2022
Loi, Iliana; Grammatikaki, Angeliki; Tsinganos, Panagiotis; Bozkir, Efe; Ampeliotis, Dimitris; Moustakas, Konstantinos; Kasneci, Enkelejda; Skodras, Athanassios
Proportional Myoelectric Control in a Virtual Reality Environment Proceedings Article
In: 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), IEEE, Nafplio, Greece, 2022.
Abstract | Links | BibTeX | Tags: Deep learning, hand gesture recognition, proportional myoelectric control, semg, virtual reality
@inproceedings{nokey,
title = {Proportional Myoelectric Control in a Virtual Reality Environment},
author = {Iliana Loi and Angeliki Grammatikaki and Panagiotis Tsinganos and Efe Bozkir and Dimitris Ampeliotis and Konstantinos Moustakas and Enkelejda Kasneci and Athanassios Skodras},
doi = {10.1109/IVMSP54334.2022.9816252},
year = {2022},
date = {2022-07-11},
urldate = {2022-07-11},
booktitle = {2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)},
publisher = {IEEE},
address = {Nafplio, Greece},
abstract = {Translating input modalities such as hand interactions, speech, and eye tracking in virtual reality offers an immersive user experience. Especially, it is crucial to track the user’s hand gestures, since they can help in translating user intentions into actions in virtual environments. In this work, we developed a virtual reality application which incorporates electromyography-based deep learning methods for recognizing and estimating hand movements in an online fashion. Our application automates all user controls, providing an immense potential for rehabilitation purposes.},
keywords = {Deep learning, hand gesture recognition, proportional myoelectric control, semg, virtual reality},
pubstate = {published},
tppubtype = {inproceedings}
}
Tsinganos, Panagiotis; Jansen, Bart; Cornelis, Jan; Skodras, Athanassios
Real-Time Analysis of Hand Gesture Recognition with Temporal Convolutional Networks Journal Article
In: Sensors, vol. 22, no. 5, pp. 1694, 2022.
Abstract | Links | BibTeX | Tags: attention, CNN, Deep learning, hand gesture recognition, real time, semg, TCN
@article{Tsinganos2022,
title = {Real-Time Analysis of Hand Gesture Recognition with Temporal Convolutional Networks},
author = {Panagiotis Tsinganos and Bart Jansen and Jan Cornelis and Athanassios Skodras},
editor = {Antonio Fernández-Caballero and Juan M. Corchado},
url = {https://www.mdpi.com/1424-8220/22/5/1694},
doi = {10.3390/s22051694},
year = {2022},
date = {2022-02-22},
urldate = {2022-02-22},
journal = {Sensors},
volume = {22},
number = {5},
pages = {1694},
abstract = {In recent years, the successful application of Deep Learning methods to classification problems has had a huge impact in many domains. (1) Background: In biomedical engineering, the problem of gesture recognition based on electromyography is often addressed as an image classification problem using Convolutional Neural Networks. Recently, a specific class of these models called Temporal Convolutional Networks (TCNs) has been successfully applied to this task. (2) Methods: In this paper, we approach electromyography-based hand gesture recognition as a sequence classification problem using TCNs. Specifically, we investigate the real-time behavior of our previous TCN model by performing a simulation experiment on a recorded sEMG dataset. (3) Results: The proposed network trained with data augmentation yields a small improvement in accuracy compared to our existing model. However, the classification accuracy is decreased in the real-time evaluation, showing that the proposed TCN architecture is not suitable for such applications. (4) Conclusions: The real-time analysis helps in understanding the limitations of the model and exploring new ways to improve its performance.},
keywords = {attention, CNN, Deep learning, hand gesture recognition, real time, semg, TCN},
pubstate = {published},
tppubtype = {article}
}
2021
Tsinganos, Panagiotis; Cornelis, Jan; Cornelis, Bruno; Jansen, Bart; Skodras, Athanassios
Transfer Learning in sEMG-based Gesture Recognition Proceedings Article
In: 2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA), IEEE, Chania, Crete, Greece, 2021.
Abstract | Links | BibTeX | Tags: Deep learning, hand gesture recognition, semg, transfer learning
@inproceedings{Tsinganos_et_al_transfer2021,
title = {Transfer Learning in sEMG-based Gesture Recognition},
author = {Panagiotis Tsinganos and Jan Cornelis and Bruno Cornelis and Bart Jansen and Athanassios Skodras},
url = {https://ieeexplore.ieee.org/abstract/document/9555555},
doi = {10.1109/IISA52424.2021.9555555},
year = {2021},
date = {2021-10-08},
urldate = {2021-10-08},
booktitle = {2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA)},
publisher = {IEEE},
address = {Chania, Crete, Greece},
abstract = {The latest advancements in the field of deep learning and biomedical engineering have allowed for the development of myoelectric interfaces based on deep neural networks. A longstanding problem of these interfaces is that the models cannot easily be applied to new users due to the high variability and stochastic nature of the electromyography signals. Further training a new model for every new subject requires the collection of large volumes of data. Therefore, this work proposes a transfer learning (TL) scheme which allows reusing the knowledge of a pre-existing model for a new user. Firstly, a convolutional neural network (CNN) is trained on an initial dataset using the data of multiple subjects. Then, the weights of this model are fine-tuned for a new target subject. The approach is evaluated on the Ninapro datasets DB2 and DB7. The experimentation included three different CNN models and eight preprocessing alternatives. The results showed that the success of the TL method depends on how the data are preprocessed. Specifically, the biggest accuracy improvement (+5.14%) is achieved when only the first 20% of the signal duration is used.},
keywords = {Deep learning, hand gesture recognition, semg, transfer learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Tsinganos, Panagiotis; Cornelis, Bruno; Cornelis, Jan; Jansen, Bart; Skodras, Athanassios
The Effect of Space-filling Curves on the Efficiency of Hand Gesture Recognition Based on sEMG Signals Journal Article
In: International Journal of Electrical and Computer Engineering Systems, vol. 12, no. 1, pp. 23 - 31, 2021, ISSN: 1847-6996.
Abstract | Links | BibTeX | Tags: classification, CNN, Deep learning, electromyography, hand gesture recognition, hilbert curve, Peano curve, semg, space-filling curve, Z-order curve
@article{Tsinganos2021,
title = {The Effect of Space-filling Curves on the Efficiency of Hand Gesture Recognition Based on sEMG Signals},
author = {Panagiotis Tsinganos and Bruno Cornelis and Jan Cornelis and Bart Jansen and Athanassios Skodras},
url = {https://ijeces.ferit.hr/index.php/ijeces/article/view/345},
doi = {10.32985/ijeces.12.1.3},
issn = {1847-6996},
year = {2021},
date = {2021-04-21},
journal = {International Journal of Electrical and Computer Engineering Systems},
volume = {12},
number = {1},
pages = {23 - 31},
abstract = {Over the past few years, Deep learning (DL) has revolutionized the field of data analysis. Not only are the algorithmic paradigms changed, but also the performance in various classification and prediction tasks has been significantly improved with respect to the state-of-the-art, especially in the area of computer vision. The progress made in computer vision has produced a spillover in many other domains, such as biomedical engineering. Some recent works are directed towards surface electromyography (sEMG) based hand gesture recognition, often addressed as an image classification problem and solved using tools such as Convolutional Neural Networks (CNN). This paper extends our previous work on the application of the Hilbert space-filling curve for the generation of image representations from multi-electrode sEMG signals, by investigating how the Hilbert curve compares to the Peano- and Z-order space-filling curves. The proposed space-filling mapping methods are evaluated on a variety of network architectures and in some cases yield a classification improvement of at least 3%, when used to structure the inputs before feeding them into the original network architectures.},
keywords = {classification, CNN, Deep learning, electromyography, hand gesture recognition, hilbert curve, Peano curve, semg, space-filling curve, Z-order curve},
pubstate = {published},
tppubtype = {article}
}
2020
Tsinganos, Panagiotis; Cornelis, Bruno; Cornelis, Jan; Jansen, Bart; Skodras, Athanassios
Data Augmentation of Surface Electromyography for Hand Gesture Recognition Journal Article
In: Sensors, vol. 20, no. 17, pp. 4892, 2020, ISSN: 1424-8220.
