Robust Anomaly Detection Using Reflectance Transformation Imaging for Surface Quality Inspection
International audience We propose a novel methodology for the detection and analysis of visual anomalies on challenging surfaces (metallic). The method is based on a local assessment of the reflectance across the inspected surface, using Reflectance Transformation Imaging data: a set of luminance im...
Main Authors: | , , , , , , |
---|---|
Other Authors: | , , , , , , , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2017
|
Subjects: | |
Online Access: | https://u-bourgogne.hal.science/hal-01564972 https://doi.org/10.1007/978-3-319-59126-1_46 |
id |
ftunigrenoble:oai:HAL:hal-01564972v1 |
---|---|
record_format |
openpolar |
spelling |
ftunigrenoble:oai:HAL:hal-01564972v1 2024-09-15T18:39:17+00:00 Robust Anomaly Detection Using Reflectance Transformation Imaging for Surface Quality Inspection Pitard, Gilles Goïc, Gaëtan Le Mansouri, Alamin Favreliere, Hugues Pillet, Maurice George, Sony Hardeberg, Jon Yngve The Norwegian Colour and Visual Computing Laboratory Norwegian University of Science and Technology Gjøvik (NTNU) Norwegian University of Science and Technology (NTNU)-Norwegian University of Science and Technology (NTNU) Imagerie et Vision Artificielle Dijon (ImViA) Université de Bourgogne (UB) Laboratoire d'Electronique, d'Informatique et d'Image EA 7508 (Le2i) Université de Technologie de Belfort-Montbeliard (UTBM)-Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM) Arts et Métiers Sciences et Technologies HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Arts et Métiers Sciences et Technologies HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Centre National de la Recherche Scientifique (CNRS) Laboratoire SYstèmes et Matériaux pour la MEcatronique (SYMME) Université Savoie Mont Blanc (USMB Université de Savoie Université de Chambéry ) Tromso, Norway 2017-06-12 https://u-bourgogne.hal.science/hal-01564972 https://doi.org/10.1007/978-3-319-59126-1_46 en eng HAL CCSD Springer International Publishing info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-319-59126-1_46 hal-01564972 https://u-bourgogne.hal.science/hal-01564972 doi:10.1007/978-3-319-59126-1_46 Image Analysis Scandinavian Conference on Image Analysis SCIA 2017 https://u-bourgogne.hal.science/hal-01564972 Scandinavian Conference on Image Analysis SCIA 2017, Jun 2017, Tromso, Norway. pp.550-561, ⟨10.1007/978-3-319-59126-1_46⟩ https://link.springer.com/chapter/10.1007%2F978-3-319-59126-1_46 Anomaly detection Metallic surfaces Reflectance RTI [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing info:eu-repo/semantics/conferenceObject Conference papers 2017 ftunigrenoble https://doi.org/10.1007/978-3-319-59126-1_46 2024-07-29T23:39:57Z International audience We propose a novel methodology for the detection and analysis of visual anomalies on challenging surfaces (metallic). The method is based on a local assessment of the reflectance across the inspected surface, using Reflectance Transformation Imaging data: a set of luminance images captured by a fixed camera while varying light spatial positions. The reflectance, in each pixel, is modelled by means of a projection of the measured luminances onto a basis of geometric functions, in this case, the Discrete Modal Decomposition (DMD) basis. However, a robust detection and analysis of surface visual anomalies requires that the method must not be affected neither by the geometry (sensor and surface orientation) nor by the texture pattern orientation of the inspected surface. We therefore introduce a rotation-invariant representation on the DMD, from which we devise saliency maps representing the local differences on reflectances. The methodology is tested on different engineering metallic samples exhibiting several types of defects. Compared to other saliency assessments, the results of our methodology demonstrate the best performance regarding anomaly detection, localisation and analysis. Conference Object Tromso Tromso Université Grenoble Alpes: HAL 550 561 |
institution |
Open Polar |
collection |
Université Grenoble Alpes: HAL |
op_collection_id |
ftunigrenoble |
language |
English |
topic |
Anomaly detection Metallic surfaces Reflectance RTI [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing |
spellingShingle |
