Otto-von-Guericke-Universität Magdeburg

 
 
 
 
 
 
 
 

Publication list

krell

[1] G. Krell and B Michaelis. On-line-Bildverarbeitung mit Neuronalen Netzen. In Materialien des TAT '92, pages 142 - 143, Aachen, September 1992.
[2] B. Michaelis and B. Krell. Neural networks for image improvement in optoelectronic measurement devices. In Proc. of the IMTC Conference, volume 1992, New York, May 1992. IMTC.
[3] B Michaelis and G. Krell. On-line-Bildfilterung mit künstlichen neuronalen Netzen. In ITG Fachbericht 122, page 259 ff. VDE- Verlag, 1992.
[4] B Michaelis and G. Krell. Künstliches neuronales Netz zur Echtzeitkorrektur bei der Bildaufnahme in Meßeinrichtungen. In MessComp, Wiesbaden, September 1993.
[5] B Michaelis and G. Krell. Artifical Neural Networks for Image Improvement, pages 838 - 845. Springer, 1993.
[6] A. Herzog, G Krell, and B. Michaelis. Bildvorverarbeitung mit künstlichen neuronalen Netzen. In Materialien des Workshops "`Bildverarbeitung"', pages 11-12. Otto-von-Guericke-Universität Magdeburg, 12 1994.
[7] G. Krell, B. Michaelis, and A. Herzog. Künstliches neuronales Netz zur Echtzeitkorrektur von optischen Systemen. In Materialien des Kolloquiums Neuroinformatik, pages 25-28. TU Dresden, July 1994.
[8] G. Krell. Bildkorrektur unter Einsatz künstlicher neuronaler Netze, Anwendungsorientierter Beitrag zur Vorverarbeitung visueller Daten. Otto-von-Guericke-Universität Magdeburg, 1997.
[9] G. Krell, B. Michaelis, and A. Herzog. Bildsensoren mit künstlichen neuronalen Netzen als Korrekturnetzwerk. In Materialien der Fachtagung "`Sensoren -Aktoren - Buskommunikation"', pages 173-179, March 1995.
[10] G. Krell, B Michaelis, and A. Herzog. Elektronische bildfokussierung mit künstlichen neuronalen netzen. In 8. Symposium "`Maritime Elektronik"', pages 83-87. Universität Rostock, April 1995.
[11] G. Krell, B. Michaelis, and A. Herzog. Bildvorverarbeitung unter einbeziehung künstlicher neuronaler netze. In Materialien des 40. Internationalen Wissenschaftlichen Kolloquiums, pages 570-575. Technischen Universität Ilmenau, September 1995.
[12] G. Krell, A. Herzog, and B. Michaelis. Real-time image restoration with an artificial neural network. In International Conference on Neural Networks (ICNN '96), pages 1552-1557, Washington, June 1996.
[13] G. Krell, A. Herzog, and B. Michaelis. An artificial neural network for real-time image restoration. In IEEE Instrumentation & Measurement Technology Conference IMTC/96, pages 833-838, Brussels, Belgium, June 1996.
[14] A. Herzog, G. Krell, B. Michaelis, K. Braun, J. Wang, and W. Zuschratter. Restoration of three-dimensional quasi-binary images from confocal microscopy and its application to dendritic trees. In Tony Wilson Carol J. Cogswell, José-Angel Conchello, editor, Progress in Biometrical Optics: Three-Dimensonal Microscopy: Image Acquisition and Processing IV,. SPIE 2984, 1997.
[15] Andreas Herzog, Gerald Krell, Bernd Michaelis, Jizhong Wang, Werner Zuschratter, and Katharina Braun. Three-dimensional quasi-binary image restoration for confocal microscopy and its application to dendritic trees. In Josef Pauli Gerald Sommer, Kostas Daniilidis, editor, Computer Analysis of Images and Patterns 7'th International Conference, CAIP'97, Kiel, Germany, pages 114-121. Spinger, Lecture Notes of Computer Science 1296, September 1997.
[16] A. Herzog, G. Krell, B. Michaelis, and W. Zuschratter. 3D Formrekonstruktion an der Auflösungsgrenze konfokaler Laserscan- Mikroskope. In DAGM Symposium Mustererkennung, Braunschweig September 1997,pp. 119-126, Springer Verlag 1997, pages 119-126. Springer, September 1997.
[17] G. Krell, H. R. Tizhoosh, T. Lilienblum, C. J. Moore, and B Michaelis. Fuzzy image enhancement and associative feature matching in radiotherapy. In International Conference on Neural Networks (ICNN '97), pages 1490-1495, Houston, Texas, June 1997.
