features such as muscles total pressure, flexors
pressure, tensors pressure, and gesture stiffness, for the
purpose of identifying differences in performing the same
gesture across three pottery constructions namely bowl,
cylindrical vase, and spherical vase. In identifying these
EMG-based features we have developed a tool for visualizing
in real-time the signals generated from a Myo
sensor along with the muscle activation level in 3D space.
In order to do this, we have introduced an algorithm for
estimating the activation level of each muscle based on
the weighted sum of the 8 EMG signals captured by Myo.
In particular, the weights are calculated as the distance
of the muscle cross-sectional volumes at Myo plane level
from each of the 8 Myo pods, multiplied by the muscle
cross-section volume. Statistics estimated on an experimental
dataset for the proposed features such as mean,
variance, and percentiles, indicate that gestures such as
“Raise clay” and “Form down cyclic clay” exhibit differences
across the three vase types (i.e. bowl, cylinder,
and sphere), although perceived as identical. More details can be found in conference publication . A visualization of the methodology is shown below.
We introduce the DanceAnno motion trajectory annotation tool which we offer publicly as open-source software here. The tool allows a user to generate annotation for the motion trajectory data and store the file in a txt file. Written in Python 3 and Tcl.
Drag'n'drop and real-time update of video frame are supported.
FastAR lets you exploit open tools, i.e. Sobipro in a Joomla framework, and commercial tools such as the three major augmented reality browsers, namely Junaio, Layar, Wikitude to make Augmented Reality without any code writting! Free to download [here]
FastAR has been qualified for the EU Innovation Radar Prize 2016. Passed to the B' phase with 1100 votes and it was presented to a board of venture capitalists in Proposer's day 2016 in Bratislava. Unfortunately did not qualified for the next round but it attracted the attention of a great audience.
ImproveMyCity-Mobile is the Android counterpart of the IMC Joomla component to report, vote and track non-emergency issues [Conf. Pub. 17]. The application enables citizens to report local problems such as potholes, illegal trash dumping, faulty street lights, broken tiles on sidewalks, and illegal advertising boards. Source code for mobile available at github.
Neurally adjusted ventilatory assist (NAVA) delivers airway pressure (P_aw) in proportion to the electrical activity of the diaphragm (EAdi) using an adjustable proportionality constant (NAVA level, cm H_20/microvolt). During systematic increases in the NAVA level, feedback-controlled down-regulation of the EAdi results in a characteristic two-phased response in P_aw and tidal volume (Vt). The transition from the 1st to the 2nd response phase allows identification of adequate unloading of the respiratory muscles with NAVA (NAVA_AL). We aimed to develop and validate a mathematical algorithm to identify NAVA_AL. More details can be found in published journal manuscript 7 [pdf].
Signals like airway pressure and electrical activity of the diaphragm are recorded.
Software developed in Matlab for the automatic estimation of NAVA adequate level.
A tool to convert human whistling sounds to piano notes by employing the spectrogram of the sound. Notes can be exported to Music xml format for further processing [pdf]. Implemented for Symbian 60 3rd Edition FP2 using python language.
VocalTract.sty is a Latex package to visualize the vocal tract. Further information can be found in journal paper . The package can be downloaded from [CTAN]. VTCalcs users: In order to install my software as a plug-in download also the update version of arcb.m
The information loss is estimated and exploited to set a lower limit for the correct classification rate achieved by the Bayes classifier that is used in subset feature selection. Details of the method can be found in journal paper . The functions to estimate the lower limit of correct classification rate (CCR) can be downloaded from Matlab File Exchange.
The target of the software is to divide speech into 3 classes: Silence, Male, Female. In Stage 1, speech is classified into voiced or unvoiced frames by applying Gabor filtering and energy tracking by a method of G. Evangelopoulos. In Stage 2, it is assumed that if two speakers exist, then they would have significant different fundamental frequency and energy below 150 Hz regions, i.e. one actor would tend to be bass and the other will tend to be soprano, these differences are tracked again with the GMM algorithm. This method can be found in  at Journal Publications Section.
Feature selection algorithms with graphical user interface for loading a pattern x features matrix and selecting the subset of features that maximizes correct classification rate. The proposed Sequential Forward Selection (SFS) employs preliminary rejections and tentative cross-validation repetittions, to improve the speed and the accuracy of SFS, respectively. Further information can be found in journal paper  and conference announcement . A demo version can be downloaded from Download from Matlab file exchage site.
