Modern imaging modalities across many application domains increasingly acquire a large number of very high-dimensional measurements, commonly collecting hundreds to millions of variables per spatial resolution element. That high-dimensional nature can severely challenge traditional (often Euclidean distance based) approaches to noise and dimensionality reduction. Furthermore, statistical analysis of such data is often hampered by the curse of dimensionality, concomitant with large numbers of pixels and channels, by the growing abundance of low signal-to-noise ratio (SNR) measurements, and by the detrimental effects of noise accumulation. It is therefore necessary to find efficient means of reducing high-dimensional (and large data size) measurement sets to a lower-dimensional representation while incurring minimal information loss. Addressing this challenge is essential (a) to enable processing of the massively multivariate measurement sets acquired by several promising imaging technologies today (commonly hundreds of gigabytes to terabytes per experiment), (b) to avoid that computational analysis becomes a bottleneck for the development of new instrumental capabilities, with hardware setups theoretically capable of yielding terabyte to petabyte imaging but currently considered impractical, and (c) to enable archiving massively multivariate measurement sets, often required to be stored for several years and containing information suitable for additional science projects. This thesis focuses on this challenge specifically. First, it explores structured and regularized matrix decomposition methods based on the l1-norm, e.g. building on principal component pursuit (PCP), to address this challenge. Second, it delivers custom implementations of these methods. Third, it develops and implements an application-driven framework for automatic setting of hyperparameters. Finally, it applies and compares these methods using several spectral imaging case studies spanning both very small scales, in molecular imaging of organic tissue, as well as very large scales, in the spectroscopic imaging of Outer space.

Macro X-ray fluorescence (MA-XRF) is a recently developed technology allowing to obtain elemental information from cultural heritage objects. This information can, for example, be used to identify pigments used in a painting. Yet, the extended period of time it takes to scan an object is a major issue within MA-XRf. For instance, it took about 60 days to scan the Ghent Altarpiece. The long scanning time is a consequence of the necessary dwell time per pixel to create a robustly interpretable spectrum: the higher the dwell time, the higher the signalto-noise ratio (SNR), hence, the easier to detect elements. This thesis explores a possible solution for this problem using a denoising algorithm that increases the signal-to-noise ratio post-acquisition by exploiting the similarity between neighbouring pixels and spectra. To this end, a customized method of wavelet filter bank denoising is proposed. Current thresholding methods used in wavelet filter bank denoising are not suitable for filtering MA-XRF data, therefore, a novel thresholding method is introduced. Here, the widely used universal thresholding method is used as a basis, for which the formula for calculating the standard deviation of the detail coefficients of a channel is altered. Several design parameters of wavelet filter bank denoising were evaluated using a synthetic dataset, for which the performance quality indicators root mean square error (RMSE), mean absolute error (MAE) and SNR were determined. The parameters for which we optimized were the mother wavelet, the number of decomposition levels, and the number of neighbouring channels used for determining the standard deviation σ for thresholding. Good performance was obtained with the haar, db2, and coif1 wavelets, all at 3 levels of decomposition. A suitable number of neighbouring channels depended on the decomposition level and was determined to be 3 (on each side of the channel). Herewith, the signal-to-noise ratio was improved for both the average pixel spectra and the sum spectrum. The filtered synthetic dataset simulated to have a dwell time of 0.5 seconds had a SNR approximately equal to the raw synthetic dataset simulated to have a dwell time of 0.75 seconds. Hence, the algorithm succeeded in lowering the necessary dwell time. A case study of a daguerreotype was used to test the proposed denoising algorithm.

Linear Parameter-Varying (LPV) systems can be used as a bridge to extend the well studied model based control methods of Linear Time-Invariant systems to certain nonlinear systems. Despite significant attention in literature over the last two decades, finding an efficient global state space identification algorithm remains an open problem. Furthermore, a common assumption has been that the scheduling signals governing the time-varying dynamics are known or measured exactly. These drawbacks are found to inhibit the number of use cases for model based LPV control. This thesis explores new ways of identifying LPV systems for more general nonlinear systems with limited information on the optimal scheduling variable and scheduling dimension. To this end, two novel rank constrained least squares problems are presented to identify system matrices and scheduling signals from input and full state measurements, and a dictionary of possible scheduling signals. The use of the methods is demonstrated in a simulation experiment, and the results are compared to existing full state measurement methods. At last, the full state measurement methods are coupled with a state sequence estimation method from literature in order to obtain a method for identification of quasi-LPV systems from Input-Output measurements. Here "quasi" indicates that the scheduling signal is dependent on the system state and input. The scheme is flexible, and a proof of concept is given on a small nonlinear system.

