Automatic vectorization of historical maps: A benchmark.

Autor: Yizi Chen, Joseph Chazalon, Edwin Carlinet, Minh Ôn Vũ Ngoc, Clément Mallet, Julien Perret

Publikováno v: PLoS ONE, Vol 19, Iss 2, p e0298217 (2024)

Shape vectorization is a key stage of the digitization of large-scale historical maps, especially city maps that exhibit complex and valuable details. Having access to digitized buildings, building blocks, street networks and other geographic content

Externí odkaz: https://doaj.org/article/ed1acb3b329746a6a5a721dcfd21bee6

Estimation of the noise level function for color images using mathematical morphology and non-parametric statistics

Autor: Baptiste Esteban, Guillaume Tochon, Edwin Carlinet, Didier Verna

Publikováno v: 2022 26th International Conference on Pattern Recognition (ICPR).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::137d617fbf0a25a344c889a13888334c
https://doi.org/10.1109/icpr56361.2022.9956218

Vectorization of historical maps using deep edge filtering and closed shape extraction

Autor: Bertrand Duménieu, Edwin Carlinet, Joseph Chazalon, Yizi Chen, Julien Perret, Clément Mallet

Publikováno v: Proceedings of the 16th International Conference on Document Analysis and Recognition (ICDAR'21
16th International Conference on Document Analysis and Recognition (ICDAR'21)
16th International Conference on Document Analysis and Recognition (ICDAR'21), Sep 2021, Lausanne, Switzerland. pp.510-525, ⟨10.1007/978-3-030-86337-1_34⟩
Document Analysis and Recognition – ICDAR 2021 ISBN: 9783030863364
ICDAR (4)

International audience; Maps have been a unique source of knowledge for centuries. Such historical documents provide invaluable information for analyzing the complex spatial transformation of landscapes over important time frames. This is particularl

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::920772e7fc9d93a602c7bd2cc4c82f9f
https://hal.archives-ouvertes.fr/hal-03256073

Revisiting the Coco Panoptic Metric to Enable Visual and Qualitative Analysis of Historical Map Instance Segmentation

Autor: Edwin Carlinet, Joseph Chazalon

Publikováno v: Document Analysis and Recognition – ICDAR 2021 ISBN: 9783030863364
ICDAR (4)

Segmentation is an important task. It is so important that there exist tens of metrics trying to score and rank segmentation systems. It is so important that each topic has its own metric because their problem is too specific. Does it? What are the f

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::05ec35a0fee808f0740ef9a9cc794a72
https://doi.org/10.1007/978-3-030-86337-1_25

Left Atrial Segmentation in a Few Seconds Using Fully Convolutional Network and Transfer Learning

Autor: Yongchao Xu, Zhou Zhao, Younes Khoudli, Jérôme Lacotte, Elodie Puybareau, Edwin Carlinet, Thierry Géraud

Publikováno v: Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges---9th International Workshop, STACOM 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers
Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges---9th International Workshop, STACOM 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, pp.339-347, 2019, ⟨10.1007/978-3-030-12029-0_37⟩
Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges ISBN: 9783030120283
STACOM@MICCAI

In this paper, we propose a fast automatic method that segments left atrial cavity from 3D GE-MRIs without any manual assistance, using a fully convolutional network (FCN) and transfer learning. This FCN is the base network of VGG-16, pre-trained on

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::36332fdea838c030b2bacf20660d7dd6
https://hal.archives-ouvertes.fr/hal-02176449/file/geraud.2018.stacom_draft.pdf