[18] G. Krell, H. R. Tizhoosh, T. Lilienblum, C. J. Moore, and B Michaelis. Enhancement and associative restoration of electronic portal images in radiotherapy. In 10th IEEE Symposium on Computer-Based Medical Systems, pages 104-108, Maribor, Slovenia, June 1997. IEEE Computer Society Press.
[19] H. R. Tizhoosh, G. Krell, and B Michaelis. Locally adaptive fuzzy image enhancement. Lecture Notes in Computer Science 1226, Springer:April, 1997.
[20] H. R. Tizhoosh, G. Krell, and B. Michaelis. On fuzzy enhancement of megavoltage images in radiation therapy. In 6th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE'97), pages Volume III, pp. 1399-1404, Barcelona, Spain, July 1996.
[21] H. R. Tizhoosh, G. Krell, and B. Michaelis. Additive fuzzy enhancement and an associative memory for feature tracking in radiation therapy images. In IEEE International Conference on Image Processing, pages Volume II of III, pp. 398-401, Santa Barbara, California USA, October 1997.
[22] A. Herzog, G. Krell, B. Michaelis, and W. Zuschratter. Tracking on tree-like structures in 3-d confocal images. In Tony Wilson Carol J. Cogswell, José-Angel Conchello, editor, Progress in Biometrical Optics: Three-Dimensonal Microscopy: Image Acquisition and Processing V, pages 165-176. SPIE 3261, 1998. 17.01.-29.01.
[23] G. Krell and B. Michaelis. An artificial neural network for inclusion of a-priori information from diagnosis images into the image analysis of on-line data in radiotherapy. In Neuronale Netze in der Anwendung '98, pages 147-154, 1998. 12.02.-13.02.
[24] G. Krell, H.R. Tizhoosh, and B. Michaelis. Integration of a-priori image information in radiation therapy via neural networks and fuzzy methods. In Informations- und Mikrosystemtechnik, pages 241-248, 1998. 25.03.-27.03.
[25] G. Krell, H.R. Tizhoosh, T. Lilienblum, C.J. Moore, and B. Michaelis. Enhancement and associative restoration of electronic portal images in radiotherapy. International Journal of Medical Informatics, Vol. 49/2:157-171, 1998.
[26] B. Michaelis and G Krell. Echtzeitbildrestauration mit künstlichen neuronalen netzen zur kompensation von aufnahmefehlern. In Tagungsmaterialien des "Neuro-NordOst" - anwendungsbezogener Workshop zu neuronalen, evolutionären und Fuzzy-Technologien in der Bildverarbeitung, 1998. 29.05.
[27] D. Nauck, G. Krell, R. Kruse, and B. Michaelis. Neural networks in applications. In D. Nauck, G. Krell, R. Kruse, and B. Michaelis, editors, Third international workshop, NN'98, page 278, Magdeburg, Germany, 1998. Inst. of knowledge processing and language engineering. February 12 - 13.
[28] H. R. Tizhoosh, G. Krell, and B. Michaelis. A hybrid neuro fuzzy system for knowledge-based restoration of electronic portal images in radiation therapy. In Takeshi Yamakawa and Gen Matsumoto, editors, Metodologies for the conception, design and application of soft computing.vol. 1, pages 341 - 344, 1998.
[29] H.R. Tizhoosh, G. Krell, and B. Michaelis. Lambda-enhancement: Contrast adaptation based on optimization of image fuzziness. In International Conference on Fuzzy Systems (FUZZ-IEEE '98), pages 1548-1553, 1998. 05.05.-09.05.
[30] W. Zuschratter, T. Steffen, B. Braun, A. Herzog, G. Krell, B. Michaelis, and H. Scheich. Acquisition of multiple image stacks with confocal laser scanning microskope. In Tony Wilson Carol J. Cogswell, José-Angel Conchello, editor, Progress in Biometrical Optics: Three-Dimensional and Multidimensional Image Acquisition and Processing V, pages 177-186. SPIE 3261, 1998.
[31] G. Krell, B. Michaelis, and G. Gademann. Using pre-treatment images for evaluation of on-line data in radiotherapy with neural networks. Journal of the International Federation for Medical and Biological Engineering, Vol. 37:1082-1083, 1999.
[32] G. Krell, B. Michaelis, D. Nauck, and R. Kruse. Neural networks in applications. In Fourth international workshop, NN'99, March 1999.