Abstract | Links | BibTeX | Tags: CNN, data augmentation, Deep learning, electromyography, hand gesture recognition, semg
@article{Tsinganos2020b,
title = {Data Augmentation of Surface Electromyography for Hand Gesture Recognition},
author = {Panagiotis Tsinganos and Bruno Cornelis and Jan Cornelis and Bart Jansen and Athanassios Skodras},
doi = {10.3390/s20174892},
issn = {1424-8220},
year = {2020},
date = {2020-08-29},
journal = {Sensors},
volume = {20},
number = {17},
pages = {4892},
abstract = {The range of applications of electromyography-based gesture recognition has increased over the last years. A common problem regularly encountered in literature is the inadequate data availability. Data augmentation, which aims at generating new synthetic data from the existing ones, is the most common approach to deal with this data shortage in other research domains. In the case of surface electromyography (sEMG) signals, there is limited research in augmentation methods and quite regularly the results differ between available studies. In this work, we provide a detailed evaluation of existing (i.e., additive noise, overlapping windows) and novel (i.e., magnitude warping, wavelet decomposition, synthetic sEMG models) strategies of data augmentation for electromyography signals. A set of metrics (i.e., classification accuracy, silhouette score, and Davies–Bouldin index) and visualizations help with the assessment and provides insights about their performance. Methods like signal magnitude warping and wavelet decomposition yield considerable increase (up to 16%) in classification accuracy across two benchmark datasets. Particularly, a significant improvement of 1% in the classification accuracy of the state-of-the-art model in hand gesture recognition is achieved.},
keywords = {CNN, data augmentation, Deep learning, electromyography, hand gesture recognition, semg},
pubstate = {published},
tppubtype = {article}
}
Tsinganos, Panagiotis; Cornelis, Bruno; Cornelis, Jan; Jansen, Bart; Skodras, Athanassios
Hilbert sEMG data scanning for hand gesture recognition based on deep learning Journal Article
In: Neural Computing and Applications, 2020, ISBN: 1433-3058.
Abstract | Links | BibTeX | Tags: classification, CNN, Deep learning, electromyography, hand gesture recognition, hilbert curve, Multi-scale, semg
@article{Tsinganos2020,
title = {Hilbert sEMG data scanning for hand gesture recognition based on deep learning},
author = {Panagiotis Tsinganos and Bruno Cornelis and Jan Cornelis and Bart Jansen and Athanassios Skodras},
url = {https://github.com/DSIP-UPatras/sEMG-hilbert-curve},
doi = {10.1007/s00521-020-05128-7},
isbn = {1433-3058},
year = {2020},
date = {2020-07-07},
journal = {Neural Computing and Applications},
abstract = {Deep learning has transformed the field of data analysis by dramatically improving the state of the art in various classification and prediction tasks, especially in the area of computer vision. In biomedical engineering, a lot of new work is directed toward surface electromyography (sEMG)-based gesture recognition, often addressed as an image classification problem using convolutional neural networks (CNNs). In this paper, we utilize the Hilbert space-filling curve for the generation of image representations of sEMG signals, which allows the application of typical image processing pipelines such as CNNs on sequence data. The proposed method is evaluated on different state-of-the-art network architectures and yields a significant classification improvement over the approach without the Hilbert curve. Additionally, we develop a new network architecture (MSHilbNet) that takes advantage of multiple scales of an initial Hilbert curve representation and achieves equal performance with fewer convolutional layers.},
keywords = {classification, CNN, Deep learning, electromyography, hand gesture recognition, hilbert curve, Multi-scale, semg},
pubstate = {published},
tppubtype = {article}
}
2019
Annousakis-Giannakopoulos, Konstantinos; Ampeliotis, Dimitrios; Skodras, Athanassios
Could DCT Reveal Photorealistic Images? Proceedings Article
In: 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), pp. 1-5, 2019.
Abstract | Links | BibTeX | Tags: Computer Graphics, DCT, Digital forensics, Discrete Cosine Transform, Fake Photos, Photorealism, Quantization
@inproceedings{Annousakis-Giannakopoulos2019,
title = {Could DCT Reveal Photorealistic Images?},
author = {Konstantinos Annousakis-Giannakopoulos and Dimitrios Ampeliotis and Athanassios Skodras},
doi = {10.1109/IISA.2019.8900752},
year = {2019},
date = {2019-07-01},
booktitle = {2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)},
pages = {1-5},
abstract = {With the development of computer graphics rendering software, it has become extremely difficult to distinguish whether an image is computer generated or a natural one. Therefore, it is really important to device robust methods for correctly classifying these two categories of images. In this work, a new approach to face the above problem is developed that is based upon the discrete cosine transform (DCT) of an image, in the YCbCr color space. The statistical features extracted, have been tested in suitable databases and the remarkable results indicate that the proposed model has a great potential to be used in digital images forensics.},
keywords = {Computer Graphics, DCT, Digital forensics, Discrete Cosine Transform, Fake Photos, Photorealism, Quantization},
pubstate = {published},
tppubtype = {inproceedings}
}
Tsagkas, Nikolaos; Tsinganos, Panagiotis; Skodras, Athanassios
On the Use of Deeper CNNs in Hand Gesture Recognition Based on sEMG Signals Proceedings Article
In: 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), pp. 1-4, 2019.
Abstract | Links | BibTeX | Tags: classification, CNN, Convolutional Neural Networks, data acquisition, database, Deep learning, hand gesture recognition, semg, signal processing, surface electromyography
@inproceedings{Tsagkas2019,
title = {On the Use of Deeper CNNs in Hand Gesture Recognition Based on sEMG Signals},
author = {Nikolaos Tsagkas and Panagiotis Tsinganos and Athanassios Skodras},
doi = {10.1109/IISA.2019.8900709},
year = {2019},
date = {2019-07-01},
booktitle = {2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)},
pages = {1-4},
abstract = {In the past few years, a great interest for the classification of hand gestures with Deep Learning methods based on surface electromyography (sEMG) signals has been developed in the scientific community. In line with latest works in the field, the objective of our work is the construction of a novel Convolutional Neural Network architecture, for the classification of hand-gestures. Our model, while avoiding overfitting, did not perform significantly better compared to a much shallower network. The results suggest that the lack of diversity in the sEMG recordings between certain hand-gestures limits the performance of the model. In addition, the classification accuracy on a database we developed using a commercial device (Myo Armband) was substantially higher (approximately 24%) than a similar benchmark dataset recorded with the same device.},
keywords = {classification, CNN, Convolutional Neural Networks, data acquisition, database, Deep learning, hand gesture recognition, semg, signal processing, surface electromyography},
pubstate = {published},
tppubtype = {inproceedings}
}
Tsinganos, Panagiotis; Cornelis, Bruno; Cornelis, Jan; Jansen, Bart; Skodras, Athanassios
A Hilbert Curve Based Representation of sEMG Signals for Gesture Recognition Proceedings Article
In: 2019 International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 201–206, IEEE, Osijek, Croatia, 2019, ISBN: 978-1-7281-3253-2.
