Výsledky vyhledávání - "Petra Gomez‐Krämer"

Robust Hashing for Character Authentication and Retrieval Using Deep Features and Iterative Quantization

Autor: Petra Gomez-Krämer, Mickael Coustaty, Musab Qassem Al-Ghadi, Jean-Christophe Burie, Théo Azzouza

Publikováno v: Document Analysis and Recognition – ICDAR 2021 Workshops ISBN: 9783030861971
ICDAR Workshops (1)

This paper proposes a hashing approach for character authentication and retrieval based on the combination of a convolutional neural network (CNN) and the iterative quantization (ITQ) algorithm. This hashing approach is made up of two steps: feature

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::954f435580091390212831c9dec3af1f
https://doi.org/10.1007/978-3-030-86198-8_33

Zobrazit plný text záznamu

Background Removal of French University Diplomas

Autor: Jean-Marc Ogier, Petra Gomez-Krämer, Mickael Coustaty, Tanmoy Mondal

Publikováno v: Document Analysis Systems14th IAPR International Workshop, DAS 2020
Document Analysis Systems 14th IAPR International Workshop, DAS 2020, 12116, Springer, Cham, pp.182-196, 2020, Lecture Notes in Computer Science, 978-3-030-57057-6. ⟨10.1007/978-3-030-57058-3_14⟩
Document Analysis Systems ISBN: 9783030570576
DAS

Separation of foreground text from noisy or textured background is an important preprocessing step for many document image processing problems. In this work we focus on decorated background removal and the extraction of textual components from French

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::035c7df23699d52959b47494a6068860
https://hal.archives-ouvertes.fr/hal-03030210

Zobrazit plný text záznamu

Low-complexity arrays of contour signatures for exact shape retrieval

Autor: Sylvain Marchand, Petra Gomez-Krämer, Florian Lardeux

Publikováno v: Pattern Recognition. 118:108000

We propose a framework for a fast exact shape retrieval called Low-complexity Arrays of Contour Signatures. The purposes are to match a shape against a database in constant time and to retrieve correct shapes very close to the query, while the latter

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eaec8419d179669d674690762cc1ccd2
https://doi.org/10.1016/j.patcog.2021.108000

Zobrazit plný text záznamu

Security and PrIvacy foR the Internet of Things: an overview of the project

Autor: Gilles Falquet, Sabrine Aroua, Nicolas Sidere, M. Rabah, Sami Ghadfi, Julian Murphy, Mickael Coustaty, R. Champagnat, Yacine Ghamri-Doudane, Klaus D. McDonald-Maier, Petra Gomez-Krämer, Gareth Howells, Nouredine Tamani, Kais Rouis

Publikováno v: 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)
2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), Oct 2019, Bari, Italy. pp.3993-3998, ⟨10.1109/SMC.2019.8914221⟩
IEEE International Conference on Systems, Man and Cybernetics (SMC 2019)
IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2019)

As the adoption of digital technologies expands, it becomes vital to build trust and confidence in the integrity of such technology. The SPIRIT project investigates the proof of concept of employing novel secure and privacy-ensuring techniques in ser

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::125cacabd52393dfec55c61f1578eede
https://hal.archives-ouvertes.fr/hal-02518333

Zobrazit plný text záznamu

Learning Free Document Image Binarization Based on Fast Fuzzy C-Means Clustering

Autor: Mickaël Coustaty, Jean-Marc Ogier, Tanmoy Mondal, Petra Gomez-Krämer

Publikováno v: 2019 International Conference on Document Analysis and Recognition (ICDAR)
2019 International Conference on Document Analysis and Recognition (ICDAR), Sep 2019, Sydney, Australia. pp.1384-1389, ⟨10.1109/ICDAR.2019.00223⟩
ICDAR

International audience; In this paper, a novel local threshold binarization method using fast Fuzzy C-Means clustering is proposed. Historical document images with non-uniform background, stains, faded ink are first processed by removing the backgrou

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b897727fffc904cc5783f25504d8333c
https://hal.archives-ouvertes.fr/hal-02555586

Zobrazit plný text záznamu

Watercolor, segmenting images using connected color components

Autor: Petra Gomez-Krämer, Sebastien Eskenazi, Jean-Marc Ogier

Publikováno v: International Conference on Pattern Recognition
International Conference on Pattern Recognition, Aug 2018, Beijing, China
ICPR

International audience; In the context of document security systems, there is a growing need for a stable segmentation method. State-of-the-art document image segmentation methods are not stable as they use several parameters and thresholds such as b

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b8511238ef4e1d5427796760d7e0f8e5
https://hal.archives-ouvertes.fr/hal-01900022/document

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání