This master thesis analyses the existing methods both practically and theoretically used to detect defected surface area in solar cells. Various methods were used but by using an upgraded CMOS camera without IR filter to implement the electroluminescence method, this has proven to have a very crucial impact on the results. Given the overall results and the acquired information, a procedure with a simple parameter can be setup to carry out the measurements. In addition to this a catalog was formed showing the defects occurring in mono and polycrystalline solar cells.

The goal of this work is to bring automatic defect detection to the manufacturing process of plastic cards. A card is considered defective when it is contaminated with a dust particle or a hair. The main challenges I am facing to accomplish this task are a very few training data samples (214 images), small area of target defects in context of an entire card (average defect area is 0.0068 \% of the card) and also very complex background the detection task is performed on. In order to accomplish the task, I decided to use Mask R-CNN detection algorithm combined with augmentation techniques such as synthetic dataset generation. I trained the model on the synthetic dataset consisting of 20 000 images. This way I was able to create a model performing 0.83 AP at 0.1 IoU on the original data test set.

Maintaining quality outcomes is an essential task for any manufacturing organization. Visual inspections have long been an avenue to detect defects in manufactured products, and recent advances within the field of deep learning has led to a surge of research in how technologies like convolutional neural networks can be used to perform these quality inspections automatically. An alternative to these often large and deep network structures is the modular neural network, which can instead divide a classification task into several sub-tasks to decrease the overall complexity of a problem. To investigate how these two approaches to image classification compare in a quality inspection task, a case study was performed at AR Packaging, a manufacturer of food containers. The many different colors, prints and geometries present in the AR Packaging product family served as a natural occurrence of complexity for the quality classification task. A modular network was designed, being formed by one routing module to classify variant type which is subsequently used to delegate the quality classification to an expert module trained for that specific variant. An image dataset was manually generated from within the production environment portraying a range of product variants in both defective and non-defective form. An image processing algorithm was developed to minimize image background and align the products in the pictures. To evaluate the adaptability of the two approaches, the networks were initially trained on same data from five variants, and then retrained with added data from a sixth variant. The modular networks were found to be overall less accurate and slower in their classification than the conventional single networks were. However, the modular networks were more than six times smaller and required less time to train initially, though the retraining times were roughly equivalent in both approaches. The retraining of the single network did also cause some fluctuation in the predictive accuracy, something which was not noted in the modular network. / <p>Det finns övrigt digitalt material (t.ex. film-, bild- eller ljudfiler) eller modeller/artefakter tillhörande examensarbetet som ska skickas till arkivet.</p>

Crack, a typical term most people know, is a common form of distress or damage in road pavements and railway sleepers. It poses significant challenges to their structural integrity, safety, and longevity. Over the years, researchers have developed various data-driven technologies for image-based crack detection in road and sleeper applications. The image-based crack detection has become a promising field.  Many researchers use ensemble learning to win the Road Damage Detection Challenge. The challenge provides a street view dataset from several countries from different perspectives. The version of the dataset is 2020, which contains images from Japan, India, and Czech. Thus, the dataset inherits a domain shift problem. Current solutions use ensemble learning to deal with such a problem. Those solutions require much computational power and challenge adaptability in real-time applications. To mitigate the problem, the thesis experiments with various data augmentation techniques that could improve the base model performance. The main focuses are erasing a crack from an image using generative AI (Erase), implementing road segmentation by using the Panoptic Segmentation (RS) and injecting a perspective-aware synthetic crack (InjectPa) into the segmented road surface in the image. The results show that compared to the base model, the Erase + RS techniques improve the model's F1 score when trained only on Japan in the dataset rather than when trained on three countries simultaneously. Moreover, the InjectPa technique does not help improve the base model in both scenarios. Then, the experiment moved to the SBB dataset containing close-up images of sleepers from cameras mounted in front of the diagnostic vehicle. This section follows the same techniques but changes the segmentation model to the Segment Anything Model (SAM) because the previous segmentation model was trained on a street view dataset, making it vulnerable to close-up images. The Erase + SAM techniques show improvement in bbox/AP and validation loss. Nevertheless, it does not improve the F1 score significantly compared to the base model.  This thesis also applies the explainable AI name D-RISE to determine which feature most influences the model decision. D-RISE shows that the augmentation model can pay attention to the damage type pothole for road pavements and defect type spalling for sleepers than other types. Finally, the thesis discusses the results and suggests a strategy for future study. / Sprickor, en typisk term som de flesta känner till, är en vänlig form av skador i vägbeläggningar och järnvägsslipers. Det innebär betydande utmaningar för strukturella integritet, säkerhet och livslängd. Under årens lopp har olika datadrivna tekniker utvecklats för bildbaserade sprickdetektering i vägbeläggningar och järnvägsslipers applikationer. Den bildbaserade sprickdetekteringen har blivit ett lovande område. Många forskare använder ensembleinlärningsmodeller för att vinna den Road Damage Detection Challenge (Vägbeläggningar Detektering Utmaning). Utmaningen ger en Gatuvy dataset från flera länder från olika perspektiv. Versionen av datasetet är 2020 som innehåller bilder från Japan, Indien och Tjeckien. Därför ärver datasetet  ett domänskiftproblem. Nuvarande lösningar använder ensembleinlärning för att hantera ett sådant problem. Dessa lösningar kräver mycket datorkraft och utmanar anpassningsförmågan i realtidsapplikationer. För att mildra problemet, denna avhandling prover många tekniker för dataökningar som kan förbättra basmodellens prestanda. Huvudfokusen är att radera en spricka från en bild via en generativ AI (Erase), implementera vägyta segmentering via den Panoptic Segmentation (RS), lägga en persective-aware syntetik spricka (InjectPa) till segmenterade vögytan in bilden. Resultaten visar att den Erase + RS ökningsteknikerna förbättrar modellens F1 score när den tränas på Japan i datasetet i stället för att tränas alla länder samtidigt. Dessutom förbättrar den InjectPa tekniken inte basmodellen på båda fallen.  Därefter flyttades experimentet till SBB-datasetet som innehåller närbilder av järnvägsslipers från kameror monterades framför ett diagnosfordon. Denna section följer de samma teknikerna men ändra segmentering modellen till den Segment Anything Model (SAM) eftersom förra segmentering modellen tränades på en Gatuvy dataset vilket gör den sårbar för närbilder. Den Erase + SAM ökningsteknikerna visar förbättringar på bbox/AP och validering. Ändå förbättrade den inte F1 score avsevört jämfört med basmodellen.  Denna avhandling tillämpar också Förklarbar AI-namnet D-RISE för att avgöra vilken funktion som mest påverkar modellbeslutet. D-RISE visar att modellen som har dataökning kan uppmärksamma skadetypen potthål för vägbeläggningar och defekttypen spjälkning för järnvägsslipers än andra typer. Slutligen diskuterar avhandlingen resultaten och föreslår en strategi för framtida arbetsinsatser.