[33] C. J. Moore, P. A. Graham, D. Burton, M. Lalor, B. Shariat, D. Van Dorpe, and G. Krell. Science and technology leveraging change in the 'diagnostic therapeutic cycle of medical thinking' in advanced radiotherapy. In Fifth Conference of the European Society for Engineering and Medicine, pages 17-18; 57-58, 1999. May 30th-June 2nd.
[34] H. R. Tizhoosh, G. Krell, and B. Michaelis. Enhancement of megavoltage image in radiation therapy using fuzzy and neural image processing techniques. In P.S. Szczepaniak, P.J.G. Lisboa, and S. Tsumoto, editors, FUZZY SYSTEMS IN MEDICINE, Studies in Fuzziness and Soft Computing. Physica-Verlag, 1999.
[35] H. R. Tizhoosh, G. Krell, and B. Michaelis. Knowledge-based enhancement of megavoltage images in radiation therapy using a hybrid neuro fuzzy system. Journal of Vision and Image Computing, 1999.
[36] M. Walke, P. Albrecht, R. Calow, G. Krell, G. Gademann, and B. Michaelis. Patient positioning and motion investigations with a new optical three-dimensional sensor. Journal of the International Federation for Medical and Biological Engineering, Vol. 37:1010-1011, 1999.
[37] G. Krell, B. Michaelis, M. Walke, R. Calow, and N. Riefenstahl. Bilder aus Diagnostik und Behandlungsplanung in der Strahlentherapie zur Auswertung von Online-daten mit neuronalen Netzen. In A. Horsch and T. Lehmann, editors, Bildverarbeitung für die Medizin 2000 : Algorithmen - Systeme - Anwendungen (Workshop München), pages 277-281, Berlin, 2000. Springer. 12. - 14.03.
[38] G. Krell, B. Michaelis, and G. Gademann. Image fusion by an associative memory applied in radiotherapy. In F. Naghdy, editor, Intelligent systems and application, ISA'2000, pages 1544-1549, 2000. December 11 - 15, Beitrag auf CD-ROM.
[39] H.-R. Tizhoosh, G. Krell, and B. Michaelis. Enhancement of megavoltage images in radiation therapy using fuzzy and neural image processing techniques. In Piotr S. Szczepaniak, editor, Fuzzy systems in medicine, pages 316-334. Physica-Verl., Heidelberg, 2000.
[40] N. Riefenstahl, G. Krell, R. Calow, B. Michaelis, and M. Walke. A multimodal image fusion framework applied in radiotherapy. In E. Banissi, editor, Information visualisation, IV 2001 (2001 IEEE International conference on computer visualization and graphics), pages 173 - 178, Los Alamitos, CA, 2001. IEEE. 25 - 27 July.
[41] H. R. Tizhoosh, G. Krell, and B. Michaelis. Knowledge-based enhancement of megavoltage images in radiation therapy using a hybrid neuro-fuzzy system. Image and vision computing, pages 217 - 233, 2001.
[42] R. Calow, P. Albrecht, G. Krell, and B. Michaelis. Ein Online-System zur Patientenpositionierung unter Verwendung codierten Lichtes. In Bildverarbeitung für die Medizin 2002, Proceedings des Workshops, pages 69-72. Springer, 2002.
[43] R. Calow, G. Gademann, G. Krell, R. Mecke, B. Michaelis, N. Riefenstahl, and M. Walke. Photogrammetric measurement of patients in radiotherapy. Journal of Photogrammetry and Remote Sensing, Vol. 56:347-359, 2002.
[44] G. Krell, B. Michaelis, and F. Daniel. Verfahren und einrichtung zur bestimmung und mindestens teilweisen korrektur der fehler eines bildwiedergabesystems, 2002.
[45] G. Krell, B. Michaelis, and F. Daniel. Verfahren und einrichtung zur bestimmung und mindestens teilweisen korrektur der fehler eines bildwiedergabesystems, 2002.
[46] G. Krell, N. Riefenstahl, and B. Michaelis. Associated images in multidimensional data sets. In First International ICSC-NAISO Congress on Neuro Fuzzy Technologies, pages Abstract p. 51, paper on Data CD, 2002. 16.-19.01.
[47] R. Rebmann, G. Krell, and B. Michaelis. Reduction of compression artefacts caused by jpeg compression. In J. J. Villanueva, editor, Visualization, imaging, and image processing (The second IASTED internationalconference), pages 271 - 275. Acta Press, 2002. September 9-12.
[48] R. Rebmann, G. Krell, and B. Michaelis. Image restoration for compression artifacts by an associative memory. In WSEAS International Conference on Signal Processing, Robotics and Automation(ISPRA '02), pages 2051-2054, 2002. June 12-16.
[49] R. Rebmann, G. Krell, and B. Michaelis. Image Restoration for Compression Artifacts by an Associative Memory. WSEAS Book Advances in Systems Engineering, Signal Processing and Communications, 2002.
[50] N. Riefenstahl, G. Krell, and B. Michaelis. Association based multimodal image sequence analysis with wavelets in radiotherapy. In International Conference on APPLIED SIMULATION AND MODELLING (ASM2002), pages 478-484. ACTA Press, 2002. June 25-28.
[51] M. Walke, N. Riefenstahl, G. Krell, G. Gademann, and B. Michaelis. Der Mensch ist kein Eisblock. Magdeburger Wissenschaftsjournal, pages 3-10, 2 2002.
[52] F. Daniel, G. Krell, O. Schnelting, and St. Schünemann. Elektronische Bildkorrektur für Rückprojektionsdisplays zur Qualitätsverbesserung und Kostenoptimierung. In 18. Electronic Displays, Wiesbaden, proceedings, pages 140-146, 2003. 24.-25.09.
[53] G. Krell, R. Rebmann, U. Seiffert, and B. Michaelis. Improving still image coding by an SOM-controlled associative memory. LNCS 2905, pages 571-579, November 2003.
[54] R. Rebmann, G. Krell, U. Seiffert, and B. Michaelis. Associative correction of compression artefacts with a self-organizing map classifying the image content. In Data Compression Conference, page 446, 2003. March 25-27.
[55] N. Riefenstahl, G. Krell, and B. Michaelis. Association based multimodal image sequence analysis with wavelets in radiotherapy. In International Conference on APPLIED SIMULATION AND MODELLING (ASM2002), pages 478-484. ACTA Press, 2003. June 25-28.
[56] G. Krell and B. Michaelis. Artificial neural networks for correction of microwave images. In Book of Abstracts, EUROEM 12-16 July, pages 196-197. University of Magdeburg, July 2004.
[57] G. Krell and B. Michaelis. Correcting image acquistion/display errors by artificial neural networks. In 7th International Conference on Pattern Recognition and Image Analysis: New Information Technologies. PRIA-7, 18-23 October, pages 293-296. St. Petersburg Electrotechnical University, October 2004.
[58] R. Rebmann, B. Michaelis, G. Krell, U. Seiffert, and F. Püschel. Improving image processing systems by artificial neural networks. In Reading and Learning - Adaptive Content Recognition, pages 37-64. Springer, 2004.
[59] N. Riefenstahl, B. Michaelis, G. Krell, and M. Walke. Dynamische Bilddatenfusion in der Strahlentherapie mittels Bewegungsanalyse und -kompensation. In 38. Jahrestagung der Deutschen Gesellschaft für Biomedizinsche Technik im VDE – BMT 2004, 22.-24. September, Ilmenau 2004, Biomedizinsche Technik, Vol. 49, Ergänzungsband 2 Teil 1, pages Vol. 39, pp 204-205, 2004.
[60] M. Tornow, J. Kaszubiak, R. Kuhn, B. Michaelis, and G. Krell. Stereophotogrammetric real-time-3-d-machine-vision. In PATTERN RECOGNITION and IMAGE ANALYSIS, pages Vol. 3, pp 940- 943, St. Petersburg, 2004. Oktober 18-23.
[61] G. Krell and B. Michaelis. Correcting image acquisition/display errors by artificial neural networks. Int. Journal PATTERN RECOGNITION AND IMAGE ANALYSIS, MAIK "Nauka (International Academic Publishing Concern "Science")/Interperiodica" Publishing, Moscow, 15(1):234-237, 2005.
[62] G. Krell and B. Michaelis. Training of neural networks for image correction with natural images. In Proc. of the SIP2005, Honolulu, 15.-17.08.2005, pages 172-177, August 2005.
[63] M. Tornow, J. Kaszubiak, R. Kuhn, B. Michaelis, and G. Krell. Stereophotogrammetric real-time-3-d-machine-vision. In PATTERN RECOGNITION and IMAGE ANALYSIS, page vol.15 no.3 (accepted), 2005.
[64] A. Herzog, G. Krell, B. Michaelis, S. Westerholz, C. Helmeke, and K. Braun. Geometrical modelling and visualization of pre- and postsynaptic structures in double-labeling confocal images. In International Conference on Medical Information Visualisation - MediVis2006 London, pages 34-39, 2006.
[65] A. Herzog, G. Krell, B. Michaelis, W. Ovtscharoff, and K Braun. Detection of presynaptic terminals on dendritic spines in double labeling confocal images. In ICPR Hongkong, pages 715-718, 2006.
[66] M. Tornow, J. Kaszubiak, R. Kuhn, B. Michaelis, and G. Krell. Stereophotogrammetric real-time 3d machine vision. Pattern Recognition and Image Analysis, 2006, Vol. 16, No. 1, 16, 1:100-103, 2006.
[67] N. Riefenstahl, G. Krell, M. Walke, B. Michaelis, and G. Gademann. Optical surface sensing and multimodal image fusion for position verification in radiotherapy. In International Conference on Medical Information Visualisation - MediVis2006 London, pages 21-26, 2006.
[68] M. Tornow, J. Kaszubiak, R. Kuhn, B. Michaelis, and G. Krell. Stereophotogrammetric real-time-3-d-machine-vision. Int. Journal PATTERN RECOGNITION AND IMAGE ANALYSIS, MAIK "Nauka (International Academic Publishing Concern "Science")/Interperiodica" Publishing, Moscow, ISSN 1054-6618, Vol 16(No. 1):100-103, 2006.
[69] M. Ahmad, A. Al-Hamadi, G. Krell, and B. Michaelis. Enhancing the visual quality in hybrid filters wavelet-based low bit-ratevideo codec. In Proceedings of 6th International Conference of MEASUREMENT OF AUDIO AND VIDEO QUALITY IN NETWORKS - MESAQIN 2007, Prague, pages 59-69, June 2007.
[70] M. Ahmad, A. Al-Hamadi, G. Krell, and B. Michaelis. Very low bit rate video codec based on wavelet filters. In International Conference on Computational Science and Its Applications (ICCSA), pages 65-71. published by IEEE-CS, 2007.
[71] M. Ahmad, G. Krell, and B. Michaelis. Different filters discrete wavelet transform-based intra-frame video codec for very low bit rate. In Proceedings of the Advanced Concepts for Intelligent Vision Systems - Acivs2007, Delft. Springer, 2007.
[72] M. Elmezain, Al-Hamadi, A., G. Krell, and B. Michaelis. Gesture recognition for alphabets from hand motion trajectory using hidden markov models. In Proceedings of the 7th IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2007), pages 1209-1214, 2007. [ .pdf ]
[73] G. Krell, A. Al-Hamadi, and B. Michaelis. Multi-error correction of image forming systems maintaining colors. In Proceedings of the 7th IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2007), pages 1221-1226, 2007. [ .pdf ]
[74] Mostafa A. Ahmad, G. Krell, A. Al-Hamadi, Mohiy Hadhoud, and B. Michaelis. Spatially scalable wavelet-based intra-frame video codec using subband interpolation. In 4th International Symposium on Image/Video Communications (ISIVC), Spain, pages 55-60, July 2008. [ .pdf ]
[75] F. Daniel, G. Krell, and B. Michaelis. Us patent: Method and apparatus for defining and correcting image data, 2008. 25.11.2008.
[76] G. Krell and B. Michaelis. Multi-error correction of image forming systems by training samples maintaining colors. In Proceedings of the VISAPP 2008 - International Conference on Computer Vision Theory and Applications, pages 152-158, 2008. [ .pdf ]
[77] M. Tornow, J. Kaszubiak, R. Kuhn, B. Michaelis, and G. Krell. Stereophotogrammetric real-time-3-d-machine-vision. Journal of Pattern Recognition and Image Analysis, Moscow, MAIK Nauka/InterperiodicaPubl.,, 18(1):139-150, 2008. [ .pdf ]
[78] G. Krell, R. Niese, and B. Michaelis. Facial expression recognition with multi-channel deconvolution. In Advances in Pattern Recognition, 2009. ICAPR '09. Seventh International Conference on, pages 413-416, 2009. February 4-6. [ .pdf ]
Facial expression recognition is an important task in human computer interaction systems to include emotion processing. In this work we present a multi-channel deconvolution method for post processing of face expression data derived from video sequences. Photogrammetric techniques are applied to determine real world geometric measures and to build the feature vector. SVM classification is used to classify a limited number of emotions from the feature vector. A multi-channel deconvolution removes ambiguities at the transitions between different classified emotions. This way, typical temporal behavior of facial expression change is considered.