Links | BibTeX | Tags: classification, CNN, Deep learning, electromyography, hand gesture recognition, hilbert curve, semg
@inproceedings{Tsinganos2019b,
title = {A Hilbert Curve Based Representation of sEMG Signals for Gesture Recognition},
author = {Panagiotis Tsinganos and Bruno Cornelis and Jan Cornelis and Bart Jansen and Athanassios Skodras},
url = {https://ieeexplore.ieee.org/document/8787290/},
doi = {10.1109/IWSSIP.2019.8787290},
isbn = {978-1-7281-3253-2},
year = {2019},
date = {2019-06-01},
booktitle = {2019 International Conference on Systems, Signals and Image Processing (IWSSIP)},
pages = {201--206},
publisher = {IEEE},
address = {Osijek, Croatia},
keywords = {classification, CNN, Deep learning, electromyography, hand gesture recognition, hilbert curve, semg},
pubstate = {published},
tppubtype = {inproceedings}
}
Tsinganos, Panagiotis; Cornelis, Bruno; Cornelis, Jan; Jansen, Bart; Skodras, Athanassios
Improved Gesture Recognition Based on sEMG Signals and TCN Proceedings Article
In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1169–1173, IEEE, Brighton, UK, 2019, ISBN: 978-1-4799-8131-1.
Abstract | Links | BibTeX | Tags: CNN, Deep learning, Gesture Recognition, semg, TCN
@inproceedings{Tsinganos2019c,
title = {Improved Gesture Recognition Based on sEMG Signals and TCN},
author = {Panagiotis Tsinganos and Bruno Cornelis and Jan Cornelis and Bart Jansen and Athanassios Skodras},
url = {https://ieeexplore.ieee.org/document/8683239/},
doi = {10.1109/ICASSP.2019.8683239},
isbn = {978-1-4799-8131-1},
year = {2019},
date = {2019-05-01},
booktitle = {ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {1169--1173},
publisher = {IEEE},
address = {Brighton, UK},
abstract = {In recent years, the successful application of Deep Learning methods to classification problems has had a huge impact in many domains. In biomedical engineering, the problem of gesture recognition based on electromyography is often addressed as an image classification problem using Convolutional Neural Networks. In this paper, we approach electromyography-based hand gesture recognition as a sequence classification problem using Temporal Convolutional Networks. The proposed network yields an improvement in gesture recognition of almost 5% to the state of the art reported in the literature, whereas the analysis helps in understanding the limitations of the model and exploring new ways to improve its performance.},
keywords = {CNN, Deep learning, Gesture Recognition, semg, TCN},
pubstate = {published},
tppubtype = {inproceedings}
}
Tsinganos, Panagiotis; Cornelis, Bruno; Cornelis, Jan; Jansen, Bart; Skodras, Athanassios
Hand Gesture Recognition Based on EMG Data: A Convolutional Neural Network Approach Book Chapter
In: Lecture Notes in Computer Science, pp. 180–197, Springer, Cham, 2019.
Abstract | Links | BibTeX | Tags: Ablation study, Biomedical engineering, CNN, Deep learning, Label smoothing, sEMG hand gesture recognition
@inbook{Tsinganos2019c,
title = {Hand Gesture Recognition Based on EMG Data: A Convolutional Neural Network Approach},
author = {Panagiotis Tsinganos and Bruno Cornelis and Jan Cornelis and Bart Jansen and Athanassios Skodras},
url = {http://link.springer.com/10.1007/978-3-030-27950-9_10},
doi = {10.1007/978-3-030-27950-9_10},
year = {2019},
date = {2019-01-01},
booktitle = {Lecture Notes in Computer Science},
pages = {180--197},
publisher = {Springer, Cham},
abstract = {Deep learning (DL) has transformed the field of data analysis by dramatically improving the state of the art in various classification and prediction tasks. Especially in the area of computer vision and speech processing, DL has recently demonstrated better performance and generalisation properties, compared to classical machine learning approaches, which are based on the extraction of hand-crafted model-based features followed by classification. Hand gestures and speech constitute two of the most important modalities in human-to-human communication and man-machine interaction. In biomedical engineering, a lot of new work is directed towards electromyography-based gesture recognition. In this paper, we present a brief overview of DL methods for electromyography-based hand gesture recognition and then we select from literature a simple model based on Convolutional Neural Networks that we consider as the baseline model. The proposed modifications to the baseline model yield a 3% classification improvement. In the current paper, we concentrate on the explanatory analysis of this performance improvement. An ablation study identifies which modifications are the most important ones, and label smoothing is investigated to verify if the results can be improved by reducing a priori bias. The analysis helps in understanding the limitations of the model and exploring new ways to improve the performance.},
keywords = {Ablation study, Biomedical engineering, CNN, Deep learning, Label smoothing, sEMG hand gesture recognition},
pubstate = {published},
tppubtype = {inbook}
}
2018
Vasilopoulos, Christos; Skodras, Athanassios
A Novel Finger Vein Recognition System Based on Enhanced Maximum Curvature Points Proceedings Article
In: 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), pp. 1-5, 2018.
Abstract | Links | BibTeX | Tags: biometrics, Enhanced Maximum Curvature Points, feature extraction, finger vein recognition, Personal identification
@inproceedings{Vasilopoulos2018,
title = {A Novel Finger Vein Recognition System Based on Enhanced Maximum Curvature Points},
author = {Christos Vasilopoulos and Athanassios Skodras},
doi = {10.1109/IVMSPW.2018.8448746},
year = {2018},
date = {2018-06-01},
booktitle = {2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)},
pages = {1-5},
abstract = {Finger vein recognition is a biometric method of authentication that offers high security, efficiency and stability. In this paper we propose a new finger vein recognition system that utilizes the Enhanced Maximum Curvature Points (EMC) technique for finger vein pattern extraction and introduces a new pre-processing stage. In addition, it combines two matching methods, leading to better recognition performance in terms of EER, FAR, FRR and recognition rate than other methods. We present the experimental results obtained by applying our system on the databases SDUMLA-HMT, Tsingua, FV-USM and HKPU and compare them with similar approaches applied on these databases.},
keywords = {biometrics, Enhanced Maximum Curvature Points, feature extraction, finger vein recognition, Personal identification},
pubstate = {published},
tppubtype = {inproceedings}
}
Tsinganos, Panagiotis; Skodras, Athanassios
On the Comparison of Wearable Sensor Data Fusion to a Single Sensor Machine Learning Technique in Fall Detection Journal Article
In: Sensors, vol. 18, no. 2, pp. 592, 2018, ISSN: 1424-8220.
