[...]L’inspection des surfaces considérées est basée sur la technique d’Inspection par Particules Magnétiques (Magnetic Particle Inspection (MPI)) qui révèle les défauts de surfaces après les traitements suivants : la surface est enduite d’une solution contenant les particules, puis magnétisées et soumise à un éclairage Ultra-Violet. La technique de contrôle non destructif MPI est une méthode bien connue qui permet de révéler la présence de fissures en surface d’un matériau métallique. Cependant, une fois le défaut révélé par le procédé, ladétection automatique sans intervention de l’opérateur en toujours problématique et à ce jour l'inspection basée sur le procédé MPI des matériaux tubulaires sur les sites de production deVallourec est toujours effectuée sur le jugement d’un opérateur humain. Dans cette thèse, nous proposons une approche par vision artificielle pour détecter automatiquement les défauts à partir des images de la surface de tubes après traitement MPI. Nous avons développé étape par étape une méthodologie de vision artificielle de l'acquisition d'images à la classification.[...] La première étape est la mise au point d’un prototype d'acquisition d’images de la surface des tubes. Une série d’images a tout d’abord été stockée afin de produire une base de données. La version actuelle du logiciel permet soit d’enrichir la base de donnée soit d’effectuer le traitement direct d’une nouvelle image : segmentation et saisie de la géométrie (caractéristiques de courbure) des défauts. Mis à part les caractéristiques géométriques et d’intensité, une analyse multi résolution a été réalisée sur les images pour extraire des caractéristiques texturales. Enfin la classification est effectuée selon deux classes : défauts et de non-défauts. Celle ci est réalisée avec le classificateur des forêts aléatoires (Random Forest) dont les résultats sontcomparés avec les méthodes Support Vector Machine et les arbres de décision.La principale contribution de cette thèse est l'optimisation des paramètres utilisées dans les étapes de segmentations dont ceux des filtres de morphologie mathématique, du filtrage linéaire utilisé et de la classification avec la méthode robuste des plans d’expériences (Taguchi), très utilisée dans le secteur de la fabrication. Cette étape d’optimisation a été complétée par les algorithmes génétiques. Cette méthodologie d’optimisation des paramètres des algorithmes a permis un gain de temps et d’efficacité significatif. La seconde contribution concerne la méthode d’extraction et de sélection des caractéristiques des défauts. Au cours de cette thèse, nous avons travaillé sur deux bases de données d’images correspondant à deux types de tubes : « Tool Joints » et « Tubes Coupling ». Dans chaque cas un tiers des images est utilisé pour l’apprentissage. Nous concluons que le classifieur du type« Random Forest » combiné avec les caractéristiques géométriques et les caractéristiques detexture extraites à partir d’une décomposition en ondelettes donne le meilleur taux declassification pour les défauts sur des pièces de « Tool Joints »(95,5%) (Figure 1). Dans le cas des « coupling tubes », le meilleur taux de classification a été obtenu par les SVM avec l’analyse multirésolution (89.2%) (figure.2) mais l’approche Random Forest donne un bon compromis à 82.4%. En conclusion la principale contrainte industrielle d’obtenir un taux de détection de défaut de 100% est ici approchée mais avec un taux de l’ordre de 90%. Les taux de mauvaises détections (Faux positifs ou Faux Négatifs) peuvent être améliorés, leur origine étant dans l’aspect de l’usinage du tube dans certaines parties, « Hard Bending ».De plus, la méthodologie développée peut être appliquée à l’inspection, par MPI ou non, de différentes lignes de produits métalliques / Industrial surface inspection of tubular material based on Magnetic Particle Inspection (MPI) is a challenging task. Magnetic Particle Inspection is a well known method for Non Destructive Testing with the goal to detect the presence of crack in the tubular surface. Currently Magnetic Particle Inspection for tubular material in Vallourec production site is stillbased on the human inspector judgment. It is time consuming and tedious job. In addition, itis prone to error due to human eye fatigue. In this thesis we propose a machine vision approach in order to detect the defect in the tubular surface MPI images automatically without human supervision with the best detection rate. We focused on crack like defects since they represent the major ones. In order to fulfill the objective, a methodology of machine vision techniques is developed step by step from image acquisition to defect classification. The proposed framework was developed according to industrial constraint and standard hence accuracy, computational speed and simplicity were very important. Based on Magnetic Particle Inspection principles, an acquisition system is developed and optimized, in order to acquire tubular material images for storage or processing. The characteristics of the crack-like defects with respect to its geometric model and curvature characteristics are used as priory knowledge for mathematical morphology and linear filtering. After the segmentation and binarization of the image, vast amount of defect candidates exist. Aside from geometrical and intensity features, Multi resolution Analysis wasperformed on the images to extract textural features. Finally classification is performed with Random Forest classifier due to its robustness and speed and compared with other classifiers such as with Support Vector Machine Classifier. The parameters for mathematical morphology, linear filtering and classification are analyzed and optimized with Design Of Experiments based on Taguchi approach and Genetic Algorithm. The most significant parameters obtained may be analyzed and tuned further. Experiments are performed ontubular materials and evaluated by its accuracy and robustness by comparing ground truth and processed images. This methodology can be replicated for different surface inspection application especially related with surface crack detection

Orientador: João Antonio Pereira / Resumo: Visão de máquina é um campo multidisciplinar que vem crescendo na indústria, que está cada vez mais preocupada em reduzir custos, automatizar processos, e atender requisitos de qualidade do produto para atender seus clientes. Processos de montagem realizados de forma manual com inspeção e controle visual são tipicamente processos susceptíveis a erros, à utilização de peças não conformes na montagem do produto final. Este trabalho apresenta uma proposta de desenvolvimento de um sistema de visão de máquina com base no processamento e análise de imagens digitais para a inspeção das características e especificações das peças e componentes utilizados na montagem de capotas marítimas, objetivando verificar e garantir a conformidade do produto final. A inspeção e avaliação da conformidade do produto são feitas por etapas com a utilização de duas câmeras, uma captura a imagem do código de identificação alfanumérico do produto e a outra inspeciona o conjunto de elementos de fixação. As imagens passam por um processo de tratamento que envolve a filtragem espacial utilizando máscara de médias para suavização, alargamento de contraste para expandir a faixa de intensidades e segmentação para formação dos objetos de interesse. Uma função de OCR é utilizada para a extração de caracteres e reconhecimento do código do produto e a extração de características específicas do conjunto de componentes de fixação é feita por descritores de forma representados pelos invariantes de momento. As caracte... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: Machine vision is a growing multidisciplinary field in the industry that is increasingly concerned with reducing costs, automating processes, and meeting product quality requirements to serve its customers. Manual assembly processes with inspection and visual control are typically error-prone processes using non-conforming parts in the final product assembly. This work presents a proposal for the development of a machine vision system based on digital image processing and analysis for the inspection of the characteristics and specifications of the parts and components used in the assembly of marine bonnets, aiming to verify and ensure the conformity of the final product. Inspection and conformity assessment of the product are done in stages using two cameras, one capturing the image of the alphanumeric identification code of the product and the other inspecting the set of fasteners. The images undergo a treatment process that involves spatial filtering using averaging masks for smoothing, contrast widening to expand the range of intensities, and segmentation to form the objects of interest. An OCR function is used for character extraction and product code recognition, and the extraction of specific features of the fastener assembly is done by shape descriptors represented by the moment invariants. The specific characteristics of the fasteners are used to assess the conformity of the product with its respective code. The presentation of data and results of the implemented prop... (Complete abstract click electronic access below) / Mestre

<div>The manufacturing industry has begun its transition into a digital age, where data-driven decisions aim to improve product quality, output, and efficiency. Decisions made based on manufacturing data can help identify key problem areas in an assembly line and mitigate any defects from progressing through to the next step in the assembly process. But what if the products’ as manufactured data was inaccurate or didn’t exist at all? Decisions based on incorrect data can lead to defective parts being passed as good parts, costing manufacturers millions of dollars in rework or recalls. When specifically referring to mechanically fastened assemblies, products that experience rotation, like an aircraft propeller, or compress to create a seal, like an oil pipe flange, all require specific torque pattern sequences to be followed during assembly. When incorrectly torqued, the parts can have catastrophic failures resulting in consumer injury or ecological contamination. This paper outlines the development and feasibility of a system and its components for tracking and error-proofing the assembly of bolted joints in an industrial environment.</div><div>Using a machine vision system, the system traces the tool location relative to the mechanical fastener and records which order the fasteners were torqued in, if an error is detected, the system does not allow the user to progress through the assembly process, notifying if an error is detected. The system leverages open source machine learning algorithms from TensorFlow2 and OpenCv, that allow efficient object detection model training. The proposed system was tested using a series of tests and evaluated using the STEP method. The data collected aims to understand the system's feasibility and effectiveness in an industrial setting. </div><div>The tests aim to understand the effectiveness of the system under standard and variable industrial work conditions. Using the STEP method and other statistical analysis, an evaluation matrix was completed, ranking the system's ability to successfully meet all predetermined benchmarks and successfully record the torque pattern used to assemble apart</div>

The correct classification of a logs assortment is crucial for the economic output within a fully mechanized timber harvest. This task is especially for unexperienced but also for professional machine operators mentally demanding. This paper presents a method towards an assistance system for machine operators for an automated log quality and assortment estimation. Therefore, machine vision methods for object detection are combined with machine learning approaches for estimating the logs weight based on a Convolutional Neural Network (CNN). Based on the dimensions oft he object ´log, a first categorisation into a specific assortment is done. By comparing the theoretical weight of a healthy log of such dimensions to the real weight estimated by the CNN-based crane scale, quality reducing properties such as beetle infestation or red rod can be detected. In such cases, the assistance system displays a visual warning to the operator to check the loaded log.

This thesis issues with possible methods for face detection and localization according to the state of the art. It describes various approaches and it is aimed at localization by neural networks and at necessary operations that have to be done before localization and after that for correct results representation. This project contains implementation of few approaches to neural netwok based face localization with emphasis on eigenfaces based face localization as well as implementation of simple classifier using distance of reconstructed face to the original one. Detailed description of implemented system, achieved results and dependecy of system performance on it's inner settings is also provided.

This master's thesis is engaged in machine vision, methods of image processing and analysis. The reason is to create application to determine relative positions of Trilobot robots in the laboratory.

The field of computer vision offers tools that allow machines to derive meaningful infor-mation from video and images and consequently make decisions based on visual inputs. In the paper industry, implementation of machine vision (MV) can be used to automate and speed up processes that require visual inspection, particularly certain segments of quality control – one such application being detection and measurement of paper roll core eccentricity. Core eccentricity is a roll build error in which the roll core is offset from the geometric roll center, potentially causing runnability issues. This particular project aims to improve the detection of paper roll core eccentricity at the Mondi Dynäs integrated pulp and paper mill through creation, calibration and evaluation of a machine-vision-based tool for on-line core eccentricity measurement. The tool utilizes the Hough Transform (HT), since HT is a simple yet fast and robust algorithm when it comes to identification of basic shapes such as lines and circles. The proposed solution was evaluated in two ways; firstly by determining at what level of accuracy the measurements could be provided, accounting for how well the solution deals with correction of systematic error caused by environmental factors, and secondly by analyzing how well characteristic roll features could be accurately identified in large sets of data, necessary to consistently perform measurements. The evaluation of the proposed solution showed a 99.9% detection rate for characteristic paper roll features, and a 98.1% detection rate of laser lines used for correction of position and orientation induced error. Assessment of the measurement accuracy following successful detection was on par with the current optical measurement method, and the proposed solution was able to classify distinctive features with a 96.8% accuracy. Lastly, several improvement actions to address faulty detection were identified, and factors to be considered for future installment were highlighted.

Small and medium-sized enterprises are highly limited on resources for the transformation into smart factories. Nytt AB, a new startup specialized in smart manufacturing solutions, is completely focused on taking down the barriers with a basic solution: implementing a machine vision system with the purpose to monitor the machines of the factories. The main aim of this thesis is to analyze the data collected from two different machines of a medium-sized factory by monitoring the color states of the stack lights.First of all, some topics are analyzed in order to get a better understanding and knowledge of the main topic of this thesis: smart manufacturing. Secondly, the methodology used during the project is explained. Thirdly, the product developed by Nytt AB is described to get a better understanding. Together with this, the companies where the product is implemented are described. The next step is the presentation of the results by analyzing the data according to these parameters:(i), the availability of the machines, (ii), critical machine tool analysis; (iii),machine idling time; (iv), disruption events; and finally, (v), information transfer. In the results, some graphs and discussions are presented. In the following chapter the conclusions are presented, which allow the analyzed company to improve its current state. Lastly, the relocation of the product into the critical machine, the implementation of new sensors to detect temperature and vibration values of the machines and the implementation of the module OpApp within the factories are suggestions presented as future work at the end of this report. / Små och medelstora företag har mycket begränsade resurser för omvandling till smarta fabriker. Nytt AB, ett nystartat företag inom smart tillverkning, är helt fokuserad på att ta bort hinder med en enkel lösning: implementering av ett kamerasystem för övervakning av maskiner i fabriker. Huvudsyftet med detta examensarbete är att analysera data som samlats in från två olika maskiner i en medelstor fabrik genom att övervaka färgändringar i deras ljuspelare. För det första analyseras några ämnesområden för att få en bättre förståelse och kunskap om huvudtemat i detta examensarbete: smart tillverkning. För det andra förklaras den metod som används under projektet. För det tredje beskrivs den produkt som utvecklats av Nytt AB för att få en bättre förståelse. Tillsammans med detta beskrivs de företag där produkten implementeras. Nästa steg är presentationen av resultatet genom att analysera data enligt följande parametrar:(i), maskinens tillgänglighet; (ii), kritisk verktygsmaskinanalys; (iii), maskinens tomgångstid; (iv), störningshändelser och slutligen; (v), informationsöverföring. I resultatet presenteras några grafer och diskussioner. Slutsatserna presenteras därefter. Dessa slutsatser gör att det analyserade företaget kan förbättra sitt nuvarande tillstånd. Som framtida arbete föreslås slutligen flytt av kamerasystemet till den kritiska maskinen, införande av nya sensorer för att övervaka temperaturer och vibrationsvärden för maskinerna och implementeringav modulen OpApp i fabriker.

This thesis treats static and dynamic surface characterization using radiometric and Fourier optical methods. A Fourier optical method has been developed for real time image processing in paper production and printing applications. It has been shown that the method can be used to measure crepe frequency, an important parameter in tissue paper production, as well as to monitor the wire mark pattern at paper web velocities of up to 20 m/s. The wire mark pattern has been used to measure dimensional variations across a paper web. These are important for the mechanical properties of paper. Imaging of the moving surfaces onto a spatial light modulator, necessary for Fourier optical analysis of opaque objects, constitutes a motion blur problem. This problem has been solved by means of optical motion compensation using a rotating mirror. A rotating mirror system has also been developed for the inspection of small particles fixed to a rotating sample disc. The optical motion compensation configurations have made exposure times of more than two orders of magnitude longer than the exposure time without compensation possible. A light scattering model for opaque objects, for example coated paper, has also been developed and verified, with a coefficient of determination between theory and measurement ranging from r2=0.84 to r2=0.98, on various paper samples. The light scattering model has been used in the development of an instrument based on the photometric stereo principle. In this instrument the reflectance (or color) and topography of opaque samples are determined from two or more images of the sample illuminated from different directions. The method has been successfully used for studies of the relation between topography and print results in gravure and flexographic printing. Comparisons of surface height profiles measured with the photometric stereo method and profiles obtained with mechanical and optical scanning stylus instruments have shown coefficients of determination of up to r2=0.97. The main advantages of the method are the high speed, the scalability and the ability to obtain reflectance and surface height maps of a surface simultaneously.

