Zobrazeno 1 - 10
of 86
pro vyhledávání: '"Daniel Keysers"'
Publikováno v:
ELCVIA Electronic Letters on Computer Vision and Image Analysis, Vol 6, Iss 1 (2007)
We present an efficient method to determine the optimal matching of two patch-based image object representations under rotation, scaling, and translation (RST). This use of patches is equivalent to a fullyconnected part-based model, for which the pre
Externí odkaz:
https://doaj.org/article/464916e81ed644c6bdc2a07fc11f1eca
Autor:
Thomas Deselaers, Sandro Feuz, Daniel Keysers, Alexander N. Daryin, Philippe Gervais, Henry Allan Rowley, Pedro Gonnet, Li-Lun Wang, Victor Carbune, Marcos Calvo
We describe an online handwriting system that is able to support 102 languages using a deep neural network architecture. This new system has completely replaced our previous Segment-and-Decode-based system and reduced the error rate by 20%-40% relati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3eba106707bab163ef26e7c93741a448
http://arxiv.org/abs/1902.10525
http://arxiv.org/abs/1902.10525
Publikováno v:
IEEE Transactions on Human-Machine Systems. 45:263-271
We present GyroPen, a method to reconstruct the motion path for pen-like interaction from standard built-in sensors in modern smartphones. The key idea is to reconstruct a representation of the trajectory of the phone's corner that is touching a writ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::21e7167e098239bb13c3e280616dca5b
https://doi.org/10.1109/thms.2014.2365723
https://doi.org/10.1109/thms.2014.2365723
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 39(6)
We describe Google's online handwriting recognition system that currently supports 22 scripts and 97 languages. The system's focus is on fast, high-accuracy text entry for mobile, touch-enabled devices. We use a combination of state-of-the-art compon
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e69d374ba005565c2b20efb83a9b791a
https://pubmed.ncbi.nlm.nih.gov/27244718
https://pubmed.ncbi.nlm.nih.gov/27244718
Publikováno v:
International Journal of Document Analysis and Recognition (IJDAR). 11:81-96
When a page of a book is scanned or photocopied, textual noise (extraneous symbols from the neighboring page) and/or non-textual noise (black borders, speckles, ...) appear along the border of the document. Existing document analysis methods can hand
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cf2c1b798cb35fb7572efc0f60c1193d
https://doi.org/10.1007/s10032-008-0071-7
https://doi.org/10.1007/s10032-008-0071-7
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 30:941-954
Informative benchmarks are crucial for optimizing the page segmentation step of an OCR system, frequently the performance limiting step for overall OCR system performance. We show that current evaluation scores are insufficient for diagnosing specifi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::73fb53206fdbe04b0dd5c26681bfec13
https://doi.org/10.1109/tpami.2007.70837
https://doi.org/10.1109/tpami.2007.70837
Publikováno v:
Information Retrieval. 11:77-107
An experimental comparison of a large number of different image descriptors for content-based image retrieval is presented. Many of the papers describing new techniques and descriptors for content-based image retrieval describe their newly proposed m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40a9a0678ed1850e735ccbbb2831362f
https://doi.org/10.1007/s10791-007-9039-3
https://doi.org/10.1007/s10791-007-9039-3
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 29:1422-1435
We present the application of different nonlinear image deformation models to the task of image recognition. The deformation models are especially suited for local changes as they often occur in the presence of image object variability. We show that,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d0c3e4cb183110906b20974c33a89668
https://doi.org/10.1109/tpami.2007.1153
https://doi.org/10.1109/tpami.2007.1153
Autor:
Hermann Ney, Berthold B. Wein, Thomas Deselaers, Mark Oliver Güld, Daniel Keysers, Klaus Spitzer, Henning Schubert, Thomas Martin Lehmann
Publikováno v:
Computerized Medical Imaging and Graphics. 29:143-155
Categorization of medical images means selecting the appropriate class for a given image out of a set of pre-defined categories. This is an important step for data mining and content-based image retrieval (CBIR). So far, published approaches are capa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::945774168229375af2a08448f0ef8081
https://doi.org/10.1016/j.compmedimag.2004.09.010
https://doi.org/10.1016/j.compmedimag.2004.09.010
Autor:
Enrique Vidal, Francisco Casacuberta, Alejandro Héctor Toselli, Ismael Salvador, Alfons Juan, Jorge González, Hermann Ney, Daniel Keysers
Publikováno v:
International Journal of Pattern Recognition and Artificial Intelligence. 18:519-539
The interpretation of handwritten sentences is carried out using a holistic approach in which both text image recognition and the interpretation itself are tightly integrated. Conventional approaches follow a serial, first-recognition then-interpreta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::18f6ad984b33efc4710d7d7ed2af8452
https://doi.org/10.1142/s0218001404003344
https://doi.org/10.1142/s0218001404003344