Abstract | Links | BibTeX | Tags: accelerometer, data fusion, fall detection, gyroscope, mHealth, smartphone, wearable sensors
@article{Tsinganos2018b,
title = {On the Comparison of Wearable Sensor Data Fusion to a Single Sensor Machine Learning Technique in Fall Detection},
author = {Panagiotis Tsinganos and Athanassios Skodras},
url = {http://www.mdpi.com/1424-8220/18/2/592},
doi = {10.3390/s18020592},
issn = {1424-8220},
year = {2018},
date = {2018-02-01},
journal = {Sensors},
volume = {18},
number = {2},
pages = {592},
abstract = {In the context of the ageing global population, researchers and scientists have tried to find solutions to many challenges faced by older people. Falls, the leading cause of injury among elderly, are usually severe enough to require immediate medical attention; thus, their detection is of primary importance. To this effect, many fall detection systems that utilize wearable and ambient sensors have been proposed. In this study, we compare three newly proposed data fusion schemes that have been applied in human activity recognition and fall detection. Furthermore, these algorithms are compared to our recent work regarding fall detection in which only one type of sensor is used. The results show that fusion algorithms differ in their performance, whereas a machine learning strategy should be preferred. In conclusion, the methods presented and the comparison of their performance provide useful insights into the problem of fall detection.},
keywords = {accelerometer, data fusion, fall detection, gyroscope, mHealth, smartphone, wearable sensors},
pubstate = {published},
tppubtype = {article}
}
Tsinganos, Panagiotis; Cornelis, Bruno; Cornelis, Jan; Jansen, Bart; Skodras, Athanassios
Deep Learning in EMG-based Gesture Recognition Proceedings Article
In: Proceedings of the 5th International Conference on Physiological Computing Systems, pp. 107–114, SCITEPRESS - Science and Technology Publications, Seville, Spain, 2018, ISBN: 978-989-758-329-2.
Abstract | Links | BibTeX | Tags: CNN, Deep learning, Gesture Recognition, semg
@inproceedings{Tsinganos2018b,
title = {Deep Learning in EMG-based Gesture Recognition},
author = {Panagiotis Tsinganos and Bruno Cornelis and Jan Cornelis and Bart Jansen and Athanassios Skodras},
url = {http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0006960201070114},
doi = {10.5220/0006960201070114},
isbn = {978-989-758-329-2},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 5th International Conference on Physiological Computing Systems},
pages = {107--114},
publisher = {SCITEPRESS - Science and Technology Publications},
address = {Seville, Spain},
abstract = {In recent years, Deep Learning methods have been successfully applied to a wide range of image and speech recognition problems highly impacting other research fields. As a result, new works in biomedical engineering are directed towards the application of these methods to electromyography-based gesture recognition. In this paper, we present a brief overview of Deep Learning methods for electromyography-based hand gesture recognition along with an analysis of a modified simple model based on Convolutional Neural Networks. The proposed network yields a 3% improvement on the classification accuracy of the basic model, whereas the analysis helps in understanding the limitations of the model and exploring new ways to improve the performance.},
keywords = {CNN, Deep learning, Gesture Recognition, semg},
pubstate = {published},
tppubtype = {inproceedings}
}
Tsinganos, Panagiotis; Skodras, Athanassios; Cornelis, Bruno; Jansen, Bart
Deep Learning in Gesture Recognition Based on sEMG Signals Book Chapter
In: Ring, Francis; Siu, Wan-Chi; Chau, Lap-Pui; Wang, Liang; Tang, Tieniu (Ed.): Learning Approaches in Signal Processing, Chapter 13, pp. 471, Pan Stanford Publishing, 1, 2018, ISBN: 9780429590320.
Abstract | Links | BibTeX | Tags:
@inbook{Tsinganos2018c,
title = {Deep Learning in Gesture Recognition Based on sEMG Signals},
author = {Panagiotis Tsinganos and Athanassios Skodras and Bruno Cornelis and Bart Jansen},
editor = {Francis Ring and Wan-Chi Siu and Lap-Pui Chau and Liang Wang and Tieniu Tang},
url = {https://books.google.be/books?id=n4V7DwAAQBAJ https://www.taylorfrancis.com/books/9780429592263/chapters/10.1201/9780429061141-23},
doi = {10.1201/9780429061141-23},
isbn = {9780429590320},
year = {2018},
date = {2018-01-01},
booktitle = {Learning Approaches in Signal Processing},
pages = {471},
publisher = {Pan Stanford Publishing},
edition = {1},
chapter = {13},
abstract = {Over the past years, Deep Learning methods have shown promising results to a wide range of research fields including image classification and natural language processing. Their increased success rates have drawn the attention of many researchers from various domains. This chapter investigates the application of Deep Learning methods to the problem of electromyography-based gesture recognition. A signal processing pipeline based on Deep Learning is presented through examples taken from the literature, whereas the details of state-of-the-art neural network architectures are discussed. In addition, this chapter illustrates a few ways adopted from image classification tasks that visualize what the neural network learns. Finally, new approaches are proposed and evaluated with publicly available datasets.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Pyrgas, Lampros; Kitsos, Paris; Skodras, Athanassios
Compact FPGA architectures for the two-band fast discrete Hartley transform Journal Article
In: Microprocessors and Microsystems, vol. 61, pp. 117 - 125, 2018, ISSN: 0141-9331.
Abstract | Links | BibTeX | Tags: Digital signal processing, FPGA architecture, Two-band fast discrete hartley transform, VHDL
@article{Pyrgas2018b,
title = {Compact FPGA architectures for the two-band fast discrete Hartley transform},
author = {Lampros Pyrgas and Paris Kitsos and Athanassios Skodras},
url = {http://www.sciencedirect.com/science/article/pii/S0141933118300358},
doi = {https://doi.org/10.1016/j.micpro.2018.06.002},
issn = {0141-9331},
year = {2018},
date = {2018-01-01},
journal = {Microprocessors and Microsystems},
volume = {61},
pages = {117 - 125},
abstract = {The discrete Hartley transform is a real valued transform similar to the complex Fourier transform that finds numerous applications in a variety of fields including pattern recognition and signal and image processing. In this paper, we propose and study two compact and versatile hardware architectures for the computation of the 8-point, 16-point and 32-point Two-Band Fast Discrete Hartley Transform. These highly modular architectures have a symmetric and regular structure consisting of two blocks, a multiplication block and an addition/subtraction block. The first architecture utilizes 8 multipliers and 16 adders/subtractors, achieving a maximum clock frequency of 95 MHz. The second architecture utilizes only 4 multipliers and 8 adders/subtractors, achieving a maximum clock frequency of 100 MHz; however it requires additional multiplexers and more clock cycles (from 1 to 58 clock cycles depends on the points) for the computation. As a result, the proposed hardware architectures constitute an efficient choice for area-restricted applications such as embedded or pervasive computing systems.},
keywords = {Digital signal processing, FPGA architecture, Two-band fast discrete hartley transform, VHDL},
pubstate = {published},
tppubtype = {article}
}
Lévêque, Lucie; Liu, Hantao; Baraković, Sabina; Husić, Jasmina Baraković; Martini, Maria; Outtas, Meriem; Zhang, Lu; Kumcu, Asli; Platisa, Ljiljana; Rodrigues, Rafael; others,
On the subjective assessment of the perceived quality of medical images and videos Proceedings Article
In: 2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX), pp. 1–6, IEEE 2018.
