Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Vladimir Rybalkin"'
iDocChip: A Configurable Hardware Accelerator for an End-to-End Historical Document Image Processing
Autor:
Menbere Kina Tekleyohannes, Vladimir Rybalkin, Muhammad Mohsin Ghaffar, Javier Alejandro Varela, Norbert Wehn, Andreas Dengel
Publikováno v:
Journal of Imaging, Vol 7, Iss 9, p 175 (2021)
In recent years, there has been an increasing demand to digitize and electronically access historical records. Optical character recognition (OCR) is typically applied to scanned historical archives to transcribe them from document images into machin
Externí odkaz:
https://doaj.org/article/873b77f5b4e5425397eeb6d6d8aea7f6
Autor:
Mhd Rashed Al Koutayni, Vladimir Rybalkin, Jameel Malik, Ahmed Elhayek, Christian Weis, Gerd Reis, Norbert Wehn, Didier Stricker
Publikováno v:
Sensors, Vol 20, Iss 10, p 2828 (2020)
The estimation of human hand pose has become the basis for many vital applications where the user depends mainly on the hand pose as a system input. Virtual reality (VR) headset, shadow dexterous hand and in-air signature verification are a few examp
Externí odkaz:
https://doaj.org/article/1c84826977a640b4a692bbb6574ff765
Autor:
Muhammad Mohsin Ghaffar, Javier Alejandro Varela, Norbert Wehn, Menbere Kina Tekleyohannes, Vladimir Rybalkin, Andreas Dengel
Publikováno v:
International Journal of Parallel Programming. 49:253-284
In recent years,$$\hbox {optical character recognition (OCR)}$$optical character recognition (OCR)systems have been used to digitally preserve historical archives. To transcribe historical archives into a machine-readable form, first, the documents a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db6487ac39f6ed933b43fdd64875d519
https://doi.org/10.1007/s10766-020-00690-y
https://doi.org/10.1007/s10766-020-00690-y
Publikováno v:
Journal of Signal Processing Systems
Recurrent Neural Networks, in particular One-dimensional and Multidimensional Long Short-Term Memory (1D-LSTM and MD-LSTM) have achieved state-of-the-art classification accuracy in many applications such as machine translation, image caption generati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eca8a1419181ce28a957f18625834f40
https://doi.org/10.1007/s11265-020-01554-x
https://doi.org/10.1007/s11265-020-01554-x
Publikováno v:
FPL
Deep Neural Networks (DNNs) are capable of solving complex problems in domains related to embedded systems, such as image and natural language processing. To efficiently implement DNNs on a specific FPGA platform for a given cost criterion, e.g. ener
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::619a82955b40104f00221af87df51b43
Autor:
Norbert Wehn, Vladimir Rybalkin
Publikováno v:
FPGA
Multidimensional Long Short-Term Memory (MD-LSTM) neural network is an extension of one-dimensional LSTM for data with more than one dimension that allows MD-LSTM to show state-of-the-art results in various applications including handwritten text rec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::221c4fe0770059022baf0ad99c77c010
https://doi.org/10.1145/3373087.3375301
https://doi.org/10.1145/3373087.3375301
Autor:
Vladimir Rybalkin, Norbert Wehn, Andreas Dengel, Muhammad Mohsin Ghaffar, Menbere Kina Tekleyohannes
Publikováno v:
ReConFig
Digitizing historical archives poses a great challenge due to the quality degradation existing in these documents. Hence, even well-established Optical Character Recognition (OCR) systems, such as Abby, OCRopus, Tesseract, etc., fail to give sufficie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2b4dba281105c8029359e2cbcdf48faf
https://doi.org/10.1109/reconfig48160.2019.8994761
https://doi.org/10.1109/reconfig48160.2019.8994761
Publikováno v:
Journal of Signal Processing Systems. 93:1467-1467
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a18a0918ea5626041a442030cfa4a101
https://doi.org/10.1007/s11265-021-01684-w
https://doi.org/10.1007/s11265-021-01684-w
iDocChip: A Configurable Hardware Accelerator for an End-to-End Historical Document Image Processing
Autor:
Norbert Wehn, Andreas Dengel, Javier Alejandro Varela, Muhammad Mohsin Ghaffar, Vladimir Rybalkin, Menbere Kina Tekleyohannes
Publikováno v:
Journal of Imaging, Vol 7, Iss 175, p 175 (2021)
Journal of Imaging
Volume 7
Issue 9
Journal of Imaging
Volume 7
Issue 9
In recent years, there has been an increasing demand to digitize and electronically access historical records. Optical character recognition (OCR) is typically applied to scanned historical archives to transcribe them from document images into machin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ff3cc98e1d5a26cbe5d71d18abbc82f
https://doi.org/10.3390/jimaging7090175
https://doi.org/10.3390/jimaging7090175
Autor:
Muhammad Mohsin Ghaffar, Vladimir Rybalkin, Christian Weis, Chirag Sudarshan, Norbert Wehn, Jan Lappas, Matthias Jung
Publikováno v:
ISCAS
2019 IEEE International Symposium on Circuits and Systems (ISCAS)
2019 IEEE International Symposium on Circuits and Systems (ISCAS)
Many advanced neural network inference engines are bounded by the available memory bandwidth. The conventional approach to address this issue is to employ high bandwidth memory devices or to adapt data compression techniques (reduced precision, spars
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f6d19eff4035d5499126662da116c8b2
https://doi.org/10.1109/iscas.2019.8702458
https://doi.org/10.1109/iscas.2019.8702458