0000000000135888
AUTHOR
Gaëtan Le Goïc
HD-RTI: an adaptive multi-light imaging approach for the quality assessment of manufactured surfaces
International audience; Reflectance Transformation Imaging (RTI) is a technique for estimating surface local angular reflectance from a set of stereo-photometric images captured with variable lighting directions. The digitization of this information fully fits into the industry 4.0 approach and makes it possible to characterize the visual properties of a surface. The proposed method, namely HD-RTI, is based on the coupling of RTI and HDR imaging techniques. This coupling is carried out adaptively according to the response at each angle of illumination. The proposed method is applied to five industrial samples which have high local variations of reflectivity because of their heterogeneity of…
Improving point matching on multimodal images using distance and orientation automatic filtering
International audience; Speed Up Robust Features SURF is one of the most popular and efficient methods used for image registration task. In order to achieve a correct registration, a good matching of feature point is required. However in the case of multimodal images, the high and non-linear intensity changes between different modalities led to many outliers (mismatching of detected points) and consequently a fail in the registration. Therefore, in this paper we introduce an efficient method devoted to the detection and removal of such outlier. It's based on an automatic filtering of outliers on both distance and orientation between features points. We tested our proposed method on a set of…
Germolles’ palace wall paintings: an interdisciplinary project for the rediscovery of a unique 14th century decoration
International audience
Système de détection d'anomalies d'aspect par la technique PTM
This documentation details the creation of a support system for the detecting visual sur- face anomalies . This work is based on a technique called Polynomial Texture Mapping (PTM). This technique allows to highlight appearance anomalies by varying the position of the light source. It also makes possible the calculation of the surface topography. This system was designed during the first quarter of 2011 in the SYMME laboratory (Laboratory for Materials and Mechatronics), and is a part of the European research program INTERREG IV. This program aims to enhance a strength of economic activity on both sides of the border France - Switzerland : the realization of high-value products (watches, au…
Flatness calibration of XY translation stages through modal parameterization
International audience; The issue of this document is to improve the metrological performances of XY translation stages of an optical profilometer Altisurf©. We propose a calibration protocol to correct the systematic geometrical errors, for example pitch and roll, related to geometrical errors of guiding system. It consists in measuring a flat glass with λ/10 (flatness ≈ 60 nm) and a very high precision optical sensor (u=0.06 μm). The correction surface is then parameterized by an original method of parameterization: the modal parameterization, to differentiate the systematic and random geometrical errors. The modal parameterization of a surface results from the Discrete Modal Decompositio…
PTMs developments for the appearance control on high-added value surfaces
International audience; In many areas of activity, the value of a product depends greatly on the perceived quality, including visual one. This work aims to better control sensory perception of products with high added value, especially on the first step of the visual control: the detection, or localization of anomalies in appearance to the surfaces. Companies have controllers, specially trained to locate and evaluate anomalies. These specialists have a higher sensitivity for the detection and evaluation of defects as a potential buyer for example, and this higher acuity is generally completed by a weighting of the intensity of defects according to their location. However, there is still gre…
Quality Assessment of Reconstruction and Relighting from RTI Images: Application to Manufactured Surfaces
In this paper, we propose to evaluate the quality of the reconstruction and relighting from images acquired by a Reflectance Transformation Imaging (RTI) device. Three relighting models, namely the PTM, HSH and DMD, are evaluated using PSNR and SSIM. A visual assessment of how the reconstructed surfaces are perceived is also carried out through a sensory experiment. This study allows to estimate the relevance of these models to reproduce the appearance of the manufactured surfaces. It also shows that DMD reproduces the most accurate reconstruction/relighting to an acquired measurement and that a higher sampling density don't mean necessarily a higher perceptual quality.
Benchmarking Saliency Detection Methods on Multimodal Image Data
Saliency detecmage processing. Most of the work is adapted to the specific application and available dataset. The present work is about a comparative analysis of saliency detection for multimodal images dataset. There were many researches on the detection of saliency on several types of images, such as multispectral, natural, 3D and so on. This work presents a first focused study on saliency detection on multimodal images. Our database was extracted from acquisitions on cultural heritage wall paintings that contain four modalities UV, IR, Visible and fluorescence. In this paper, the analysis has been performed for many methods on saliency detection. We evaluate the performance of each metho…
Geometric quality and appearance of surfaces : local and global approaches
Accounting for customers' perception of manufactured goods has become a major challenge for the industry. This process is to be established from early design to retail. Customers are nowadays more aware and detail oriented about perceived quality of products. This allows one to set not only an estimated price but also the expected quality of the product. Surface appearance analysis has therefore become a key industrial issue. Two approaches are proposed here to formalize the detection methodology and provide objective criteria for experts to evaluate surface anomalies. The first proposed approach is based on surface metrology. It consists in analyzing the measured topologies in order to bin…
3D objects descriptors methods: Overview and trends
International audience; Object recognition or object's category recognition under varying conditions is one of the most astonishing capabilities of human visual system. The scientists in computer vision have been trying for decades to reproduce this ability by implementing algorithms and providing computers with appropriate tools. Hence, several intelligent systems have been proposed. To act in this field, numerous approaches have been proposed. In this paper we present an overview of the current trend in 3D objects recognition and describe some representative state of the art methods, highlighting their limits and complexity.
