Prof. Dr.-Ing. Erhardt Barth
Stellvertretender Direktor
Institut für Neuro- und Bioinformatik
Ratzeburger Allee 160 (Geb. 64)
23562 Lübeck
| Email: | erhardt.barth(at)uni-luebeck.de |
| Phone: | +49 451 3101 5503 |
Current research interests
Main research interests are in Computer Vision and Machine Learning. A further interest is in biological vision, which is used as a source of inspiration for solving computer vision problems and for building enhanced vision systems that can compensate the strengths and weaknesses of both human and computer vision.
Brief biography
Prof. Barth leads the research on human and machine vision at the INB. He obtained his Ph.D in Electrical Engineering from the Technical University of Munich in 1994, was a Research Associate at the Department of Communications Engineering in Munich and a Visiting Fellow at the Department of Computer Science, Melbourne University, Australia, where he was supported by the Gottlieb-Daimler and Karl-Benz Foundation. He then was a researcher at the Department of Medical Psychology, University of Munich, and a Klaus-Piltz fellow at the Institute for Advanced Study in Berlin. In 1997/98 he was a member of the NASA Vision Science and Technology Group at NASA Ames, Moffet Field, California. In May 2000 he received a Schloessmann Award from the Max-Planck Gesellschaft. Since then, he initiated and conducted a number of basic and applied research projects, and started a few companies (e.g. ARTTS, GazeCom, PRC, gestigon).
Google Scholar - aktuelle Publikationen
Publications
2016
Recurrent Dropout without Memory Loss, in COLING , ACL, 2016. pp. 1757--1766.
Autoconvolution for Unsupervised Feature Learning, arXiv: 1606.00611v1 [cs.CV] , 2016.
| Datei: | |
| Bibtex: | @article{KnBaMa16,
author = {Boris Knyazew and Erhardt Barth and Thomas Martinetz},
title = {Autoconvolution for {U}nsupervised {F}eature {L}earning},
journal = {arXiv:1606.00611v1 [cs.CV]},
year = {2016},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/KnBaMa16.pdf}
}
|
2015
EUROPattern Suite technology for computer-aided immunofluorescence microscopy in autoantibody diagnostics, Lupus , vol. 24, no. 4--5, pp. 516--529, 2015.
Foveated Manifold Sensing for object recognition, in IEEE International Black Sea Conference on Communications and Networking , 2015. pp. 196--200.
| Datei: | BlackSeaCom.2015.7185114 |
| Bibtex: | @inproceedings{BuMaBa15,
author = {Irina Burciu and Thomas Martinetz and Erhardt Barth},
title = {Foveated {M}anifold {S}ensing for object recognition},
booktitle = {IEEE International Black Sea Conference on Communications and Networking},
pages = {196--200},
year = {2015},
url = {http://dx.doi.org/10.1109/BlackSeaCom.2015.7185114}
}
|
Self-organizing maps for hand and full body tracking, Neurocomputing , vol. 147, pp. 174--184, 2015. Elsevier.
| DOI: | http://dx.doi.org/10.1016/j.neucom.2013.10.041 |
| Datei: | |
| Bibtex: | @article{CoStKlBaMa15,
author = {Foti Coleca and Andreea State and Sascha Klement and Erhardt Barth and Thomas Martinetz},
title = {Self-organizing maps for hand and full body tracking},
journal = {Neurocomputing},
year = {2015},
note = {Advances in Self-Organizing Maps Subtitle of the special issue: Selected Papers from the Workshop on Self-Organizing Maps 2012 (WSOM 2012)},
volume = {147},
pages = {174--184},
publisher = {Elsevier},
doi = {http://dx.doi.org/10.1016/j.neucom.2013.10.041},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/CoStKlBaMa15.pdf}
}
|
Learning Orthogonal Sparse Representations by Using Geodesic Flow Optimization, in IJCNN 2015 Conference Proceedings , 2015. pp. 15540:1--8.
| Datei: | |
| Bibtex: | @inproceedings{ScBaMa15,
author={Sch{\"u}tze, Henry and Barth, Erhardt and Martinetz, Thomas},
title={{L}earning {O}rthogonal {S}parse {R}epresentations by {U}sing {G}eodesic {F}low {O}ptimization},
booktitle = {IJCNN 2015 Conference Proceedings},
series = {The International Joint Conference on Neural Networks},
year = {2015},
pages = {15540:1--8},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/ScBaMa15.pdf}
}
|
Deep Convolutional Neural Networks as Generic Feature Extractors, in Proc. 2015 IEEE International Joint Conference on Neural Networks (IJCNN) , Killarney, Ireland , 2015.