Anomaly detection Metallic surfaces Reflectance RTI [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing Pitard, Gilles Goïc, Gaëtan Le Mansouri, Alamin Favreliere, Hugues Pillet, Maurice George, Sony Hardeberg, Jon Yngve Robust Anomaly Detection Using Reflectance Transformation Imaging for Surface Quality Inspection |
topic_facet |
Anomaly detection Metallic surfaces Reflectance RTI [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing |
description |
International audience We propose a novel methodology for the detection and analysis of visual anomalies on challenging surfaces (metallic). The method is based on a local assessment of the reflectance across the inspected surface, using Reflectance Transformation Imaging data: a set of luminance images captured by a fixed camera while varying light spatial positions. The reflectance, in each pixel, is modelled by means of a projection of the measured luminances onto a basis of geometric functions, in this case, the Discrete Modal Decomposition (DMD) basis. However, a robust detection and analysis of surface visual anomalies requires that the method must not be affected neither by the geometry (sensor and surface orientation) nor by the texture pattern orientation of the inspected surface. We therefore introduce a rotation-invariant representation on the DMD, from which we devise saliency maps representing the local differences on reflectances. The methodology is tested on different engineering metallic samples exhibiting several types of defects. Compared to other saliency assessments, the results of our methodology demonstrate the best performance regarding anomaly detection, localisation and analysis. |
author2 |
The Norwegian Colour and Visual Computing Laboratory Norwegian University of Science and Technology Gjøvik (NTNU) Norwegian University of Science and Technology (NTNU)-Norwegian University of Science and Technology (NTNU) Imagerie et Vision Artificielle Dijon (ImViA) Université de Bourgogne (UB) Laboratoire d'Electronique, d'Informatique et d'Image EA 7508 (Le2i) Université de Technologie de Belfort-Montbeliard (UTBM)-Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM) Arts et Métiers Sciences et Technologies HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Arts et Métiers Sciences et Technologies HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Centre National de la Recherche Scientifique (CNRS) Laboratoire SYstèmes et Matériaux pour la MEcatronique (SYMME) Université Savoie Mont Blanc (USMB Université de Savoie Université de Chambéry ) |
format |
Conference Object |
author |
Pitard, Gilles Goïc, Gaëtan Le Mansouri, Alamin Favreliere, Hugues Pillet, Maurice George, Sony Hardeberg, Jon Yngve |
author_facet |
Pitard, Gilles Goïc, Gaëtan Le Mansouri, Alamin Favreliere, Hugues Pillet, Maurice George, Sony Hardeberg, Jon Yngve |
author_sort |
Pitard, Gilles |
title |
Robust Anomaly Detection Using Reflectance Transformation Imaging for Surface Quality Inspection |
title_short |
Robust Anomaly Detection Using Reflectance Transformation Imaging for Surface Quality Inspection |
title_full |
Robust Anomaly Detection Using Reflectance Transformation Imaging for Surface Quality Inspection |
title_fullStr |
Robust Anomaly Detection Using Reflectance Transformation Imaging for Surface Quality Inspection |
title_full_unstemmed |
Robust Anomaly Detection Using Reflectance Transformation Imaging for Surface Quality Inspection |
title_sort |
robust anomaly detection using reflectance transformation imaging for surface quality inspection |
publisher |
HAL CCSD |
publishDate |
2017 |
url |
https://u-bourgogne.hal.science/hal-01564972 https://doi.org/10.1007/978-3-319-59126-1_46 |
op_coverage |
Tromso, Norway |
genre |
Tromso Tromso |
genre_facet |
Tromso Tromso |
op_source |
Image Analysis Scandinavian Conference on Image Analysis SCIA 2017 https://u-bourgogne.hal.science/hal-01564972 Scandinavian Conference on Image Analysis SCIA 2017, Jun 2017, Tromso, Norway. pp.550-561, ⟨10.1007/978-3-319-59126-1_46⟩ https://link.springer.com/chapter/10.1007%2F978-3-319-59126-1_46 |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-319-59126-1_46 hal-01564972 https://u-bourgogne.hal.science/hal-01564972 doi:10.1007/978-3-319-59126-1_46 |
op_doi |
https://doi.org/10.1007/978-3-319-59126-1_46 |
container_start_page |
550 |
op_container_end_page |
561 |
_version_ |
1810483665722933248 |