Abstract | Links | BibTeX | Tags: image quality assessment, medical image quality, MOS, subjective experiment, video quality assessment
@inproceedings{Lévêque2018b,
title = {On the subjective assessment of the perceived quality of medical images and videos},
author = {Lucie Lévêque and Hantao Liu and Sabina Baraković and Jasmina Baraković Husić and Maria Martini and Meriem Outtas and Lu Zhang and Asli Kumcu and Ljiljana Platisa and Rafael Rodrigues and others},
url = {https://ieeexplore.ieee.org/document/8463297?part=1},
doi = {10.1109/QoMEX.2018.8463297},
year = {2018},
date = {2018-01-01},
booktitle = {2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX)},
pages = {1--6},
organization = {IEEE},
abstract = {Medical professionals are viewing an increasing number of images and videos in their clinical routine. However, various types of distortions can affect medical imaging data, and therefore impact the viewers' experienced quality and their clinical practice. Thus it is necessary to quantify this impact and understand how the viewers, i.e., medical experts, perceive the quality of (distorted) images and videos. In this paper, we present an up-to-date review of the methodologies used in the literature for the subjective quality assessment of medical images and videos and discuss their merits and drawbacks depending on the use case.},
keywords = {image quality assessment, medical image quality, MOS, subjective experiment, video quality assessment},
pubstate = {published},
tppubtype = {inproceedings}
}
Alexiou, Evangelos; Ebrahimi, Touradj; Bernardo, Marco V; Pereira, Manuela; Pinheiro, Antonio; Cruz, Luis Da Silva A; Duarte, Carlos; Dmitrovic, Lovorka Gotal; Dumic, Emil; Matkovics, Dragan; Skodras, Athanassios
Point cloud subjective evaluation methodology based on 2D rendering Proceedings Article
In: 2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX), pp. 1–6, IEEE 2018.
Abstract | Links | BibTeX | Tags: Point Cloud, Quality Assessment, Quality Metrics
@inproceedings{Alexiou2018b,
title = {Point cloud subjective evaluation methodology based on 2D rendering},
author = {Evangelos Alexiou and Touradj Ebrahimi and Marco V Bernardo and Manuela Pereira and Antonio Pinheiro and Luis Da Silva A Cruz and Carlos Duarte and Lovorka Gotal Dmitrovic and Emil Dumic and Dragan Matkovics and Athanassios Skodras},
url = {https://ieeexplore.ieee.org/document/8463406},
doi = {10.1109/QoMEX.2018.8463406},
year = {2018},
date = {2018-01-01},
booktitle = {2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX)},
pages = {1--6},
organization = {IEEE},
abstract = {Point clouds are one of the most promising technologies for 3D content representation. In this paper, we describe a study on quality assessment of point clouds, degraded by octree-based compression on different levels. The test contents were displayed using Screened Poisson surface reconstruction, without including any textural information, and they were rated by subjects in a passive way, using a 2D image sequence. Subjective evaluations were performed in five independent laboratories in different countries, with the inter-laboratory correlation analysis showing no statistical differences, despite the different equipment employed. Benchmarking results reveal that the state-of-the-art point cloud objective metrics are not able to accurately predict the expected visual quality of such test contents. Moreover, the subjective scores collected from this experiment were found to be poorly correlated with subjective scores obtained from another test involving visualization of raw point clouds. These results suggest the need for further investigations on adequate point cloud representations and objective Quality assessment tools.},
keywords = {Point Cloud, Quality Assessment, Quality Metrics},
pubstate = {published},
tppubtype = {inproceedings}
}
2017
Tsinganos, Panagiotis; Skodras, Athanassios
A smartphone-based fall detection system for the elderly Proceedings Article
In: Kovačič, Stanislav; Lončarić, Sven; Kristan, Matej; Štruc, Vitomir; Vučić, Mladen (Ed.): Proceedings of the 10th International Symposium on Image and Signal Processing and Analysis, pp. 53–58, IEEE, Ljubljana, Slovenia, 2017, ISBN: 978-1-5090-4011-7.
Abstract | Links | BibTeX | Tags: accelerometer, ADLs, fall detection, falls, machine learning, smartphone
@inproceedings{Tsinganos2017a,
title = {A smartphone-based fall detection system for the elderly},
author = {Panagiotis Tsinganos and Athanassios Skodras},
editor = {Stanislav Kovačič and Sven Lončarić and Matej Kristan and Vitomir Štruc and Mladen Vučić},
url = {http://ieeexplore.ieee.org/document/8073568/},
doi = {10.1109/ISPA.2017.8073568},
isbn = {978-1-5090-4011-7},
year = {2017},
date = {2017-09-01},
booktitle = {Proceedings of the 10th International Symposium on Image and Signal Processing and Analysis},
pages = {53--58},
publisher = {IEEE},
address = {Ljubljana, Slovenia},
abstract = {Falls can be severe enough to cause disabilities especially to frail populations. Thus, prompt health care provision is essential to prevent and restore any harm. The purpose of this study is to develop a smartphone-based fall detection system that can distinguish between falls and activities of daily living (ADL). The typical fall detection system consists of a sensing component and a notification module. Android devices, equipped with sensors and communication services, are the best candidates for the development of such systems. This work incorporates a threshold based algorithm, whose accuracy is enhanced by a k Nearest Neighbor (kNN) classifier. In addition, this paper proposes the implementation of a personalization and power regulation system. It achieves high fall detection accuracy, (97.53% sensitivity and 94.89% specificity), which is comparable to related works.},
keywords = {accelerometer, ADLs, fall detection, falls, machine learning, smartphone},
pubstate = {published},
tppubtype = {inproceedings}
}
Tagkalakis, Fotios; Vlachakis, Dimitrios; Megalooikonomou, Vasileios; Skodras, Athanassios
A novel approach to finger vein authentication Proceedings Article
In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), pp. 659-662, 2017, ISSN: 1945-8452.
Abstract | Links | BibTeX | Tags: bio-identity, biometrics, digital signatures, finger vein authentication, person identification
@inproceedings{Tagkalakis2017,
title = {A novel approach to finger vein authentication},
author = {Fotios Tagkalakis and Dimitrios Vlachakis and Vasileios Megalooikonomou and Athanassios Skodras},
doi = {10.1109/ISBI.2017.7950606},
issn = {1945-8452},
year = {2017},
date = {2017-04-01},
booktitle = {2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)},
pages = {659-662},
abstract = {Finger vein patterns are unique biometric features, which differentiate from individual to individual, so they are suitable for authentication applications. Systems based on the use of this feature have numerous advantages such as low cost and high accuracy. A new finger vein authentication approach is proposed, which is based on the efficient detection of the non-vein regions, in order to define the main vein patterns. The proposed method is robust in extracting and depicting not only the finger's vein pattern, but also other important features such as the veins' width. The authentication algorithm has been evaluated on a finger vein database of 400 images. The false acceptance and false rejection rates achieved are 0% and 0.5% respectively.},
keywords = {bio-identity, biometrics, digital signatures, finger vein authentication, person identification},
pubstate = {published},
tppubtype = {inproceedings}
}
2016
Triantafyllopoulos, Andreas; Krilis, Ioannis; Foliadis, Anastasios; Skodras, Athanassios
A Hilbert-Based Approach to the ENF Extraction Problem Proceedings Article
In: IEICE Information and Communication Technology Forum 2016 (ICTF 2016), 2016.
Abstract | BibTeX | Tags: ENF, Hilbert
@inproceedings{Triantafyllopoulos2016,
title = {A Hilbert-Based Approach to the ENF Extraction Problem},
author = {Andreas Triantafyllopoulos and Ioannis Krilis and Anastasios Foliadis and Athanassios Skodras},
year = {2016},
date = {2016-01-01},
booktitle = {IEICE Information and Communication Technology Forum 2016 (ICTF 2016)},
abstract = {The estimation of location based on the time varying Electric Network Frequency (ENF) is a new emerging technology in Information Forensics. This requires the extraction of the ENF signal from multimedia recordings and a comparison with already known power grid signatures. In this paper, we focus on ENF signal extraction and statistical modelling of ENF signals. We introduce a novel technique based on instantaneous frequency estimation using the Hilbert transform, which shows promising results.},
keywords = {ENF, Hilbert},
pubstate = {published},
tppubtype = {inproceedings}
}
Alexiou, Evangelos; Viola, Irene; Krasula, Lukas; Richter, Thomas; Bruylants, Tim; Pinheiro, Antonio; Fliegel, Karel; Rerabek, Martin; Skodras, Athanassios; Schelkens, Peter; others,
Overview and Benchmarking summary for the ICIP 2016 Compression Challenge Proceedings Article
In: 23rd International Conference on Image Processing, 2016.
