Centre dedocumentation
scientifique

BuyTheDips : PathLoss for improved topology-preserving deep learning-based image segmentation / Minh On Vu Ngoc (2022)  

Public Titre : BuyTheDips : PathLoss for improved topology-preserving deep learning-based image segmentation Type de document : Article/Communication Auteurs : Minh On Vu Ngoc, Auteur ; Yizi Chen , Auteur ; Nicolas Boutry, Auteur ; Jonathan Fabrizio, Auteur ; Clément Mallet , Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2022 Projets : SODUCO / Perret, Julien Importance : 13 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] chemin le plus court, algorithme du [Termes IGN] fonction de perte [Termes IGN] image numérique [Termes IGN] proximité sémantique [Termes IGN] segmentation d'image Résumé : (auteur) Capturing the global topology of an image is essential for proposing an accurate segmentation of its domain. However, most of existing segmentation methods do not preserve the initial topology of the given input, which is detrimental for numerous downstream object-based tasks. This is all the more true for deep learning models which most work at local scales. In this paper, we propose a new topology-preserving deep image segmentation method which relies on a new leakage loss: the Pathloss. Our method is an extension of the BALoss [1], in which we want to improve the leakage detection for better recovering the closeness property of the image segmentation. This loss allows us to correctly localize and fix the critical points (a leakage in the boundaries) that could occur in the predictions, and is based on a shortest-path search algorithm. This way, loss minimization enforces connectivity only where it is necessary and finally provides a good localization of the boundaries of the objects in the image. Moreover, according to our research, our Pathloss learns to preserve stronger elongated structure compared to methods without using topology-preserving loss. Training with our topological loss function, our method outperforms state-of-the-art topology-aware methods on two representative datasets of different natures: Electron Microscopy and Historical Map. Numéro de notice : P2022-005 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Preprint nature-HAL : Préprint DOI : 10.48550/arXiv.2207.11446 En ligne : https://doi.org/10.48550/arXiv.2207.11446 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101338

Preface: the 2021 edition of the XXIVth ISPRS congress / Clément Mallet in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-1-2021 (July 2021)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-1-2021 (July 2021) . - pp 1 - 5 Titre : Preface: the 2021 edition of the XXIVth ISPRS congress Type de document : Article/Communication Auteurs : Clément Mallet , Auteur ; Florent Lafarge, Auteur ; Martyna Poreba , Auteur ; Teng Wu , Auteur ; Gaétan Bahl, Auteur ; Min Yu, Auteur ; Anatol Garioud , Auteur ; Yizi Chen , Auteur ; San Jiang, Auteur ; Michael Ying Yang, Auteur ; Nicolas Paparoditis , Auteur Année de publication : 2021 Projets : 1-Pas de projet / Perret, Julien Conférence : ISPRS 2021, Commission 1, XXIV ISPRS Congress, Imaging today foreseeing tomorrow 05/07/2021 09/07/2021 Nice on-line France OA Annals Commission 1 Article en page(s) : pp 1 - 5 Note générale : bibliographie Langues : Anglais (eng) Résumé : (auteur) We report key elements and figures related to the proceedings of the 2021 edition of the XXIVth ISPRS Congress. Similarly to 2020, the COVID-19 pandemic caused global travel challenges and restrictions for the first half of 2021. Consequently, the physical Congress re-scheduled from June 2020 to July 2021 was again postponed to June 2022, still in Nice (France). Papers were already submitted and the ISPRS Council decided to carry out the review process and the publication of the proceedings of the papers submitted under the label “2021 Edition”. The authors of published papers had the opportunity to present their work during a Digital Event, this year scheduled the same week as the planned Congress (5–9 July 2021). Numéro de notice : A2021-613 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/isprs-annals-V-4-2021-1-2021 Date de publication en ligne : 17/06/2021 En ligne : http://dx.doi.org/10.5194/isprs-annals-V-4-2021-1-2021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97948 [article]

Combining deep learning and mathematical morphology for historical map segmentation / Yizi Chen (2021)  

Public Titre : Combining deep learning and mathematical morphology for historical map segmentation Type de document : Chapitre/Contribution Auteurs : Yizi Chen , Auteur ; Edwin Carlinet, Auteur ; Joseph Chazalon, Auteur ; Clément Mallet , Auteur ; Bertrand Duménieu , Auteur ; Julien Perret , Auteur Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2021 Collection : Lecture notes in Computer Science, ISSN 0302-9743 num. 12708 Projets : SODUCO / Perret, Julien Conférence : DGMM 2021, 1st International Joint Conference on Discrete Geometry and Mathematical Morphology 24/05/2021 27/05/2021 Uppsala Suède Proceedings Springer Importance : pp 79 - 92 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] analyse diachronique [Termes IGN] apprentissage profond [Termes IGN] carte ancienne [Termes IGN] chaîne de traitement [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection d'objet [Termes IGN] données maillées [Termes IGN] morphologie mathématique [Termes IGN] vectorisation Résumé : (auteur) The digitization of historical maps enables the study of ancient, fragile, unique, and hardly accessible information sources. Main map features can be retrieved and tracked through the time for subsequent thematic analysis. The goal of this work is the vectorization step, i.e., the extraction of vector shapes of the objects of interest from raster images of maps. We are particularly interested in closed shape detection such as buildings, building blocks, gardens, rivers, etc. in order to monitor their temporal evolution. Historical map images present significant pattern recognition challenges. The extraction of closed shapes by using traditional Mathematical Morphology (MM) is highly challenging due to the overlapping of multiple map features and texts. Moreover, state-of-the-art Convolutional Neural Networks (CNN) are perfectly designed for content image filtering but provide no guarantee about closed shape detection. Also, the lack of textural and color information of historical maps makes it hard for CNN to detect shapes that are represented by only their boundaries. Our contribution is a pipeline that combines the strengths of CNN (efficient edge detection and filtering) and MM (guaranteed extraction of closed shapes) in order to achieve such a task. The evaluation of our approach on a public dataset shows its effectiveness for extracting the closed boundaries of objects in historical maps. Numéro de notice : H2021-001 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers HAL Thématique : GEOMATIQUE Nature : Chapître / contribution nature-HAL : ChOuvrScient DOI : 10.1007/978-3-030-76657-3_5 Date de publication en ligne : 16/05/2021 En ligne : https://hal.science/hal-03101578v1 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96739