| Datei: | |
| Bibtex: | @inproceedings{HeBaKaMa15,
author = {Lars Hertel and Erhardt Barth and Thomas K{\"a}ster and Thomas Martinetz},
title = {Deep {C}onvolutional {N}eural {N}etworks as {G}eneric {F}eature {E}xtractors},
booktitle = {Proc. 2015 {IEEE} International Joint Conference on Neural Networks (IJCNN)},
address = {Killarney, Ireland},
owner = {Hertel},
year = {2015},
timestamp = {2015.05.13},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/HeBaKaMa15.pdf}
}
|
2014
Visual Manifold Sensing, in Human Vision and Electronic Imaging XIX , Proceedings of SPIE Electronic Imaging, 2014. pp. 48:1--8.
| Datei: | |
| Bibtex: | @inproceedings{BuMaMaBa14,
author = {Irina Burciu and Adrian Ion-Margineanu and Thomas Martinetz and Erhardt Barth},
title = {Visual {M}anifold {S}ensing}, booktitle = {Human Vision and Electronic Imaging XIX},
publisher = {Proceedings of SPIE Electronic Imaging},
volume = {9014},
pages = {48:1--8},
year = {2014},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/BuMaMaBa14.pdf}
}
|
Committees of deep feedforward networks trained with few data, arXiv:1406.5947v1[cs.CV] , 2014.
| Datei: | |
| Bibtex: | @article{MiKaMaBa14,
author = {Bogdan Miclut and Thomas K{\"a}ster and Thomas Martinetz and Erhard Barth },
title = {Committees of deep feedforward networks trained with few data},
journal = {arXiv:1406.5947v1[cs.CV]},
year = {2014},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/MiKaMaBa14.pdf}
}
|
Key-point Detection with Multi-layer Center-surround Inhibition, in Proceedings of the 9th International Conference on Computer Vision Theory and Applications , 2014. pp. 386--393.
| Datei: | |
| Bibtex: | @inproceedings{CoZiKaMaBa14,
author = {Foti Coleca and Sabrina Z{\^i}rnovean and Thomas K{\"a}ster and Thomas Martinetz and Erhardt Barth},
title = {Key-point Detection with Multi-layer Center-surround Inhibition},
booktitle = {Proceedings of the 9th International Conference on Computer Vision Theory and Applications},
pages = {386--393},
abstract = {We present a biologically inspired algorithm for key-point detection based on multi-layer and nonlinear centersurround inhibition. A Bag-of-Visual-Words framework is used to evaluate the performance of the detector on the Oxford III-T Pet Dataset for pet recognition. The results demonstrate an increased performance of our algorithm compared to the SIFT key-point detector. We further improve the recognition rate by separately training codebooks for the ON- and OFF-type key points. The results show that our key-point detection algorithms outperform the SIFT detector by having a lower recognition-error rate over a whole range of different key-point densities. Randomly selected key-points are also outperformed.},
year = {2014},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/CoZiKaMaBa14.pdf}
}
|
An adaptive hierarchical sensing scheme for sparse signals, in Human Vision and Electronic Imaging XIX , Bernice E. Rogowitz and Thrasyvoulos N. Pappas and Huib de Ridder, Eds. 2014. pp. 15:1--8.
| Datei: | |
| Bibtex: | @inproceedings{ScBaMa14,
author={Sch{\"u}tze, Henry and Barth, Erhardt and Martinetz, Thomas},
title={An adaptive hierarchical sensing scheme for sparse signals},
booktitle = {Human Vision and Electronic Imaging XIX},
series = {Proc. of SPIE Electronic Imaging},
editor = {Bernice E. Rogowitz and Thrasyvoulos N. Pappas and Huib de Ridder},
volume = {9014},
pages = {15:1--8},
year = {2014},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/ScBaMa14.pdf}
}
|
2013
Sparse Coding Neural Gas Applied to Image Recognition, in Advances in Self-Organizing Maps , Springer Berlin Heidelberg, 2013. pp. 105--114.
Real-time skeleton tracking for embedded systems, in Mobile Computational Photography , Proceedings of SPIE, 2013.
| Datei: | |
| Bibtex: | @inproceedings{CoKlMaBa13,
author = {Foti Coleca and Sascha Klement and Thomas Martinetz and Erhardt Barth},
title = {Real-time skeleton tracking for embedded systems},
booktitle = {Mobile Computational Photography},
publisher = {Proceedings of SPIE},
year = {2013},
volume = {8667D},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/CoKlMaBa13.pdf}
}
|
Gesture Interfaces with Depth Sensors, in Time-of-Flight and Depth Imaging. Sensors, Algorithms, and Applications , Springer Berlin Heidelberg, 2013. pp. 207--227.