Le Contrôle-Santé Intégré (CSI) réduit les besoins d’inspections humaines grâce à une surveillance automatisée, réduit les coûts de maintenance grâce à la détection précoce des anomalies avant qu’elles ne dégénèrent et améliore la sécurité ainsi que la fiabilité des services. L’objectif de cette thèse est de concevoir une plateforme de communication sans fil pour le CSI des structures ferroviaires. Le principe de contrôle repose sur la reconstruction des réponses impulsionnelles (fonctions de Green) par corrélation de bruit aléatoire se propageant dans le milieu. Durant ces travaux, nous avons éprouvé expérimentalement la relation entre les réponses actives expérimentales et une version post-traitée des fonctions de corrélation de bruit dans un contexte ferroviaire. Ainsi, nous avons démontré l’applicabilité des fonctions de corrélation pour la détection d’un défaut local sur un rail. Ensuite, nous avons réalisé une étude expérimentale comparative sur la caractérisation d’une transmission ZigBee en termes d’atténuation et de portée dans plusieurs environnements. Dans l’environnement ferroviaire sous test, nous avons démontré l’adéquation avec la portée d’une transmission ZigBee mono-saut (dans un rayon de 76m). Une solution de synchronisation des capteurs lors du prélèvement du signal basée sur la norme IEEE 802.15.4 a été proposée et validée par une campagne de mesures. Il a été démontré que cette approche offre une précision de l’ordre de quelques centaines de nanosecondes. Un prototype-plateforme de communication sans fil basé sur la technologie ZigBee/IEEE 802.15.4 a été mis en place et déployé sur un échantillon de rail. Cette solution a permis de valider les performances de cette plateforme, une fois les données récoltées par les transducteurs, ces informations sont transmises par un lien ZigBee vers une station de base où des algorithmes de détection leurs sont appliqués. / Structural Health Monitoring (SHM) reduces human inspection requirements through automated monitoring, reduces maintenance costs by early detection of defects before they escalate, and improves safety and reliability of services. The work presented in this thesis aims to design a wireless communication platform for railway structures health monitoring. The control principle is based on the reconstruction of impulse responses (Green’s functions) by correlation of random noise propagated in the medium. In this work, direct comparison between an active emission-reception response and the estimated noise correlation function has confirmed the validity of the equivalence relation between them. Thus, we have demonstrated the applicability of the correlation functions for local defect detection in a rail. Then, we conducted an experimental study on the characterization of a ZigBee transmission in terms of path loss and communication range in multiple environments. In the railway environment under test, we showed the adequacy with the range of a ZigBee single-hop transmission (within a radius of 76m). Furthermore, a flexible solution for sensors synchronization during the sampling process, based on IEEE 802.15.4 standard was proposed and validated by a measurement campaign. It has been demonstrated that this approach provides a precision of a few hundred nanoseconds. A wireless communication-platform prototype based on the ZigBee/IEEE 802.15.4 technology has been implemented and deployed on a rail sample. This solution enabled the validation of the platform performances, once the data collected by the transducers, the information is transmitted by a ZigBee link to a base station where detection algorithms are applied.

Until recent years, terahertz (THz) waves were an undiscovered, or most importantly, an unexploited area of electromagnetic spectrum. This was due to difficulties in generation and detection of THz waves. Recent advances in hardware technology have started to open up the field to new applications such as THz imaging. This non-destructive and non-contact imaging technique can penetrate through diverse materials such that internal structures, in some cases invisible to other imaging modalities, can be visualized. Today, there are variety of techniques available to generate and detect THz waves in both pulsed and continuous fashion in two different geometries; transition, and reflection modes. In this thesis continuous wave THz imaging was employed for higher spatial resolution. However, with any new technology comes its challenges; automated processing of THz images can be quite cumbersome. Low contrast and the presence of a widely unknown type of noise make the analysis of these images difficult. In this work, there is an attempt to detect defects in composite material via segmentation by using a Terahertz imaging system. According to our knowledge, this is the first time that this type of materials are being tested under Terahertz cameras to detect manufacturing defects in aerospace industry. In addition, segmentation accuracy of THz images have been investigated by using a phantom. Beyond the defect detection for composite materials, this can establish some general knowledge about Terahertz imaging, its capabilities and limitations. To be able to segment the THz images successfully, pre-processing techniques are inevitable. In this thesis, a variety of different image processing techniques, self-developed or available from literature, have been employed for image enhancement. These methods range from filtering to contrast adjustment to fusion of phase and amplitude images by using fuzzy set theory, to just name a few. The result of pre-procssing and segmentation methods demonstrates promising outcome for future work in this field.

Until recent years, terahertz (THz) waves were an undiscovered, or most importantly, an unexploited area of electromagnetic spectrum. This was due to difficulties in generation and detection of THz waves. Recent advances in hardware technology have started to open up the field to new applications such as THz imaging. This non-destructive and non-contact imaging technique can penetrate through diverse materials such that internal structures, in some cases invisible to other imaging modalities, can be visualized. Today, there are variety of techniques available to generate and detect THz waves in both pulsed and continuous fashion in two different geometries; transition, and reflection modes. In this thesis continuous wave THz imaging was employed for higher spatial resolution. However, with any new technology comes its challenges; automated processing of THz images can be quite cumbersome. Low contrast and the presence of a widely unknown type of noise make the analysis of these images difficult. In this work, there is an attempt to detect defects in composite material via segmentation by using a Terahertz imaging system. According to our knowledge, this is the first time that this type of materials are being tested under Terahertz cameras to detect manufacturing defects in aerospace industry. In addition, segmentation accuracy of THz images have been investigated by using a phantom. Beyond the defect detection for composite materials, this can establish some general knowledge about Terahertz imaging, its capabilities and limitations. To be able to segment the THz images successfully, pre-processing techniques are inevitable. In this thesis, a variety of different image processing techniques, self-developed or available from literature, have been employed for image enhancement. These methods range from filtering to contrast adjustment to fusion of phase and amplitude images by using fuzzy set theory, to just name a few. The result of pre-procssing and segmentation methods demonstrates promising outcome for future work in this field.

Este proyecto tiene como objetivo la implementación de algoritmos para la detección de defectos en las telas poliéster. Como sabemos, desde sus inicios la industria ha utilizado avances tecnológicos no sólo para optimizar los procesos de fabricación sino también para mejorar la calidad de los productos. Ahora, si bien, no es posible evitar las fallas que alteran la calidad de las telas poliéster, sí es posible su detección mediante una inspección visual dentro del proceso de fabricación. En el presente estudio se realizó algoritmos de procesamiento de imágenes mediante el uso de librerías del software LabView para la detección de defectos en las telas poliéster, basándonos en muestras de telas con manchas comunes (MC), manchas de aceite (MA) y puntadas erróneas (PE), las cuales nos permitieron realizar varias pruebas experimentales, utilizando un módulo de pruebas a pequeña escala el cual fue fabricado según el tamaño de las muestras de tela, con la utilización de la técnica de iluminación lateral doble, y basándonos en el análisis del histograma de la imagen original de las muestras de telas, se lograron obtener parámetros numéricos que permitieron la detección de manchas comunes, manchas de aceite y puntadas erróneas, basado en el histograma de cada imagen, el cual muestra la cantidad de píxeles (tamaño de imagen) y la intensidad que se encuentra comprendido en un rango de 0-255 (siendo 0 el valor mínimo y 255 el valor máximo), se logró parametrizar numéricamente cada rango de valores de detección para el caso de MC un rango de valores de intensidad de cada pixel, obteniendo como resultado un intervalo de detección para MC de 0-195 y para el caso de las MA obteniendo como resultado un intervalo de detección de 167-194, que ayudaron en la realización del algoritmo para cada tipo de defecto, que validaron lo planteado en un inicio en la presente investigación. This project takes the implementation of algorithms to detect faults in fabrics polyester. Now, though, it is not possible to avoid the faults that alter the quality of fabrics polyester, the detection is possible by means of a visual inspection of the product inside the manufacturing process. This study carried out algorithms of image processing through the use of libraries from LabView software for detection of defects in fabrics polyester, based on samples of fabrics with Common Stains (MC), Oil Stains (MA) and Erroneous Stitches (PE), which allowed us to carry out several experimental tests, using a module of small scale tests which was manufactured according to the size of the fabric samples , using the technique of double side lighting, and based on histogram analysis, we have managed to obtain parameters that allowed the detection of Common Stains, Oil Stains and Erroneous Stitches. In the case of common stains, was parameterized numerically every range of detection values for the case of MC a range of values of each pixel intensity, resulting in a detection interval for 0-195 MC and the case of the MA resulting in a 167-194 detection interval.