 

[79] G. Krell, R. Niese, A. Al-Hamadi, and B. Michaelis. Suppression of uncertainties at emotional transitions - facial mimics recognition in video with 3-d model. In Proceedings of the VISAPP 2010 - International Conference on Computer Vision Theory and Applications, pages 537-542, Angers, France, 5 2010. 17-21 May. [ .pdf ]
Facial expression is of increasing importance for man-machine communication. It is expected that future human computer interaction systems even include emotions of the user. In this work we present an associative approach based on a multi-channel deconvolution for processing of face expression data derived from video sequences supported by a 3-D facial model generated with stereo support. Photogrammetric techniques are applied to determine real world geometric measures and to create a feature vector. Standard classification is used to discriminate between a limited number of mimics, but often fails at transitions from one detected emotion state to another. The proposed associative approach reduces ambiguities at the transitions between different classified emotions. This way, typical patterns of facial expression change is considered.

 

[80] Bernd Michaelis, Gerald Krell, and Florian Daniel. Patent: Method and device for determining and at least partially corecting of errors in an image reproducing system, 2011.
[81] Saira Saleem Pathan, Ayoub Al-Hamadi, Gerald Krell, and Bernd Michaelis. Resolving data-association uncertainty in multi-object tracking through qualitative modules. In Proceedings of the VISAPP 2010 - International Conference on Computer Vision Theory and Applications, pages 461-466, 5 2010. [ .pdf ]
In real-time tracking, a crucial challenge is to efficiently build association among the objects. However, realtime interferences (e.g. occlusion) manifest errors in data association. In this paper, the uncertainties in data association are handled when discrete information is incomplete during occlusion through qualitative reasoning modules. The formulation of the qualitative modules are based on exploiting human-tracking abilities (i.e. common sense) which are integrated with data association technique. Each detected object is described as a node in space with a unique identity and status tag whereas association weights are computed using CWHI and Bhattacharyya coefficient. These weights are input to qualitative modules which interpret the appropriate status of the objects satisfying the fundamental constraints of objects continuity during tracking. The results are linked with Kalman Filter to estimate the trajectories of objects. The proposed approach has shown promising results illustrating its contribution when tested on a set of videos representing various challenges.

 

[82] Gerald Krell. 17. Workshop Farbbildverarbeitung 29.09.-30.09.2011 Konstanz, Offizieller Tagungsband, chapter Training von Netzen für die mehrkanalige Bildkorrektur, pages 41-50. Markus Schnitzlein, 2011. ISBN: 978-3-00-035834-0. [ .pdf ]
Ein reales, mehrkanaliges, bildgebendes System wird mit einem korrigierenden Netz kombiniert. Dabei bilden die angelernten lokalen, ortsvarianten Filter gewissermaßen ein die Bildkanäle verbindendes Netzwerk, dessen Ausgänge die korrigierten Bildkanäle sind. In einem Lernvorgang erfolgt die Ermittlung der erforderlichen Korrekturwerte mit Hilfe von Testbildern, um verschiedene Fehlerarten gleichzeitig zu erfassen. Die einmal ermittelten Korrekturwerte werden für die laufende Bildkorrektur benutzt, solange sich die zu korrigierenden Fehler des bildgebenden Systems nicht wesentlich ändern.

 

[83] Sharpness Improvement of Warped Document Images for Top View Book Scanners, Sorrento, Italy, 11 2012. 25-29 November. [ .pdf ]
This paper is aiming at improving the top view book scanner functionalities to the ability of depicting homogeneous sharpness across the output colour image. Typically, the opened book has a curved shape which results in a space-variant blur in the recorded image. A priori calibration filters are computed by taking an advantage of longitudinal chromatic aberration behaviour in the scanners. Hence, the sharpest channel on the focused plane is chosen as an exemplar to compute a restoration filter for the sharpest channel on each of the defocused planes. Assuming strong correlation between the channels, another filter is computed to reflect the sharpness of the restored channel to the other channels. In order to enhance spatial homogeneity of the scanned image, 3-D information is estimated from book contours. Results exhibit the possibility of having visually homogeneous sharpness in the entire scanned images.