The Expectation-Maximization algorithm (EM) is widely used to find the parameters of a mixture of Gaussian probability density functions (pdfs) or briefly Gaussian components that fits the sample measurement vectors in maximum likelihood sense. In our work, the expectation-maximization (EM) algorithm for Gaussian mixture modeling is improved via three statistical tests: a) A multivariate normality test, b) a central tendency (kurtosis) criterion, and c) a test based on marginal cdf to find a discriminant to split a non-Gaussian component. Details of the method can be found in journal paper . The method can be downloaded from: Download from Matlab file exchange.
Small scale car development using LEGO parts. A 50 cm length solar car that stores the energy in Ni-Mh batteries. The car can be either remote controled or machine controled using the NXT brick processor. Project site http://code.google.com/p/lazy-summer-car/
Digital Speech Processing Techniques for Emotion Recognition ([pdf], Greek)
Supervisor: Associate Professor Constantine Kotropoulos
Artificial Intelligence and Information Analysis Laboratory, Dept. Informatics Aristotle Univ. of Thessaloniki (AUTH)
1. D. Ververidis, S. Nikolopoulos, S. Papadopoulos, I. Kompatsiaris, "Citizen Sensing for Reality mining in urban spaces," chapter in book Network Design and Optimization for Smart Cities, Ed. Konstantinos Gakis, Panos Pardalos. World Scientific, Vol. 8, Mar. 2017, 400pp, ISBN-978-981-3200-00-5.
1. Dimitrios Ververidis and Constantine Kotropoulos, "Emotional speech recognition: Resources, features, methods, and applications," Elsevier Speech Communication, vol. 48, issue 9, pp. 1162-1181, Sep. 2006. [pdf]
2. Vassiliki Moschou, Dimitrios Ververidis, Constantine Kotropoulos, "Assessment of self organizing map variants for clustering with application to redistribution of emotional speech patterns," Elsevier Neurocomputing, vol. 71, issues 1-3, pp. 147-156, 2007. [pdf]
3. Dimitrios Ververidis and Constantine Kotropoulos, "Gaussian mixture modeling by exploiting the Mahalanobis distance," IEEE Trans. Signal Processing, vol. 56, issue 7B, pp. 2797-2811, 2008. [pdf]
4. Dimitrios Ververidis and Constantine Kotropoulos, "Fast and accurate feature subset selection applied into speech emotion recognition," Elsevier Signal Processing, vol. 88, issue 12, pp. 2956-2970, 2008. [pdf]
5. M. Kotti, D. Ververidis, G. Evangelopoulos, I. Panagakis, C. Kotropoulos, P. Maragos, and I. Pitas, "Audio-assisted movie dialogue detection," IEEE Trans. Circuits and Systems for Video Technology, vol. 18, issue 11, pp. 1618-1627, 2008. [pdf]
6. Dimitrios Ververidis and Constantine Kotropoulos, "Information loss of the Mahalanobis distance in high dimensions: Application to feature selection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 12, pp. 2275-2281, 2009. [pdf]
7. Dimitrios Ververidis, Mark Van Gils, Christina Passath, Jukka Takala and Lukas Brander, "Identification of adequate neurally adjusted ventilatory assist (NAVA) during systematic increases in the NAVA level," IEEE Trans. Biomedical Engineering, vol. 58, no. 9, pp. 2598-2606, Sept. 2011. [pdf]
8. Dimitrios Ververidis, Daniel Schneider, and Joachim Koehler, "The vocal tract LaTeX package," PracTeX journal, no 1, 2012 [pdf]. Package available at CTAN.
9. Abrams G., Di Modica K., Bezombes F., Bonjean D., Burton D., Hardy A., Lilley F., Nikolopoulos S., Precioso F., Strecha C, Thomaidou E., Ververidis D. & De Groote I., 2016. DigiArt: towards a virtualization of Cultural Heritage. Notae Praehistoricae, 36/2016 : 131-142 [pdf].