Reflectance-based surface saliency
In this paper, we propose an original methodology allowing the computation of the saliency maps for high dimensional RTI data (Reflectance Transformation Imaging). Unlike most of the classical methods, our approach aims at devising an intrinsic visual saliency of the surface, independent of the sensor (image) and the geometry of the scene (light-object-camera). From RTI data, we use the DMD (Discrete Modal Decomposition) technique for the angular reflectance reconstruction, which we extend by a new transformation on the modal basis enabling a rotation-invariant representation of reconstructed reflectances. This orientation-invariance of the resulting reflectance shapes fosters a robust esti…
Multi-scale analysis of surface topographies by modal filtering
International audience; This work introduces an innovative method for the multi-scale analysis of surface topographies, which consists of applying a method based on a new parameterization. This kind of surface parameterization refers to natural modes of vibration, and is therefore named modal parameterization. It allows us to characterize the form, waviness and roughness defects of a surface. This parameterization opens up new fields of analysis, such as the appearance quality of surfaces. It is thereby possible to decompose a measured surface in a vector basis, of which vectors are represented by plane natural eigenmodes sorted by frequency and complexity. Different filtering operations ca…
SVM-based classification of High resolution Urban Satellites Images using Dense SURF and Spectral Information
Remote-sensing focusing on image classification knows a large progress and receives the attention of the remote-sensing community day by day. Combining many kinds of extracted features has been successfully applied to High resolution urban satellite images using support vector machine (SVM). In this paper, we present a methodology that is promoting a performed classification by using pixel-wise SURF description features combined with spectral information in Cielab space for the first time on common scenes of urban imagery. The proposed method gives a promising classification accuracy when compared with the two types of features used separately.
Improvement of multimodal images classification based on DSMT using visual saliency model fusion with SVM
Multimodal images carry available information that can be complementary, redundant information, and overcomes the various problems attached to the unimodal classification task, by modeling and combining these information together. Although, this classification gives acceptable classification results, it still does not reach the level of the visual perception model that has a great ability to classify easily observed scene thanks to the powerful mechanism of the human brain.
 In order to improve the classification task in multimodal image area, we propose a methodology based on Dezert-Smarandache formalism (DSmT), allowing fusing the combined spectral and dense SURF features extracted …
Vers une automatisation du contrôle visuel des produits
International audience; La "qualité esthétique" des produits occupe aujourd'hui une place de plus en plus importante dans la maîtrise de la qualité. Elle se pose en tout cas parfois comme un objectif supplémentaire à atteindre par l'entreprise pour améliorer et pérenniser les relations que celle-ci établit avec ses clients. Le contrôle qualité à mettre en place doit réduire autant que possible la subjectivité dans l'évaluation de ce type de qualité, cette subjectivité pouvant être à l'origine de désaccords entre l'entreprise et ses clients sur le niveau de qualité à obtenir. Nos précédents travaux ont jusqu'à présent visé à mieux formaliser les différentes étapes d'un contrôle visuel des pr…
Multiscale analyses and characterizations of surface topographies
International audience; This work studies multiscale analyses and characterizations of surface topographies from the engineering and scientific literature with an emphasis on production engineering research and design. It highlights methods that provide strong correlations between topographies and performance or topographies and processes, and methods that can confidently discriminate topographies that were processed or that perform differently. These methods have commonalities in geometric characterizations at certain scales, which are observable with statistics and measurements. It also develops a semantic and theoretical framework and proposes a new system for organizing and designating …
Multimodal Images Classification using Dense SURF, Spectral Information and Support Vector Machine
International audience; The multimodal image classification is a challenging area of image processing which can be used to examine the wall painting in the cultural heritage domain. In such classification, a common space of representation is important. In this paper, we present a new method for multimodal representation learning, by using a pixel-wise feature descriptor named dense Speed Up Robust Features (SURF) combined with the spectral information carried by the pixel. For classification of extracted features we have used support vector machine (SVM). Our database was extracted from acquisition on cultural heritage wall paintings that contain four modalities UV, Visible, IRR and fluores…
An automatic filtering algorithm for SURF-based registration of remote sensing images
International audience; The registration of remote sensing images has been often a necessary step for further analyses of images taken at different times, different viewing geometry or with different sensors. For this task there exists many approaches. This paper focuses on the feature-based category of image registration methods. Particularly, we propose an improvement of the SURF algorithm on the point matching step. Indeed, in order to achieve a correct registration, a good matching of feature point is required. However The presence of outliers lead to a fail in the registration. Therefore, in this paper, we introduce an efficient method devoted to the detection and removal of such outli…
Surface Reflectance: An Optical Method for Multiscale Curvature Characterization of Wear on Ceramic–Metal Composites
Surface gradient characterization by light reflectance (SGCLR) is used for the first time for multiscale curvature calculations and discrimination of worn surfaces on six damaged ceramic&ndash