 

[84] Gerald Krell, Michael Glodek, Axel Panning, Ingo Siegert, Bernd Michaelis, Andreas Wendemuth, and Friedhelm Schwenker. Fusion of fragmentary classifier decisions for affective state recognition. In Morency Schwenker, Scherer, editor, Multimodal Pattern Recognition of Social Signals in Human Computer Interaction (MPRSS 2012), volume 7742 of Lecture Notes of Artificial Intelligence (LNAI), pages 116-130. Springer, Tsukuba Science City, Japan, 2012. November 11. [ .pdf ]
Real human-computer interaction systems based on different modalities face the problem that not all information channels are always available at regular time steps. Nevertheless an estimation of the current user state is required at anytime to enable the system to interact instantaneously based on the available modalities. A novel approach to decision fusion of fragmentary classifications is therefore proposed and empirically evaluated for audio and video signals of a corpus of non-acted user behavior. It is shown that visual and prosodic analysis successfully complement each other leading to an outstanding performance of the fusion architecture.

 

[85] Axel Panning, Ingo Siegert, Ayoub Al-Hamadi, Andreas Wendemuth, Dietmar Rösner, Jörg Frommer, Gerald Krell, and Bernd Michaelis. Multimodal Affect Recognition in Spontaneous HCI Environment. In Proceedings of the IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC 2012), pages 430 - 435, 2012. [ .pdf ]
Human Computer Interaction (HCI) is known to be a multimodal process. In this paper we will show results of experiments for affect recognition, with non-acted, affective multimodal data from the new Last Minute Corpus (LMC). This corpus is more related to real HCI applications than other known data sets where affective behavior is elicited untypically for HCI.We utilize features fromthreemodalities: facial expressions, prosody and gesture. The results show, that even simple fusion architectures can reach respectable results compared to other approaches. Further we could show, that probably not all features and modalities contribute substantially to the classification process, where prosody and eye blink frequency seem most contributing in the analyzed dataset. Index Terms: Multimodal, Affect Recognition, HCI

 

[86] Samy Sadek, Ayoub Al-Hamadi, Gerald Krell, and Bernd Michaelis. Affine-Invariant Feature Extraction for Activity Recognition. International Scholarly Research Notices, ISRN Machine Vision, 2013:e215195, July 2013. [ DOI | http | .pdf ]
We propose an innovative approach for human activity recognition based on affine-invariant shape representation and SVM-based feature classification. In this approach, a compact computationally efficient affine-invariant representation of action shapes is developed by using affine moment invariants. Dynamic affine invariants are derived from the 3D spatiotemporal action volume and the average image created from the 3D volume and classified by an SVM classifier. On two standard benchmark action datasets (KTH and Weizmann datasets), the approach yields promising results that compare favorably with those previously reported in the literature, while maintaining real-time performance.

 

[87] Ingo Siegert, Michael Glodek, Axel Panning, Gerald Krell, Friedhelm Schwenker, Ayoub Al-Hamadi, and Andreas Wendemuth. Using speaker group dependent modelling to improve fusion of fragmentary classifier decisions. In 2013 IEEE International Conference on Cybernetics, pages 132-137, 2013. [ .pdf ]
Current speech-controlled human computer interaction is purely based on spoken information. For a successful interaction, additional information such as the individual skills, preferences and actual affective state of the user are often mandatory. The most challenging of these additional inputs is the affective state, since affective cues are in general expressed very sparsely. The problem can be addressed in two ways. On the one hand, the recognition can be enhanced by making use of already available individual information. On the other hand, the recognition is aggravated by the fact that research is often limited to a single modality, which in real-life applications is critical since recognition may fail in case sensors do not perceive a signal. We address the problem by enhancing the acoustic recognition of the affective state by partitioning the user into groups. The assignment of a user to a group is performed at the beginning of the interaction, such that subsequently a specialized classifier model is utilized. Furthermore, we make use of several modalities, acoustics, facial expressions, and gesture information. The combination of decisions not affected by sensor failures from these multiple modalities is achieved by a Markov Fusion Network. The proposed approach is studied empirically using the LAST MINUTE corpus. We could show that compared to previous studies a significant improvement of the recognition rate can be obtained. Index Terms: Multimodal Pattern Recognition, Affect Recognition, Companion Systems, Human Computer Interaction

