Knot segmentation in 3D CT images of wet wood

Autor: Adrien Krähenbühl, Fleur Longuetaud, Bertrand Kerautret, Isabelle Debled-Rennesson, Frédéric Mothe
Přispěvatelé: Applying Discrete Algorithms to Genomics and Imagery (ADAGIO), Department of Algorithms, Computation, Image and Geometry (LORIA - ALGO), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Etudes des Ressources Forêt-Bois (LERFoB), Institut National de la Recherche Agronomique (INRA)-AgroParisTech, Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria), AgroParisTech-Institut National de la Recherche Agronomique (INRA)
Jazyk: angličtina
Rok vydání: 2014
Předmět:
Source code
[SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging
media_common.quotation_subject
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Scale-space segmentation
02 engineering and technology
[INFO.INFO-DM]Computer Science [cs]/Discrete Mathematics [cs.DM]
Curvature
Work related
ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.10: Image Representation/I.4.10.4: Volumetric
Knot (unit)
Segmentation
[SDV.SA.SF]Life Sciences [q-bio]/Agricultural sciences/Silviculture
forestry
Artificial Intelligence
Curvature estimators
ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.7: Feature Measurement/I.4.7.4: Size and shape
0202 electrical engineering
electronic engineering
information engineering
Wood knot
[INFO.INFO-IM]Computer Science [cs]/Medical Imaging
Computer vision
Mathematics
media_common
ComputingMethodologies_COMPUTERGRAPHICS
X-ray CT scanner
Parallelizable manifold
business.industry
Discrete geometry
020207 software engineering
Image segmentation
Mathematics::Geometric Topology
ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.6: Segmentation
[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]
Signal Processing
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
business
Software
Zdroj: Pattern Recognition
Pattern Recognition, Elsevier, 2014, 47 (12), pp.3852-3869. ⟨10.1016/j.patcog.2014.05.015⟩
Pattern Recognition, 2014, 47 (12), pp.3852-3869. ⟨10.1016/j.patcog.2014.05.015⟩
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2014.05.015⟩
Popis: International audience; This paper proposes a fully automatic method to segment wood knots from images obtained by an X-ray Computed Tomography scanner. Wood knot segmentation is known to be a difficult problem in the presence of sapwood because of the quite similar density of knots and wet sapwood. Classical segmentation techniques produce unsatisfactory results due to the very weak distinction between these two intensities. To overcome this limitation caused by physical characteristics, we propose to exploit the geometric properties of both the knot shapes and knot-sapwood interface. Based on previous work related to automatic knot detection, a new segmentation algorithm is proposed that uses a robust curvature estimation of 2D digital contours. The segmentation process is fast, easily parallelizable and produces better segmentation results than other state-of-the-art algorithms. It may be reproduced from the precise description given here or from source code available online.
Databáze: OpenAIRE
Externí odkaz: