Feature extraction is one of the major challenges in object recognition. Features that are extracted from one type of objects cannot always be used directly for a different type of objects, therefore limiting the performance of feature extraction. Having an automatic feature learning algorithm could be a big advantage for an object recognition algorithm. This research first introduces several improvements on a fully automatic feature construction method called Evolution COnstructed Feature (ECO-Feature). These improvements are developed to construct more robust features and make the training process more efficient than the original version. The main weakness of the original ECO-Feature algorithm is that it is designed only for binary classification and cannot be directly applied to multi-class cases. We also observe that the recognition performance depends heavily on the size of the feature pool from which features can be selected and the ability of selecting the best features. For these reasons, we have developed an enhanced evolutionary learning method for multi-class object classification to address these challenges. Our method is called Evolutionary Learning of Boosted Features (ECO-Boost). ECO-Boost method is an efficient evolutionary learning algorithm developed to automatically construct highly discriminative image features from the training image for multi-class image classification. This unique method constructs image features that are often overlooked by humans, and is robust to minor image distortion and geometric transformations. We evaluate this algorithm with a few visual inspection datasets including specialty crops, fruits and road surface conditions. Results from extensive experiments confirm that ECO-Boost performs closely comparable to other methods and achieves a good balance between accuracy and simplicity for real-time multi-class object classification applications. It is a hardware-friendly algorithm that can be optimized for hardware implementation in an FPGA for real-time embedded visual inspection applications.

Automated visual inspection is an emerging multi-disciplinary field with many challenges; it combines different aspects of computer vision, pattern recognition, automation, and control systems. There does not exist a large body of work dedicated to the design of generalized visual inspection systems; that is, those that might easily be made applicable to different product types. This is an important oversight, in that many improvements in design and implementation times, as well as costs, might be realized with a system that could easily be made to function in different production environments. <br /><br /> This thesis proposes a framework for generalizing and automating the design of the defect classification stage of an automated visual inspection system. It involves using an expandable set of features which are optimized along with the classifier operating on them in order to adapt to the application at hand. The particular implementation explored involves optimizing the feature set in disjoint sets logically grouped by feature type to keep search spaces reasonable. Operator input is kept at a minimum throughout this customization process, since it is limited only to those cases in which the existing feature library cannot adequately delineate the classes at hand, at which time new features (or pools) may have to be introduced by an engineer with experience in the domain. <br /><br /> Two novel methods are put forward which fit well within this framework: cluster-space and hybrid-space classifiers. They are compared in a series of tests against both standard benchmark classifiers, as well as mean and majority vote multi-classifiers, on feature sets comprised of just the logical feature subsets, as well as the entire feature sets formed by their union. The proposed classifiers as well as the benchmarks are optimized with both a progressive combinatorial approach and with an genetic algorithm. Experimentation was performed on true colour industrial lumber defect images, as well as binary hand-written digits. <br /><br /> Based on the experiments conducted in this work, it was found that the sequentially optimized multi hybrid-space methods are capable of matching the performances of the benchmark classifiers on the lumber data, with the exception of the mean-rule multi-classifiers, which dominated most experiments by approximately 3% in classification accuracy. The genetic algorithm optimized hybrid-space multi-classifier achieved best performance however; an accuracy of 79. 2%. <br /><br /> The numeral dataset results were less promising; the proposed methods could not equal benchmark performance. This is probably because the numeral feature-sets were much more conducive to good class separation, with standard benchmark accuracies approaching 95% not uncommon. This indicates that the cluster-space transform inherent to the proposed methods appear to be most useful in highly dependant or confusing feature-spaces, a hypothesis supported by the outstanding performance of the single hybrid-space classifier in the difficult texture feature subspace: 42. 6% accuracy, a 6% increase over the best benchmark performance. <br /><br /> The generalized framework proposed appears promising, because classifier performance over feature sets formed by the union of independently optimized feature subsets regularly met and exceeded those classifiers operating on feature sets formed by the optimization of the feature set in its entirety. This finding corroborates earlier work with similar results [3, 9], and is an aspect of pattern recognition that should be examined further.

A inspeção visual automática é uma tarefa importante para a produtividade industrial. Ela pode ser aplicada em controle de qualidade para substituir operadores humanos em trabalhos perigosos ou repetitivos. O estágio de classificação em controle de qualidade da produção industrial é freqüentemente baseado no conhecimento humano. Portanto, torna-se importante alimentar um sistema visual automático com dados nebulosos ou ambíguos. Um sistema \"neuro-fuzy\" é uma forma adequada de implementar isto. O trabalho contribui na área tecnológica de inspeção visual com o desenvolvimento de uma nova abordagem para avaliação da qualidade de placas de madeira utilizadas na fabricação de lápis. Outra contribuição foi a divisão do vetor de características, fazendo com que cada característica específica seja tratada em uma rede neural própria. O método é baseado em duas redes neurais, cada uma tratando com apenas uma característica de entrada. Os resultados das redes neurais são combinados através de lógica nebulosa (\"fuzzy) fornecendo um sistema com maior poder discriminante do que aqueles que utilizam métodos tradicionais. O sistema se caracteriza por ser ágil, repetitivo, com um padrão de classificação definido e por possuir baixo custo. / Automatic visual inspection is an important task for industrial productivity. It could be applied for quality control or for replacing manual work under dangerous or repetitive activity. The classification stage in quality control of the industrial production is often based on the human knowledge. It seems, therefore, to be a great concern to supply an automated visual inspection system with fuzzy or ambiguous data. The Neuro-Fuzzy system is a good way to do this. The objective of this work is to develop a new approach for the classification of wooden plates used in the pencil production. This new method is based on two neural networks, each one working with just an input feature. The results of neural networks are combined through fuzzy logic giving the system a greater discriminating power than those that use traditional methods. The proposed method is characterized by being agile, repetitive, with a defined classification pattern and having low cost.

Automated visual inspection is an emerging multi-disciplinary field with many challenges; it combines different aspects of computer vision, pattern recognition, automation, and control systems. There does not exist a large body of work dedicated to the design of generalized visual inspection systems; that is, those that might easily be made applicable to different product types. This is an important oversight, in that many improvements in design and implementation times, as well as costs, might be realized with a system that could easily be made to function in different production environments. <br /><br /> This thesis proposes a framework for generalizing and automating the design of the defect classification stage of an automated visual inspection system. It involves using an expandable set of features which are optimized along with the classifier operating on them in order to adapt to the application at hand. The particular implementation explored involves optimizing the feature set in disjoint sets logically grouped by feature type to keep search spaces reasonable. Operator input is kept at a minimum throughout this customization process, since it is limited only to those cases in which the existing feature library cannot adequately delineate the classes at hand, at which time new features (or pools) may have to be introduced by an engineer with experience in the domain. <br /><br /> Two novel methods are put forward which fit well within this framework: cluster-space and hybrid-space classifiers. They are compared in a series of tests against both standard benchmark classifiers, as well as mean and majority vote multi-classifiers, on feature sets comprised of just the logical feature subsets, as well as the entire feature sets formed by their union. The proposed classifiers as well as the benchmarks are optimized with both a progressive combinatorial approach and with an genetic algorithm. Experimentation was performed on true colour industrial lumber defect images, as well as binary hand-written digits. <br /><br /> Based on the experiments conducted in this work, it was found that the sequentially optimized multi hybrid-space methods are capable of matching the performances of the benchmark classifiers on the lumber data, with the exception of the mean-rule multi-classifiers, which dominated most experiments by approximately 3% in classification accuracy. The genetic algorithm optimized hybrid-space multi-classifier achieved best performance however; an accuracy of 79. 2%. <br /><br /> The numeral dataset results were less promising; the proposed methods could not equal benchmark performance. This is probably because the numeral feature-sets were much more conducive to good class separation, with standard benchmark accuracies approaching 95% not uncommon. This indicates that the cluster-space transform inherent to the proposed methods appear to be most useful in highly dependant or confusing feature-spaces, a hypothesis supported by the outstanding performance of the single hybrid-space classifier in the difficult texture feature subspace: 42. 6% accuracy, a 6% increase over the best benchmark performance. <br /><br /> The generalized framework proposed appears promising, because classifier performance over feature sets formed by the union of independently optimized feature subsets regularly met and exceeded those classifiers operating on feature sets formed by the optimization of the feature set in its entirety. This finding corroborates earlier work with similar results [3, 9], and is an aspect of pattern recognition that should be examined further.

Present and future demonstrator designs were used to demonstrate the quality assurance of welds. The NDT methods tested on prototype demonstrator parts are: visual inspection, radius gauges, throat size gauge, liquid-penetrant testing, magnetic particle testing and ultrasonics with pulse echo and phased array. The other methods like eddy current, time of flight diffraction, radiography, impression test, macro test and infrared thermographs are currently being analyzed along with their inspection costs.   The control plans for present and future designs with corresponding present and future NDT methods are suggested to minimize a shift in process. Magnetic particle testing revealed a lack of fusion and cracks for fillet welds, whereas ultrasonic pulse echo and phased array identified an internal lack of fusion, inner pores/slag inclusions on butt welds. Ultrasonic PAUT &amp; TOFD could be used for accurate defect identification and thermography for online identification of lack of penetration, depth of penetration and weld parameters. / Weight reduction by improved weld quality (WIQ)

A majority of utilities conduct maintenance of transmission line components based on the results of routine visual inspection. The inspection is normally done by inspectors who detect defects by visually checking transmission line components either from the air (in helicopters), from the ground (by using high-powered binoculars) or from the top of the structure (by climbing the structure). The main problems with visual inspection of transmission lines are that the determination of the defects varies depending on the inspectors' knowledge and experience and that the defects are often reported qualitatively using vague and linguistic terms such as "medium crack", "heavy rust", "small deflection". As a result of these drawbacks, there is a large variance and inconsistency in defect reporting (which, in time, makes it difficult for the utility to monitor the condition of the components) leading to ineffective or wrong maintenance decisions. The use of inspection guides has not been able to fully address these uncertainties. This thesis reports on the application of a visual inspection methodology that is aimed at addressing the above-mentioned problems. A knowledge-based Fuzzy Inference System (FIS) is designed using Matlab's Fuzzy Logic Toolbox as part of the methodology and its application is demonstrated on utility visual inspection practice of porcelain cap and pin insulators. The FIS consists of expert-specified input membership functions (representing various insulator defect levels), output membership functions (indicating the overall conditions of the insulator) and IF-THEN rules. Consistency in the inspection results is achieved because the condition of the insulator is inferred using the same knowledge-base in the FIS rather than by individual inspectors. The output of the FIS is also used in a mathematical model that is developed to suggest appropriate component replacement date. It is hoped that the methodology that is introduced in this research will help utilities achieve better maintenance management of transmission line assets.

abstract: In recent years, solar photovoltaic (PV) industry has seen lots of improvements in technology and of growth in market with crystalline silicon PV modules being the most widely used technology. Plant inspections are gaining much importance to identify and quantitatively determine the impacts of various visual defects on performance. There are about 86 different types of defects found in the PV modules installed in various climates and most of them can be visually observed. However, a quantitative determination of impact or risk of each of identified defect on performance is challenging. Thus, it is utmost important to quantify the risk for each of the visual defects without any human subjectivity. The best way to quantify the risk of each defect is to perform current-voltage measurements of the defective modules installed in the plant but it requires disruption of plant operation, expensive measuring equipment and intensive human resources. One of the most riskiest and dominant visual defects is encapsulant browning which affects the PV module performance in the form of current degradation. The present study deals with developing an automated image processing tool which can address the issues of human subjectivity on browning level impacting performance. The image processing tool developed in this work can be directly used to quantify the impact of browning on performance without intrusively disconnecting the modules from the plant. In this work, the quantified browning level impact on performance has also been experimentally validated through a correlation study using short-circuit current and reflectance/transmittance measurements of browned PV modules retrieved from aged plants/systems installed in diverse climatic conditions. The primary goal of the image processing tool developed in this work is to determine the performance impact of encapsulant browning without interrupting the plant operation for I-V measurements. The use of image processing tool provides a single numerical value, called browning index (BI), which can accurately quantify browning levels on modules and also correlate with the performance and reflectance/transmittance parameters of the modules. / Dissertation/Thesis / Masters Thesis Mechanical Engineering 2016