ICDAR 2021 competition on historical map segmentation / Joseph Chazalon (2021)  

Public Titre : ICDAR 2021 competition on historical map segmentation Type de document : Article/Communication Auteurs : Joseph Chazalon, Auteur ; Edwin Carlinet, Auteur ; Yizi Chen , Auteur ; Julien Perret , Auteur ; Bertrand Duménieu , Auteur ; Clément Mallet , Auteur ; Thierry Géraud, Auteur ; Vincent Nguyen, Auteur ; Nam Nguyen, Auteur ; Josef Baloun, Auteur ; Ladislav Lenc, Auteur ; Pavel Král, Auteur Editeur : Le Kremlin Bicêtre : Ecole pour l'Informatique et les Techniques Avancées EPITA Année de publication : 2021 Projets : 1-Pas de projet / Perret, Julien Conférence : ICDAR 2021, 16th International Conference on Document Analysis and Recognition 05/09/2021 10/09/2021 Lausanne Suisse Proceedings Springer Importance : 15 p. Note générale : bibliographie Langues : Anglais (eng) Résumé : (auteur) This paper presents the final results of the ICDAR 2021 Competition on Historical Map Segmentation (MapSeg), encouraging research on a series of historical atlases of Paris, France, drawn at 1/5000 scale between 1894 and 1937. The competition featured three tasks, awarded separately. Task 1 consists in detecting building blocks and was won by the L3IRIS team using a DenseNet-121 network trained in a weakly supervised fashion. This task is evaluated on 3 large images containing hundreds of shapes to detect. Task 2 consists in segmenting map content from the larger map sheet, and was won by the UWB team using a U-Net-like FCN combined with a binarization method to increase detection edge accuracy. Task 3 consists in locating intersection points of geo-referencing lines, and was also won by the UWB team who used a dedicated pipeline combining binarization, line detection with Hough transform, candidate filtering, and template matching for intersection refinement. Tasks 2 and 3 are evaluated on 95 map sheets with complex content. Dataset, evaluation tools and results are available under permissive licensing at https://icdar21-mapseg.github.io/. Numéro de notice : C2021-022 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : https://hal.archives-ouvertes.fr/hal-03256193/document Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98032

Introducing the boundary-aware loss for deep image segmentation / Minh On Vu Ngoc (2021)  

Public Titre : Introducing the boundary-aware loss for deep image segmentation Type de document : Article/Communication Auteurs : Minh On Vu Ngoc, Auteur ; Yizi Chen , Auteur ; Nicolas Boutry, Auteur ; Joseph Chazalon, Auteur ; Edwin Carlinet, Auteur ; Jonathan Fabrizio, Auteur ; Clément Mallet , Auteur ; Thierry Géraud, Auteur Editeur : The British Machine Vision Association Press (BMVA) Année de publication : 2021 Projets : SODUCO / Perret, Julien Conférence : BMVC 2021, 32nd British Machine Vision Conference 22/11/2021 25/11/2021 online Royaume-Uni OA Proceedings Importance : 17 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] apprentissage profond [Termes IGN] classification barycentrique [Termes IGN] segmentation d'image Résumé : (auteur) Most contemporary supervised image segmentation methods do not preserve the initial topology of the given input (like the closeness of the contours). One can generally remark that edge points have been inserted or removed when the binary prediction and the ground truth are compared. This can be critical when accurate localization of multiple interconnected objects is required. In this paper, we present a new loss function, called, Boundary-Aware loss (BALoss), based on the Minimum Barrier Distance (MBD) cut algorithm. It is able to locate what we call the leakage pixels and to encode the boundary information coming from the given ground truth. Thanks to this adapted loss, we are able to significantly refine the quality of the predicted boundaries during the learning procedure. Furthermore, our loss function is differentiable and can be applied to any kind of neural network used in image processing. We apply this loss function on the standard U-Net and DC U-Net on Electron Microscopy datasets. They are well-known to be challenging due to their high noise level and to the close or even connected objects covering the image space. Our segmentation performance, in terms of Variation of Information (VOI) and Adapted Rank Index (ARI), are very promising and lead to 15% better scores of VOI and 5% better scores of ARI than the state-of-the-art. The code of boundary-awareness loss is freely available at https://github.com/onvungocminh/MBD_BAL Numéro de notice : C2021-054 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : https://www.bmvc2021-virtualconference.com/assets/papers/1546.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99411

Vectorization of historical maps using deep edge filtering and closed shape extraction / Yizi Chen (2021)  

Permalink