BibTeX | Tags:
@inproceedings{alexiou2016overview,
title = {Overview and Benchmarking summary for the ICIP 2016 Compression Challenge},
author = {Evangelos Alexiou and Irene Viola and Lukas Krasula and Thomas Richter and Tim Bruylants and Antonio Pinheiro and Karel Fliegel and Martin Rerabek and Athanassios Skodras and Peter Schelkens and others},
year = {2016},
date = {2016-01-01},
booktitle = {23rd International Conference on Image Processing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Pyrgas, Labros; Kitsos, Paris; Skodras, Athanassios
An FPGA design for the two-band fast discrete hartley transform Proceedings Article
In: 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), pp. 295–299, IEEE 2016.
Abstract | Links | BibTeX | Tags: Digital signal processing, Field Programmable Gate Array architecture (FPGA), Two-band fast discrete hartley transform, VHDL
@inproceedings{Pyrgas2016b,
title = {An FPGA design for the two-band fast discrete hartley transform},
author = {Labros Pyrgas and Paris Kitsos and Athanassios Skodras},
url = {https://ieeexplore.ieee.org/document/7886052},
doi = {10.1109/ISSPIT.2016.7886052},
year = {2016},
date = {2016-01-01},
booktitle = {2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)},
pages = {295--299},
organization = {IEEE},
abstract = {The discrete Hartley transform finds numerous applications in signal and image processing. An efficient Field Programmable Gate Array implementation for the 64-point Two-Band Fast Discrete Hartley Transform is proposed in this communication. The architecture requires 57 clock cycles to compute the 64-point Two-Band Fast Discrete Hartley Transform and reaches a rate of up to 103.82 million samples per second at a 92 MHz clock frequency. The architecture has been implemented using VHDL and realized on a Cyclone IV FPGA of Altera.},
keywords = {Digital signal processing, Field Programmable Gate Array architecture (FPGA), Two-band fast discrete hartley transform, VHDL},
pubstate = {published},
tppubtype = {inproceedings}
}
2015
Mysirlidis, Charalampos; Dagiuklas, Tasos; Rocha, Pedro; Cruz, Luis Da Silva; Kotaranin, Dino; Gruicic, Savina; Dumic, Emil; Skodras, Athanassios
STESCAL3D: Subjective evaluation of HD stereo video streaming using H.264 SVC in diverse laboratory environments Proceedings Article
In: 2015 Seventh International Workshop on Quality of Multimedia Experience (QoMEX), pp. 1-6, 2015, ISSN: null.
Abstract | Links | BibTeX | Tags: 3D video, objective measures, QoE, STESCAL3D database, subjective evaluation
@inproceedings{Mysirlidis2015,
title = {STESCAL3D: Subjective evaluation of HD stereo video streaming using H.264 SVC in diverse laboratory environments},
author = {Charalampos Mysirlidis and Tasos Dagiuklas and Pedro Rocha and Luis Da Silva Cruz and Dino Kotaranin and Savina Gruicic and Emil Dumic and Athanassios Skodras},
doi = {10.1109/QoMEX.2015.7148151},
issn = {null},
year = {2015},
date = {2015-05-01},
booktitle = {2015 Seventh International Workshop on Quality of Multimedia Experience (QoMEX)},
pages = {1-6},
abstract = {This paper presents a new 3D video database (STESCAL3D -Stereoscopic Scalable 3D), made up of 3D stereo video sequences affected by different types of degradations. A set of subjective quality grades have been collected in three geographically displaced sites. The database contents have been produced using scalable video coding to encode 3D stereo video clips with distinct encoding parameters, after which different transmission degradations have been applied to the encoded video streams. These sequences have been subjectively evaluated by observers from three countries, Croatia, Portugal and Greece, using a purpose-built web-based platform. The subjective quality data compiled were processed, analyzed and compared to quality estimates obtained using several well-known objective measures. It is shown that the correlation between objective quality estimates and the subjective quality grades is in general low. Additionally the results show that stereo-view asymmetries in terms of encoding parameters and packet loss ratio (PLR) leads to low quality of experience. The video database and the subjective grades collection are publicly available with the referral link provided in the text.},
keywords = {3D video, objective measures, QoE, STESCAL3D database, subjective evaluation},
pubstate = {published},
tppubtype = {inproceedings}
}
Skodras, Athanassios; Aburdene, Maurice; Nandi, Asoke
Two-band fast Hartley transform Journal Article
In: Electronics Letters, vol. 51, no. 1, pp. 57-59, 2015, ISSN: 0013-5194.
Abstract | Links | BibTeX | Tags: computational complexity, DFT, DHTs, discrete Fourier transform, discrete Fourier transforms, discrete Hartley transforms, fast Fourier transform, fast Fourier transforms, FFT algorithms, FHT, forward discrete Hartley transforms, input data, input data shuffling, inverse discrete Hartley transforms, inverse transforms, out data shuffling, radix-2 fast Hartley transform, two-band decomposition, two-band fast Hartley transform
@article{Skodras2015,
title = {Two-band fast Hartley transform},
author = {Athanassios Skodras and Maurice Aburdene and Asoke Nandi},
doi = {10.1049/el.2014.3170},
issn = {0013-5194},
year = {2015},
date = {2015-01-01},
journal = {Electronics Letters},
volume = {51},
number = {1},
pages = {57-59},
abstract = {Efficient algorithms have been developed over the past 30 years for computing the forward and inverse discrete Hartley transforms (DHTs). These are similar to the fast Fourier transform (FFT) algorithms for computing the discrete Fourier transform (DFT). Most of these methods seek to minimise the complexity of computations and/or the number of operations. A new approach for the computation of the radix-2 fast Hartley transform (FHT) is presented. The proposed algorithm, based on a two-band decomposition of the input data, possesses a very regular structure, avoids the input or out data shuffling, requires slightly less multiplications than the existing approaches, but increases the number of additions.},
keywords = {computational complexity, DFT, DHTs, discrete Fourier transform, discrete Fourier transforms, discrete Hartley transforms, fast Fourier transform, fast Fourier transforms, FFT algorithms, FHT, forward discrete Hartley transforms, input data, input data shuffling, inverse discrete Hartley transforms, inverse transforms, out data shuffling, radix-2 fast Hartley transform, two-band decomposition, two-band fast Hartley transform},
pubstate = {published},
tppubtype = {article}
}
Fotopoulos, Vasileios; Fanariotis, Anastasios; Orphanoudakis, Theofanis; Skodras, Athanassios
Remote FPGA Laboratory Course Development Based on an Open Multimodal Laboratory Facility Proceedings Article
In: Proceedings of the 19th Panhellenic Conference on Informatics, pp. 447–452, ACM, Athens, Greece, 2015, ISBN: 978-1-4503-3551-5.
Abstract | Links | BibTeX | Tags: distance learning, FPGA, online course, remote lab, VHDL
@inproceedings{Fotopoulos2015,
title = {Remote FPGA Laboratory Course Development Based on an Open Multimodal Laboratory Facility},
author = {Vasileios Fotopoulos and Anastasios Fanariotis and Theofanis Orphanoudakis and Athanassios Skodras},
url = {http://doi.acm.org/10.1145/2801948.2801950},
doi = {10.1145/2801948.2801950},
isbn = {978-1-4503-3551-5},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the 19th Panhellenic Conference on Informatics},
pages = {447--452},
publisher = {ACM},
address = {Athens, Greece},
series = {PCI '15},
abstract = {In this paper the implementation of a remote FPGA laboratory course is proposed, based on a low cost but powerful FPGA development board, the ALTERA DE0-Nano which is powered by an Altera Cyclone IV Field Programmable Gate Array (FPGA) IC. The course is developed based on an open multimodal laboratory facility at the Digital Systems and Media Computing Laboratory of the Hellenic Open University. The course consists of laboratory exercises in the form of VHDL (VHSIC Hardware Description Language) design experiments that the end user can conduct from his or her Personal Computer through a graphical web interface and Altera's Quartus II EDA (Electronic Design Automation) software on hardware that is connected and set-up on a remote server while observing the results in real time. The exercises created for this course are designed to be both educational and interesting while being geared towards entry-level users thus producing a trouble-free RL (Remote Laboratory) that in turn maximizes educational gain.},
keywords = {distance learning, FPGA, online course, remote lab, VHDL},
pubstate = {published},
tppubtype = {inproceedings}
}
2014
Chrysochos, Eleftherios; Fotopoulos, Vasileios; Xenos, Michalis; Skodras, Athanassios
Hybrid watermarking based on chaos and histogram modification Journal Article
In: Signal, Image and Video Processing, vol. 8, no. 5, pp. 843–857, 2014.
Abstract | Links | BibTeX | Tags: Authentication, Chaos, Chaotic maps, DCTRobust watermarking, Dual watermarking, Geometrical attacks, Histogram modification
@article{Chrysochos2014b,
title = {Hybrid watermarking based on chaos and histogram modification},
author = {Eleftherios Chrysochos and Vasileios Fotopoulos and Michalis Xenos and Athanassios Skodras},
url = {https://link.springer.com/article/10.1007/s11760-012-0307-3},
doi = {10.1007/s11760-012-0307-3},
year = {2014},
date = {2014-01-01},
journal = {Signal, Image and Video Processing},
volume = {8},
number = {5},
pages = {843--857},
publisher = {Springer},
abstract = {A hybrid watermarking scheme for authentication is presented, which demonstrates robustness against various attacks. Due to the different nature of filtering and geometrical attacks, two different watermarks are used in this scheme. The first one is embedded in frequency domain combined with a chaotic function and is based on the correlation method. The second watermark is embedded in luminosity histogram of the image. In this way, this hybrid watermarking scheme combines the robustness of chaotic domain against filtering, noise and compression attacks with the robustness of histogram domain against geometrical attacks.},
keywords = {Authentication, Chaos, Chaotic maps, DCTRobust watermarking, Dual watermarking, Geometrical attacks, Histogram modification},
pubstate = {published},
tppubtype = {article}
}
Varsaki, Eleni; Fotopoulos, Vasileios; Skodras, Athanassios
A discrete Gould transform data hiding scheme Journal Article
In: Mathematical Methods in the Applied Sciences, vol. 37, no. 2, pp. 283-288, 2014.
Abstract | Links | BibTeX | Tags: data hiding, fragile watermarking, Gould transform
@article{Varsaki2014,
title = {A discrete Gould transform data hiding scheme},
author = {Eleni Varsaki and Vasileios Fotopoulos and Athanassios Skodras},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/mma.3041},
doi = {10.1002/mma.3041},
year = {2014},
date = {2014-01-01},
journal = {Mathematical Methods in the Applied Sciences},
volume = {37},
number = {2},
pages = {283-288},
abstract = {Discrete Gould transform has been recently introduced in image processing. This paper proposes a data hiding scheme that uses the discrete Gould transform in order to invisibly embed a secret message. The Gould coefficients represent the differences between neighboring pixels. Small changes of the coefficients generate even smaller changes to the pixels. By this, a high capacity fragile steganographic technique is achieved. The message is easily destroyed after any manipulation, and therefore, its absence can prove that the image has been altered in some way. Because of this property, the proposed technique finds application in image authentication and tamper proofing.},
keywords = {data hiding, fragile watermarking, Gould transform},
pubstate = {published},
tppubtype = {article}
}
Korshunov, Pavel; Nemoto, Hiromi; Skodras, Athanassios; Ebrahimi, Touradj
Crowdsourcing-based evaluation of privacy in HDR images Proceedings Article
In: Schelkens, Peter; Ebrahimi, Touradj; Cristóbal, Gabriel; Truchetet, Frédéric; Saarikko, Pasi (Ed.): Optics, Photonics, and Digital Technologies for Multimedia Applications III, pp. 1 – 11, International Society for Optics and Photonics SPIE, 2014.
Abstract | Links | BibTeX | Tags: crowdsourcing, evaluation, HDR imaging, privacy protection
@inproceedings{Korshunov2014,
title = {Crowdsourcing-based evaluation of privacy in HDR images},
author = {Pavel Korshunov and Hiromi Nemoto and Athanassios Skodras and Touradj Ebrahimi},
editor = {Peter Schelkens and Touradj Ebrahimi and Gabriel Cristóbal and Frédéric Truchetet and Pasi Saarikko},
url = {https://doi.org/10.1117/12.2054541},
doi = {10.1117/12.2054541},
year = {2014},
date = {2014-01-01},
booktitle = {Optics, Photonics, and Digital Technologies for Multimedia Applications III},
volume = {9138},
pages = {1 -- 11},
publisher = {SPIE},
organization = {International Society for Optics and Photonics},
abstract = {The ability of High Dynamic Range imaging (HDRi) to capture details in high-contrast environments, making both dark and bright regions clearly visible, has a strong implication on privacy. However, the extent to which HDRi affects privacy when it is used instead of typical Standard Dynamic Range imaging (SDRi) is not yet clear. In this paper, we investigate the effect of HDRi on privacy via crowdsourcing evaluation using the Microworkers platform. Due to the lack of HDRi standard privacy evaluation dataset, we have created such dataset containing people of varying gender, race, and age, shot indoor and outdoor and under large range of lighting conditions. We evaluate the tone-mapped versions of these images, obtained by several representative tone-mapping algorithms, using subjective privacy evaluation methodology. Evaluation was performed using crowdsourcing-based framework, because it is a popular and effective alternative to traditional lab-based assessment. The results of the experiments demonstrate a significant loss of privacy when even tone-mapped versions of HDR images are used compared to typical SDR images shot with a standard exposure.},
keywords = {crowdsourcing, evaluation, HDR imaging, privacy protection},
pubstate = {published},
tppubtype = {inproceedings}
}
2013
Kitsos, Paris; Voros, Nikolaos; Dagiuklas, Tasos; Skodras, Athanassios
A high speed FPGA implementation of the 2D DCT for Ultra High Definition video coding Proceedings Article
In: 2013 18th International Conference on Digital Signal Processing (DSP), pp. 1-5, 2013, ISSN: 1546-1874.