1. D. Ververidis and C. Kotropoulos, "A Review of Emotional Speech Databases," in Proc. 9th Panhellenic Conference on informatics (PCI), pp. 560-574, Thessaloniki, Greece, November 2003. [pdf]
2. D. Ververidis and C. Kotropoulos, "A State of the Art Review on Emotional Speech Databases," in Proc. 1st Richmedia Conference, pp. 109-119, Laussane, Oktober 2003. [pdf]
3. D. Ververidis, C. Kotropoulos and I. Pitas, "Automatic Emotional Speech Classification," in Proc. Int. Conf. Acoustics Speech and Signal Processing (ICASSP), vol. 1, pp. 593-596, Montreal, Canada, 2004. [pdf]
4. D. Ververidis and C. Kotropoulos, "Automatic Speech Classification to Five Emotional States Based on Gender Information," in Proc. European Signal Processing Conference (EUSIPCO), pp. 341–344, Austria, 2004. [pdf]
5. D. Ververidis and C. Kotropoulos, "Emotional speech classification using Gaussian mixture models," in Proc. IEEE Inter. Symposium on Circuits and Systems (ISCAS), Japan, 2005. [pdf]
6. D. Ververidis and C. Kotropoulos, "Emotional speech classification using Gaussian mixture models and the Sequential Floating Forward Selection algorithm," in Proc. IEEE Int. Conf. on Multimedia & Expo. (ICME), Amsterdam, 2005. [pdf]
7. D. Ververidis and C. Kotropoulos, "Sequential forward feature selection with low computational cost," in Proc. European Signal Processing Conference (EUSIPCO), Antalya, Turkey, 2005. [pdf]
8. D. Ververidis and C. Kotropoulos, "Fast Sequential Floating Forward Selection applied to emotional speech features estimated on DES and SUSAS data collections," in Proc. European Signal Processing Conf. (EUSIPCO), Italy, 2006. [pdf]
9. M. Haindl, P. Somol, D. Ververidis, and C. Kotropoulos, "Feature Selection Based on Mutual Correlation," in Proc. 11th Iberoamerican Congress on Pattern Recognition (CIAPR), Mexico, 2006. [pdf]
10. V. Moschou, D. Ververidis and C. Kotropoulos, "On the variants of the self-organizing map that are based on order statistics," in Proc. Inter. Conf. Artificial Neural Networks (ICANN), Athens, Sep. 2006. [pdf]
11. M. Sedaaghi, D. Ververidis and C. Kotropoulos, "Improving speech emotion recognition using adaptive genetic algorithms," in Proc. European Signal Processing Conference (EUSIPCO), Polland, 2007. [pdf]
12. D. Ververidis and C. Kotropoulos, "Accurate estimate of the cross-validated prediction error variance in Bayes classifiers," in Proc. Machine Learning for Signal Processing (MLSP), Thessaloniki, 2007. [pdf]
13. M. Sedaaghi, C. Kotropoulos, and D. Ververidis, "Using adaptive genetic algorithms to improve speech emotion recognition," in Proc. IEEE Workshop Multimedia Signal Processing (MMSP), Crete, 2007. [pdf]
14. D. Ververidis, I. Kotsia, C. Kotropoulos, and Ioannis Pitas, "Multi-modal emotion-related data collection within a virtual earthquake emulator," in Proc. Inter. Conf. Language Resources and Evaluation (LREC), Morocco, 2008. [pdf]
15. D. Ververidis, M. Van Gils, J. Koikkalainen, and J. Lotjonen, "Feature selection and time regression software: Application on predicting Alzheimer's disease progress," in Proc. European Signal Processing Conference (EUSIPCO), Aalborg, 2010. [pdf]
16. J. Mattila, H. Soininen, D. Ververidis, M. van Gils, J. Lotjonen, G. Waldemar, A. H. Simonsen, D. Rueckert, L. Thurfjell, and J. Koikkalainen, "Clinical decision support system based on statistical analysis of heterogeneous clinical data and Alzheimer biomarkers," in Proc. Intern. Conf. Alzheimer's Disease (ICAD), Hawaii, 2010.
17. I. Tsampoulatidis, D. Ververidis, P. Tsarchopoulos, S. Nikolopoulos, I. Kompatsiaris, N. Komninos, "ImproveMyCity – An open source platform for direct citizen-government communication," in Proc. ACM Intern. Conf. Multimedia, 2013. [pdf]
18. D. Ververidis, S. Nikolopoulos, and I. Kompatsiaris, "Transforming your website to an Augmented Reality view," in Proc. IEEE Intern. Symp. on Mixed and Augmented Reality (ISMAR), Fukuoka, 2015. [pdf]
19. S. Karavarsamis, D. Ververidis, G. Chantas, S. Nikolopoulos and Y. Kompatsiaris, "Classification of Salsa Dance Steps from Skeletal Poses," in Proc. Intern. WS on Content Based Multimedia Indexing (CBMI), Bucharest, 2016.
20. D. Ververidis, S. Karavarsamis, S. Nikolopoulos, and I. Kompatsiaris, "Pottery gestures style comparison by exploiting Myo sensor and forearm anatomy," in Proc. ACM International Symposium on Movement and Computing (MOCO), Thessaloniki, 2016. [pdf]
21. E. Anastasovitis, D. Ververidis, S. Nikolopoulos, and I. Kompatsiaris, "DigiArt: Building new 3D cultural heritage worlds," in Proc. IEEE 3DTV-Conference, Copenhagen, 2017.
22. A. Karakostas, D. Ververidis, S. Nikolopoulos, I. Kompatsiaris, "SpAtiAL: A Sensor based Framework to Support Affective Learning," in Proc. IEEE 3DTV-Conference, Copenhagen, 2017.