 

[88] M. Walke, N. Saeednejad, G. Krell, and G. Gademann. Investigation of different icp algorithms with respect to the registration precision of data from two different 3d surface sensors (rt-vision, in-house built). In Joint Conference of the SSRMP, DGMP, ÖGMP (Dreiländertagung der Medizinischen Physik), 7-10 September 2014, University of Zurich/Switzerland, 2014.
The installation of a new optical sensor on the TomoTherapy HD modality requires the investigation of the precision of the settlement (registration) of raw data generated by this system. The applied ICP (iterative closest point) algorithm should be tested in comparison to the inherent data registration of RT Vision and additionally to the own in-house built 3D surface sensor. The action of independent and different ICP algorithms was tested on raw data for pre-defined positions of the treatment couch. In comparison to this, these ICP algorithms were also applied to data gathered by our installed in-house 3D system in the localizer room. Our aim was an assessment of the usability of different ICP algorithms. Especially an estimation of the reliability of the particular ICP method for registration should be checked.

 

[89] Michael Glodek, Frank Honold, Thomas Geier, Gerald Krell, Florian Nothdurft, Stephan Reuter, Felix Schüssel, Thilo Hörnle, Klaus Dietmayer, Wolfgang Minker, Susanne Biundo, Michael Weber, Günther Palm, and Friedhelm Schwenker. Fusion paradigms in cognitive technical systems for human-computer interaction. Number 0. 2015. [ DOI | http | .pdf ]
Abstract Recent trends in human–computer interaction (HCI) show a development towards cognitive technical systems (CTS) to provide natural and efficient operating principles. To do so, a {CTS} has to rely on data from multiple sensors which must be processed and combined by fusion algorithms. Furthermore, additional sources of knowledge have to be integrated, to put the observations made into the correct context. Research in this field often focuses on optimizing the performance of the individual algorithms, rather than reflecting the requirements of CTS. This paper presents the information fusion principles in {CTS} architectures we developed for Companion Technologies. Combination of information generally goes along with the level of abstractness, time granularity and robustness, such that large {CTS} architectures must perform fusion gradually on different levels — starting from sensor-based recognitions to highly abstract logical inferences. In our {CTS} application we sectioned information fusion approaches into three categories: perception-level fusion, knowledge-based fusion and application-level fusion. For each category, we introduce examples of characteristic algorithms. In addition, we provide a detailed protocol on the implementation performed in order to study the interplay of the developed algorithms.
Keywords: Cognitive technical systems
[90] Rupesh Durgesh, Gerald Krell, Andrii Iegorov, Peter Schuberth, and Felix Friedmann. Faster convolutional architecture search for semantic segmentation. In Workshop on Deep Learning for Autonomous Driving ITSC2017, October 2017. [ http ]
[91] Gerald Krell, Nazila Saeid Nezhad, Mathias Walke, Ayoub Al-Hamadi, and Günther Gademann. Assessment of iterative closest point registration accuracy for different phantom surfaces captured by an optical 3d sensor in radiotherapy. Computational and Mathematical Methods in Medicine, 2017:13, 2017. [ DOI | http ]
[92] Friedhelm Schwenker, Ronald Böck, Martin Schels, Sascha Meudt, Ingo Siegert, Michael Glodek, Markus Kächele, Miriam Schmidt-Wack, Patrick Thiam, Andreas Wendemuth, and Gerald Krell. Multimodal affect recognition in the context of human-computer interaction for companion-systems. In Susanne Biundo and Andreas Wendemuth, editors, Companion Technology, pages 387-408. Springer International Publishing. [ DOI | http ]
[93] Ingo Siegert, Felix Schüssel, Miriam Schmidt, Stephan Reuter, Sascha Meudt, Georg Layher, Gerald Krell, Thilo Hörnle, Sebastian Handrich, Ayoub Al-Hamadi, Klaus Dietmayer, Heiko Neumann, Günther Palm, Friedhelm Schwenker, and Andreas Wendemuth. Multi-modal information processing inCompanion-systems: A ticket purchase system. In Susanne Biundo and Andreas Wendemuth, editors, Companion Technology, pages 493-500. Springer International Publishing. [ DOI | http ]

This file was generated by bibtex2html 1.97.

Letzte Änderung: 11.12.2017 - Ansprechpartner: Dipl.-Ing. Arno Krüger