Abstract | Links | BibTeX | Tags: 2D DCT, distributed arithmetic, FPGA implementation, VHDL, video coding
@inproceedings{Kitsos2013b,
title = {A high speed FPGA implementation of the 2D DCT for Ultra High Definition video coding},
author = {Paris Kitsos and Nikolaos Voros and Tasos Dagiuklas and Athanassios Skodras},
doi = {10.1109/ICDSP.2013.6622742},
issn = {1546-1874},
year = {2013},
date = {2013-07-01},
booktitle = {2013 18th International Conference on Digital Signal Processing (DSP)},
pages = {1-5},
abstract = {This paper presents two high performance FPGA architectures for the 2D DCT computation for Ultra High Definition video coding systems. Both architectures use Distributed Arithmetic to perform the necessary multiplications instead of traditional multipliers. The first architecture uses 105 clock cycles to transform an 8×8 block and reaches a rate of up to 206 samples per second at a 338.5 MHz frequency, while the second one requires 65 cycles for each 8×8 block and achieves a rate equal to 252 samples per second at 256 MHz. Both architectures have been implemented using VHDL. Virtex7 FPGA of Xilinx has been used for the realization of both implementations.},
keywords = {2D DCT, distributed arithmetic, FPGA implementation, VHDL, video coding},
pubstate = {published},
tppubtype = {inproceedings}
}
Mylona, Eleftheria; Savelonas, Michalis; Maroulis, Dimitris; Skodras, Athanassios
Autopilot spatially-adaptive active contour parameterization for medical image segmentation Proceedings Article
In: Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems, pp. 268-272, 2013, ISSN: 1063-7125.
Abstract | Links | BibTeX | Tags: active contour regularization, Active contours, artifacts, autopilot spatially-adaptive active contour parameterization, biodiffusion, Biomedical imaging, biomedical optical imaging, contour convergence speeding, Convergence, data fidelity parameters, diffusion tensors, edge region diffusivity, eigenvalues, eigenvalues and eigenfunctions, Ellipsoids, endoscope, endoscopes, entropy, entropy-based spatially-adaptive heatmaps, false local minima association, framework bypasses iterations, high-segmentation quality, image denoising, Image edge detection, image segmentation, inhomogeneities, isomorphism, iterative methods, mammographic images, mammography, medical image processing, medical image segmentation, noise, randomly directed edge regions
@inproceedings{Mylona2013,
title = {Autopilot spatially-adaptive active contour parameterization for medical image segmentation},
author = {Eleftheria Mylona and Michalis Savelonas and Dimitris Maroulis and Athanassios Skodras},
doi = {10.1109/CBMS.2013.6627800},
issn = {1063-7125},
year = {2013},
date = {2013-06-01},
booktitle = {Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems},
pages = {268-272},
abstract = {In this work, a novel framework for automated, spatially-adaptive adjustment of active contour regularization and data fidelity parameters is proposed and applied for medical image segmentation. The proposed framework is tailored upon the isomorphism observed between these parameters and the eigenvalues of diffusion tensors. Since such eigenvalues reflect the diffusivity of edge regions, we embed this information in regularization and data fidelity parameters by means of entropy-based, spatially-adaptive `heatmaps'. The latter are able to repel an active contour from randomly directed edge regions and guide it towards structured ones. Experiments are conducted on endoscopic as well as mammographic images. The segmentation results demonstrate that the proposed framework bypasses iterations dedicated to false local minima associated with noise, artifacts and inhomogeneities, speeding up contour convergence, whereas it maintains a high segmentation quality.},
keywords = {active contour regularization, Active contours, artifacts, autopilot spatially-adaptive active contour parameterization, biodiffusion, Biomedical imaging, biomedical optical imaging, contour convergence speeding, Convergence, data fidelity parameters, diffusion tensors, edge region diffusivity, eigenvalues, eigenvalues and eigenfunctions, Ellipsoids, endoscope, endoscopes, entropy, entropy-based spatially-adaptive heatmaps, false local minima association, framework bypasses iterations, high-segmentation quality, image denoising, Image edge detection, image segmentation, inhomogeneities, isomorphism, iterative methods, mammographic images, mammography, medical image processing, medical image segmentation, noise, randomly directed edge regions},
pubstate = {published},
tppubtype = {inproceedings}
}
Kitsos, Paris; Sklavos, Nicolas; Provelengios, George; Skodras, Athanassios
FPGA-based performance analysis of stream ciphers ZUC, Snow3g, Grain V1, Mickey V2, Trivium and E0 Journal Article
In: Microprocessors and Microsystems, vol. 37, no. 2, pp. 235 - 245, 2013, ISSN: 0141-9331, (Digital System Safety and Security).
Abstract | Links | BibTeX | Tags: Bluetooth, Cryptography, eStream portfolio, FPGA implementation, GSM, LTE, Stream ciphers, UMTS
@article{Kitsos2013bb,
title = {FPGA-based performance analysis of stream ciphers ZUC, Snow3g, Grain V1, Mickey V2, Trivium and E0},
author = {Paris Kitsos and Nicolas Sklavos and George Provelengios and Athanassios Skodras},
url = {http://www.sciencedirect.com/science/article/pii/S014193311200169X},
doi = {https://doi.org/10.1016/j.micpro.2012.09.007},
issn = {0141-9331},
year = {2013},
date = {2013-01-01},
journal = {Microprocessors and Microsystems},
volume = {37},
number = {2},
pages = {235 - 245},
abstract = {In this paper, the hardware implementations of six representative stream ciphers are compared in terms of performance, consumed area and the throughput-to-area ratio. The stream ciphers used for the comparison are ZUC, Snow3g, Grain V1, Mickey V2, Trivium and E0. ZUC, Snow3g and E0 have been used for the security part of well known standards, especially wireless communication protocols. In addition, Grain V1, Mickey V2 and Trivium are currently selected as the final portfolio of stream ciphers for Profile 2 (Hardware) by the eStream project. The designs were implemented by using VHDL language and for the hardware implementations a FPGA device was used. The highest throughput has been achieved by Snow3g with 3330Mbps at 104MHz and the lowest throughput has been achieved by E0 with 187Mbps at 187MHz. Also, the most efficient cipher for hardware implementation in terms of throughput-to-area ratio is Mickey V2 cipher while the worst cipher for hardware implementation is Grain V1.},
note = {Digital System Safety and Security},
keywords = {Bluetooth, Cryptography, eStream portfolio, FPGA implementation, GSM, LTE, Stream ciphers, UMTS},
pubstate = {published},
tppubtype = {article}
}
Skodras, Athanassios
Discrete Gould transform - Fast realisations and data hiding Proceedings Article
In: 2013 Constantinides International Workshop on Signal Processing (CIWSP 2013), pp. 1-4, 2013.
Abstract | Links | BibTeX | Tags: computational complexity, data encapsulation, data hiding method, DGT, digital imaging, discrete Gould transform, discrete transforms, edge detection
@inproceedings{Skodras2013,
title = {Discrete Gould transform - Fast realisations and data hiding},
author = {Athanassios Skodras},
doi = {10.1049/ic.2013.0003},
year = {2013},
date = {2013-01-01},
booktitle = {2013 Constantinides International Workshop on Signal Processing (CIWSP 2013)},
pages = {1-4},
abstract = {The computational complexity of the discrete Gould transform (DGT) is studied and a fast realisation approach is proposed. The reversible difference expansion data hiding method is applied to the DGT coefficients and experimental results are given.},
keywords = {computational complexity, data encapsulation, data hiding method, DGT, digital imaging, discrete Gould transform, discrete transforms, edge detection},
pubstate = {published},
tppubtype = {inproceedings}
}