[...]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

Submitted by Fabio Sobreira Campos da Costa (fabio.sobreira@ufpe.br) on 2017-07-24T12:11:04Z No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) Dissertação Mestrado Paulo César de Oliveira.pdf: 2358509 bytes, checksum: 36436ca63e0a8098c05718bbee92d36e (MD5) / Made available in DSpace on 2017-07-24T12:11:04Z (GMT). No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) Dissertação Mestrado Paulo César de Oliveira.pdf: 2358509 bytes, checksum: 36436ca63e0a8098c05718bbee92d36e (MD5) Previous issue date: 2015-08-31 / Com a competitividade cada vez maior do mercado, aplicações de alto nível de qualidade são exigidas para a automação de um serviço. Para garantir qualidade de um software, testá-lo visando encontrar falhas antecipadamente é essencial no ciclo de vida de desenvolvimento. O objetivo do teste de software é encontrar falhas que poderão ser corrigidas e consequentemente, aumentar a qualidade do software em desenvolvimento. À medida que o software cresce, uma quantidade maior de testes é necessária para prevenir ou encontrar defeitos, visando o aumento da qualidade. Porém, quanto mais testes são criados e executados, mais recursos humanos e de infraestrutura são necessários. Além disso, o tempo para realizar as atividades de teste geralmente não é suficiente, fazendo com que os defeitos possam escapar. Cada vez mais as empresas buscam maneiras mais baratas e efetivas para detectar defeitos em software. Muitos pesquisadores têm buscado nos últimos anos, mecanismos para prever automaticamente defeitos em software. Técnicas de aprendizagem de máquina vêm sendo alvo das pesquisas, como uma forma de encontrar defeitos em módulos de software. Tem-se utilizado muitas abordagens supervisionadas para este fim, porém, rotular módulos de software como defeituosos ou não para fins de treinamento de um classificador é uma atividade muito custosa e que pode inviabilizar a utilização de aprendizagem de máquina. Neste contexto, este trabalho propõe analisar e comparar abordagens não supervisionadas e semisupervisionadas para detectar módulos de software defeituosos. Para isto, foram utilizados métodos não supervisionados (de detecção de anomalias) e também métodos semi-supervisionados, tendo como base os classificadores AutoMLP e Naive Bayes. Para avaliar e comparar tais métodos, foram utilizadas bases de dados da NASA disponíveis no PROMISE Software Engineering Repository. / Because the increase of market competition then high level of quality applications are required to provide automate services. In order to achieve software quality testing is essential in the development lifecycle with the purpose of finding defect as earlier as possible. The testing purpose is not only to find failures that can be fixed, but improve software correctness and quality. Once software gets more complex, a greater number of tests will be necessary to prevent or find defects. Therefore, the more tests are designed and exercised, the more human and infrastructure resources are needed. However, time to run the testing activities are not enough, thus, as a result, it causes escape defects. Companies are constantly trying to find cheaper and effective ways to software defect detection in earlier stages. In the past years, many researchers are trying to finding mechanisms to automatically predict these software defects. Machine learning techniques are being a research target, as a way of finding software modules detection. Many supervised approaches are being used with this purpose, but labeling software modules as defective or not defective to be used in training phase is very expensive and it can make difficult machine learning use. Considering that this work aims to analyze and compare unsupervised and semi-supervised approaches to software module defect detection. To do so, unsupervised methods (of anomaly detection) and semi-supervised methods using AutoMLP and Naive Bayes algorithms were used. To evaluate and compare these approaches, NASA datasets were used at PROMISE Software Engineering Repository.