A inspeção visual automática é uma tarefa importante para a produtividade industrial. Ela pode ser aplicada em controle de qualidade para substituir operadores humanos em trabalhos perigosos ou repetitivos. O estágio de classificação em controle de qualidade da produção industrial é freqüentemente baseado no conhecimento humano. Portanto, torna-se importante alimentar um sistema visual automático com dados nebulosos ou ambíguos. Um sistema \"neuro-fuzy\" é uma forma adequada de implementar isto. O trabalho contribui na área tecnológica de inspeção visual com o desenvolvimento de uma nova abordagem para avaliação da qualidade de placas de madeira utilizadas na fabricação de lápis. Outra contribuição foi a divisão do vetor de características, fazendo com que cada característica específica seja tratada em uma rede neural própria. O método é baseado em duas redes neurais, cada uma tratando com apenas uma característica de entrada. Os resultados das redes neurais são combinados através de lógica nebulosa (\"fuzzy) fornecendo um sistema com maior poder discriminante do que aqueles que utilizam métodos tradicionais. O sistema se caracteriza por ser ágil, repetitivo, com um padrão de classificação definido e por possuir baixo custo. / Automatic visual inspection is an important task for industrial productivity. It could be applied for quality control or for replacing manual work under dangerous or repetitive activity. The classification stage in quality control of the industrial production is often based on the human knowledge. It seems, therefore, to be a great concern to supply an automated visual inspection system with fuzzy or ambiguous data. The Neuro-Fuzzy system is a good way to do this. The objective of this work is to develop a new approach for the classification of wooden plates used in the pencil production. This new method is based on two neural networks, each one working with just an input feature. The results of neural networks are combined through fuzzy logic giving the system a greater discriminating power than those that use traditional methods. The proposed method is characterized by being agile, repetitive, with a defined classification pattern and having low cost.

This study examines the automatization potential for two production lines at Scania Transmission workshop in Södertälje using Industry 4.0 technologies. In order to do so, the capabilities of the operational performance and safety features of cobots and an Automated Visual Inspection System is theoretically investigated and intended to substitute CNC operators on certain tasks such as loading of conveyors and quality controls. The purpose of the study is to generate a realistic approach and give insight to the benefits of a future practical implementation.Previous research around these technologies as well as the actual data recordings and several interviews that took place during on-site visits is presented. The results show that a significant amount of time can be saved and allocated differently. Based on the findings of the study, a layout for the cobots and AVIS placement is proposed, aiming for CNC operator’s better control over the critical parts of the production lines, thus contributing to a much more manageable workflow.

Title without typo: Visual Analysis of Within-Subject Data: A Comparison Within and Across Certification Levels The field of behavior analysis has relied on the visual inspection of data to draw conclusions about the effects of experimental manipulations on dependent variables (Baer, Wolf, & Risley, 1968; Baer, Wolf, & Risley 1987; Kazdin, 1982). Although previous researchers have consistently found low levels of interrater agreement when manipulating the statistical parameters of graphs (e.g., DeProspero & Cohen, 1979; Ottenbacher, 1986), research conducted by Kahng et al. (2010) disagrees with the finding that poor interrater agreement is common among applied behavior analysts. The purpose of the current study was to replicate and extend the findings of Kahng et al. In Experiment 1, Editors of several applied behavior analysis journals and BCBA-Ds provided a dichotomous response and numerical rating to the question whether a set of simulated ABAB graphs displayed experimental. High levels of agreement were found for Experiment 1. In Experiment 2, Masters-level BCBAs were also asked to reply to a set of simulated ABAB graphs similar to those presented in Experiment 1. Low levels of agreement were found for Experiment 2. Additionally, In Experiment 3 the effects of multiple exemplar training on participant interrater agreement were examined. Improved performance across all three participants was observed. However, an increasing trend in responding was observed across baseline, training, and generalization suggesting repeated exposure to the ABAB graphs led to improvement. Taken together, the findings of Experiment 1 and Kahng et al. suggest that consistent analysis of intrasubject data is possible under certain circumstances.