| Datei: | |
| Bibtex: | @inproceedings{CoMaBa13,
author = {Foti Coleca and Thomas Martinetz and Erhardt Barth},
title = {{G}esture {I}nterfaces with {D}epth {S}ensors},
publisher = {Springer Berlin Heidelberg},
booktitle = {Time-of-Flight and Depth Imaging. Sensors, Algorithms, and Applications},
series = {Lecture Notes in Computer Science},
volume = {8200},
pages = {207--227},
year = {2013},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/CoMaBa13.pdf}
}
|
Simple gaze-contingent cues guide eye movements in a realistic driving simulator, in IS&T/SPIE Electronic Imaging , 2013. pp. 865110-865110-8.
| Datei: | |
| Bibtex: | @inproceedings{PoDoBeBa13,
author = {Laura Pomarjanschi and Michael Dorr and Peter J. Bex and Erhardt Barth},
title = {Simple gaze-contingent cues guide eye movements in a realistic driving simulator},
booktitle = {IS&T/SPIE Electronic Imaging},
volume = {8651},
pages = {865110-865110-8},
year = {2013},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/PoDoBeBa13.pdf}
}
|
Learning Orthogonal Bases for k-Sparse Representations, in Workshop New Challenges in Neural Computation 2013 , Barbara Hammer and Thomas Martinetz and Thomas Villmann, Eds. 2013. pp. 119--120.
| Datei: | |
| Bibtex: | @inproceedings{ScBaMa13,
author={Sch{\"u}tze, Henry and Barth, Erhardt and Martinetz, Thomas},
title = {{L}earning {O}rthogonal {B}ases for k-{S}parse {R}epresentations},
booktitle = {Workshop New Challenges in Neural Computation 2013},
editor = {Barbara Hammer and Thomas Martinetz and Thomas Villmann},
series ={Machine Learning Reports},
volume = {02},
year = {2013},
pages = {119--120},
note = {Short Paper},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/ScBaMa13.pdf}
}
|
Efficient image representations and features, in Human Vision and Electronic Imaging XVIII , Bernice E. Rogowitz and Thrasyvoulos N. Pappas Huib de Ridder, Eds. 2013. pp. 86510R.
| Datei: | |
| Bibtex: | @inproceedings{DoViBa13,
author = {Michael Dorr and Eleonora Vig and Erhardt Barth},
title = {Efficient image representations and features},
editor = {Bernice E. Rogowitz and Thrasyvoulos N. Pappas Huib de Ridder},
booktitle = {Human Vision and Electronic Imaging XVIII},
series = {Proc. of SPIE-IS&T Electronic Imaging},
volume = {8651},
pages = {86510R},
year = {2013},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/DoViBa13.pdf}
}
|
Hand Tracking with an Extended Self-Organizing Map, in Advances in Self-Organizing Maps , Estévez, Pablo A. and Príncipe, José C. and Zegers, Pablo, Eds. Springer Berlin Heidelberg, 2013, pp. 115--124.
| DOI: | 10.1007/978-3-642-35230-0_12 |
| ISBN: | 978-3-642-35229-4 |
| Datei: | |
| Bibtex: | @incollection{StCoBaMa13,
author = {Andreea State and Foti Coleca and Erhardt Barth and Thomas Martinetz},
title = {Hand {T}racking with an {E}xtended {S}elf-{O}rganizing {M}ap},
booktitle = {Advances in Self-Organizing Maps},
publisher = {Springer Berlin Heidelberg},
editor = {Est{\'e}vez, Pablo A. and Príncipe, Jos{\'e} C. and Zegers, Pablo},
volume = {198},
series = {Advances in Intelligent Systems and Computing},
pages = {115--124},
doi = {10.1007/978-3-642-35230-0_12},
isbn = {978-3-642-35229-4},
keywords = {hand skeleton tracking; self-organizing maps; kinect},
year = {2013},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/StCoBaMa13.pdf}
}
|
Computer-aided immunofluorescence microscopy (CAIFM) for ANCA diagnostics, La Presse Medicale , vol. 42, no. 4, pp. 685, 2013. Elsevier Masson.
ANA and ANCA diagnostics with computer-aided immunofluorescence microscopy (CAIFM), Zeitschrift für Rheumatologie , vol. 72, pp. 24, 2013. Springer Heidelberg.
Optimizing depth-of-field based on a range map and a wavelet transform, in Mobile Computational Photography , Proceedings of SPIE, 2013.
| Datei: | |
| Bibtex: | @inproceedings{WeKaMaBa13,
author = {Mike Wellner and Thomas K{\"a}ster and Thomas Martinetz and Erhardt Barth},
title = {Optimizing depth-of-field based on a range map and a wavelet transform},
booktitle = {Mobile Computational Photography},
publisher = {Proceedings of SPIE},
year = {2013},
volume = {8667D},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/WeKaMaBa13.pdf}
}
|
2012
Impact of dynamic bottom-up features and top-down control on the visual exploration of moving real-world scenes in hemispatial neglect, Neuropsychologia , vol. 50, pp. 2415--2425, 2012.