Les systèmes de vision artificielle sont de plus en plus présents en contexte routier. Ils sont installés sur l'infrastructure, pour la gestion du trafic, ou placés à l'intérieur du véhicule, pour proposer des aides à la conduite. Dans les deux cas, les systèmes de vision artificielle visent à augmenter la sécurité et à optimiser les déplacements. Une revue bibliographique retrace les origines et le développement des algorithmes de vision artificielle en contexte routier. Elle permet de démontrer l'importance des descripteurs d'images dans la chaîne de traitement des algorithmes. Elle se poursuit par une revue des descripteurs d'images avec une nouvelle approche source de nombreuses analyses, en les considérant en parallèle des applications finales. En conclusion, la revue bibliographique permet de déterminer quels sont les descripteurs d'images les plus représentatifs en contexte routier. Plusieurs bases de données contenant des images et les données météorologiques associées (ex : pluie, brouillard) sont ensuite présentées. Ces bases de données sont innovantes car l'acquisition des images et la mesure des conditions météorologiques sont effectuées en même temps et au même endroit. De plus, des capteurs météorologiques calibrés sont utilisés. Chaque base de données contient différentes scènes (ex: cible noir et blanc, piéton) et divers types de conditions météorologiques (ex: pluie, brouillard, jour, nuit). Les bases de données contiennent des conditions météorologiques naturelles, reproduites artificiellement et simulées numériquement. Sept descripteurs d'images parmi les plus représentatifs du contexte routier ont ensuite été sélectionnés et leur robustesse en conditions de pluie évaluée. Les descripteurs d'images basés sur l'intensité des pixels ou les contours verticaux sont sensibles à la pluie. A l'inverse, le descripteur de Harris et les descripteurs qui combinent différentes orientations sont robustes pour des intensités de pluie de 0 à 30 mm/h. La robustesse des descripteurs d'images en conditions de pluie diminue lorsque l'intensité de pluie augmente. Finalement, les descripteurs les plus sensibles à la pluie peuvent potentiellement être utilisés pour des applications de détection de la pluie par caméra.Le comportement d'un descripteur d'images en conditions météorologiques dégradées n'est pas forcément relié à celui de la fonction finale associée. Pour cela, deux détecteurs de piéton ont été évalués en conditions météorologiques dégradées (pluie, brouillard, jour, nuit). La nuit et le brouillard sont les conditions qui ont l'impact le plus important sur la détection des piétons. La méthodologie développée et la base de données associée peuvent être utilisées à nouveau pour évaluer d'autres fonctions finales (ex: détection de véhicule, détection de signalisation verticale).En contexte routier, connaitre les conditions météorologiques locales en temps réel est essentiel pour répondre aux deux enjeux que sont l'amélioration de la sécurité et l'optimisation des déplacements. Actuellement, le seul moyen de mesurer ces conditions le long des réseaux est l'installation de stations météorologiques. Ces stations sont coûteuses et nécessitent une maintenance particulière. Cependant, de nombreuses caméras sont déjà présentes sur le bord des routes. Une nouvelle méthode de détection des conditions météorologiques utilisant les caméras de surveillance du trafic est donc proposée. Cette méthode utilise des descripteurs d'images et un réseau de neurones. Elle répond à un ensemble de contraintes clairement établies afin de pouvoir détecter l'ensemble des conditions météorologiques en temps réel, mais aussi de pourvoir proposer plusieurs niveaux d'intensité. La méthode proposée permet de détecter les conditions normales de jour, de nuit, la pluie et le brouillard. Après plusieurs phases d'optimisation, la méthode proposée obtient de meilleurs résultats que ceux obtenus dans la littérature, pour des algorithmes comparables. / Computer vision systems are increasingly being used on roads. They can be installed along infrastructure for traffic monitoring purposes. When mounted in vehicles, they perform driver assistance functions. In both cases, computer vision systems enhance road safety and streamline travel.A literature review starts by retracing the introduction and rollout of computer vision algorithms in road environments, and goes on to demonstrate the importance of image descriptors in the processing chains implemented in such algorithms. It continues with a review of image descriptors from a novel approach, considering them in parallel with final applications, which opens up numerous analytical angles. Finally the literature review makes it possible to assess which descriptors are the most representative in road environments.Several databases containing images and associated meteorological data (e.g. rain, fog) are then presented. These databases are completely original because image acquisition and weather condition measurement are at the same location and the same time. Moreover, calibrated meteorological sensors are used. Each database contains different scenes (e.g. black and white target, pedestrian) and different kind of weather (i.e. rain, fog, daytime, night-time). Databases contain digitally simulated, artificial and natural weather conditions.Seven of the most representative image descriptors in road context are then selected and their robustness in rainy conditions is evaluated. Image descriptors based on pixel intensity and those that use vertical edges are sensitive to rainy conditions. Conversely, the Harris feature and features that combine different edge orientations remain robust for rainfall rates ranging in 0 – 30 mm/h. The robustness of image features in rainy conditions decreases as the rainfall rate increases. Finally, the image descriptors most sensitive to rain have potential for use in a camera-based rain classification application.The image descriptor behaviour in adverse weather conditions is not necessarily related to the associated final function one. Thus, two pedestrian detectors were assessed in degraded weather conditions (rain, fog, daytime, night-time). Night-time and fog are the conditions that have the greatest impact on pedestrian detection. The methodology developed and associated database could be reused to assess others final functions (e.g. vehicle detection, traffic sign detection).In road environments, real-time knowledge of local weather conditions is an essential prerequisite for addressing the twin challenges of enhancing road safety and streamlining travel. Currently, the only mean of quantifying weather conditions along a road network requires the installation of meteorological stations. Such stations are costly and must be maintained; however, large numbers of cameras are already installed on the roadside. A new method that uses road traffic cameras to detect weather conditions has therefore been proposed. This method uses a combination of a neural network and image descriptors applied to image patches. It addresses a clearly defined set of constraints relating to the ability to operate in real-time and to classify the full spectrum of meteorological conditions and grades them according to their intensity. The method differentiates between normal daytime, rain, fog and normal night-time weather conditions. After several optimisation steps, the proposed method obtains better results than the ones reported in the literature for comparable algorithms.