| Datei: | |
| Bibtex: | @article{MaDoSpGaHeBaHe12,
author = {Bj\"orn Machner and Michael Dorr and Andreas Sprenger and Janina von der Gablentz and Wolfgang Heide and Erhardt Barth and Christoph Helmchen},
title = {Impact of dynamic bottom-up features and top-down control on the visual exploration of moving real-world scenes in hemispatial neglect},
journal = {Neuropsychologia},
volume = {50},
year = {2012},
pages = {2415--2425},
abstract = {<p>Patients with hemispatial neglect are severely impaired in orienting their attention to contralesional hemispace. Although motion is one of the strongest attentional cues in humans, it is still unknown how neglect patients visually explore their moving real-world environment.</p> <p>We therefore recorded eye movements at bedside in 19 patients with hemispatial neglect following acute right hemisphere stroke, 14 right-brain damaged patients without neglect and 21 healthy control subjects. Videos of naturalistic real-world scenes were presented first in a free viewing condition together with static images, and subsequently in a visual search condition. We analyzed number and amplitude of saccades, fixation durations and horizontal fixation distributions. Novel computational tools allowed us to assess the impact of different scene features (static and dynamic contrast, colour, brightness) on patients{\textquoteright} gaze.</p> <p>Independent of the different stimulus conditions, neglect patients showed decreased numbers of fixations in contralesional hemispace (ipsilesional fixation bias) and increased fixation durations in ipsilesional hemispace (disengagement deficit). However, in videos left-hemifield fixations of neglect patients landed on regions with particularly high dynamic contrast. Furthermore, dynamic scenes with few salient objects led to a significant reduction of the pathological ipsilesional fixation bias. In visual search, moving targets in the neglected hemifield were more frequently detected than stationary ones. The top-down influence (search instruction) could neither reduce the ipsilesional fixation bias nor the impact of bottom-up features.</p> <p>Our results provide evidence for a strong impact of dynamic bottom-up features on neglect patients{\textquoteright} scanning behaviour. They support the neglect model of an attentional priority map in the brain being imbalanced towards ipsilesional hemispace, which can be counterbalanced by strong contralateral motion cues. Taking into account the lack of top-down control in neglect patients, bottom-up stimulation with moving real-world stimuli may be a promising candidate for future neglect rehabilitation schemes.</p>},
url = {http://dx.doi.org/10.1016/j.neuropsychologia.2012.06.012},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/MaDoSpGaHeBaHe12.pdf}
}
|
How to make a small phone camera shoot like a big DSLR: creating and fusing multi-modal exposure series, in Human Vision and Electronic Imaging XVII , 2012.
| DOI: | 10.1117/12.905560 |
| Datei: | |
| Bibtex: | @inproceedings{BiKrWiWiWeKaMaBa12,
author = {T. Binder and F. Kriener and C. Wichner and M. Wille and M. Wellner and T. K{\"a}ster and T. Martinetz and E. Barth},
title = {How to make a small phone camera shoot like a big {DSLR}: creating and fusing multi-modal exposure series},
booktitle = {Human Vision and Electronic Imaging XVII},
series = {Proceedings SPIE},
volume = {8291},
year = {2012},
doi = {10.1117/12.905560},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/BiKrWiWiWeKaMaBa12.pdf}
}
|
Gaze guidance reduces the number of collisions with pedestrians in a driving simulator, ACM Transactions on Interactive Intelligent Systems , vol. 1, no. 2, pp. 8:1--8:14, 2012.
| Datei: | |
| Bibtex: | @article{PoDoBa11,
author = {Laura Pomarjanschi and Michael Dorr and Erhardt Barth},
title = {Gaze guidance reduces the number of collisions with pedestrians in a driving simulator},
journal = {ACM Transactions on Interactive Intelligent Systems},
pages = {8:1--8:14},
volume = {1},
number = {2},
year = {2012},
note = {((c) ACM, 2012. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM Transactions on Interactive Intelligent Systems, January 2012.)},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/PoDoBa12.pdf}
}
|
Safer Driving with Gaze Guidance, in BIONETICS 2010 , J. Suzuki and T. Nakano, Eds. Springer, 2012. pp. 581--586.
| Datei: | |
| Bibtex: | @inproceedings{PoDoRaBa10,
author = {Laura Pomarjanschi and Michael Dorr and Christoph Rasche and Erhardt Barth},
title = {Safer {D}riving with {G}aze {G}uidance},
booktitle = {BIONETICS 2010},
series = {LNICST},
volume = {87},
pages = {581--586},
editor = {J. Suzuki and T. Nakano},
publisher = {Springer},
year = {2012},
url = {https://www.inb.uni-luebeck.de/fileadmin/files/publications/inb-publications/pdfs/PoDoRaBa10.pdf}
}
|