The study of tumor microenvironments (TMEs) and immune cell composition in cancer, a disease characterized by uncontrolled growth and spread of tumor cells, has become increasingly important for understanding tumor progression and patient outcomes. Tools such as the TME-Analyzer enable this kind of research, but their manual workflows highlight a common problem in medical imaging: the scarcity of labeled data. This limits the efficiency and applicability of supervised learning algorithms to improve such medical image analysis tools. Self-supervised learning algorithms offer a promising alternative by learning feature representations without requiring labeled data. This thesis aims to address the issue of label scarcity by exploring the potential of self-supervised learning models for TME analysis involving the classification of individual cells in multiplex immunofluorescence (MxIF) microscopy images of triple-negative breast cancer (TNBC) tissue. To enable the learning of feature representations from MxIF images with an arbitrary number of color channels, this thesis proposes to pre-train an encoder network on every image channel separately according to the SimCLR algorithm and perform classification of multi-channel images by feeding the concatenated feature representation outputs of every channel to a classifier network — referred to as the Siamese configuration. A hyperparameter search is conducted to optimize the SimCLR encoder’s ability to learn high-quality feature representations of individual cells in MxIF images of TNBC tissue. Upon obtaining an optimal set of hyperparameters, the effectiveness of the learned feature representations in improving label-efficiency for individual cell classification is assessed. The results demonstrate that the proposed Siamese configuration improves the accuracy of classifying the inflammation status of TNBC tumor sections by 2.63%. Additionally, the optimal set of hyperparameters identified through the search include the use of the normalized temperature cross-entropy loss function with low temperature and an added image intensity thresholding term, as well as zoom and brightness/contrast augmentations. Furthermore, the optimized self-supervised learning model improves label-efficiency for individual cell classification, maintaining performance with only 40% of labeled data, while performance drops only when the label percentage is reduced below this threshold.

Knowledge on adversaries during military missions at sea heavily influences decision making, making identification of unknown vessels an important task. Identification of surrounding vessels based on visual data offers an alternative to AIS information (Automatic Identification System), the current standard in vessel identification, which can be spoofed. One visual approach employs human expertise and manually identifies vessels guided by a ship catalog. In order to minimize or potentially eliminate human error and performance limitations, there is strong interest in developing an automated vessel classification pipeline. One such pipeline is currently being developed at TNO, capable of classifying over 500 separate classes. A crucial part of the classification pipeline is retrieving an accurate contour of a vessel from a digital image. To address this important challenge, this thesis proposes an advanced deep learning pipeline to automatically segment the vessel image into background (e.g. sky and sea) and the object of interest (a vessel). Deep learning models based on Fully Convolutional Neural Networks (FCNs) have achieved high performance on the task of semantic segmentation. Several networks such as CRF-RNN, PSPNet, DeepLab and Mask R-CNN are employed to determine a baseline performance. We will focus on identifying the cause of poor or failing segmentations and aim to construct a robust network capable of handling these challenges. By sampling disturbances, caused by ship distance and camera noise, augmented data sets are built to tune networks to input from on-site images. Additionally, experiments are done to evaluate the influence of different levels of disturbances. Previous approaches implementing the CRF-RNN network achieved top 1 and top 5 classification accuracies of 31.1% and 44.0% respectively. Employing the DeepLab network, trained to convergence on artificial noise augmented data, we report top 1 and top 5 accuracy of 68.9% and 88.8% respectively. Additionally, implementing an ensemble of classifiers, performance is increased to 73.0% and 91.7% for top 1 and top 5 accuracy respectively. This best result is comparable to the classification results with human annotated ship silhouettes. The human performance accuracy is 73.4% on top 1, and 91.3% on top 5 classification performance. Finally, we show that training on a collection of different levels of image disturbances results in a network that is robust against increasing disturbance in images, while retaining performance on clean images.

Multivariate images are built up by measuring multiple features or variables simultaneously while recording a measurement’s location. An example of such images is Imaging Mass Spectrometry (IMS) data. IMS is a technique for recording the mass-over-charge ratio of molecules in (biological) samples while also recording the molecules’ spatial location. High dimensionality in multivariate images (e.g. many recorded features per pixel) often makes direct human interpretation infeasible and computational analysis impractical. For this reason, unsupervised and data-driven factorization is often applied prior to any exploration of the data, with the goal of reducing its dimensionality. However, one of the more promising factorization methods for multivariate images, Maximum Autocorrelation Factorization (MAF), still depends on some input from the user. Unlike most factorization methods, that focus solely on the spectral content of the observations, MAF also utilizes the spatial structure of the input data to generate matrix factors that try to capture both spatial and spectral patterns in the data. The factors of MAF represent the content of a matrix, ranked according to spatial autocorrelation, i.e. how rapidly they vary spatially. The idea for application of MAF in a bioimaging context is that naturally occurring, signals tend to form larger, more uniform areas and therefore change more slowly spatially, compared to noisy, non-biological measurement patterns. Since MAF factors are ordered according to autocorrelation, noisy measurement (with low autocorrelation) tend to get demoted in the order of factors, effectively separating them from biological data components (with positive autocorrelation). The goal of this thesis is to build upon the MAF algorithm and remove the current need for user input, making an extension of MAF. This novel factorization method is named Extended Maximum Autocorrelation Factorization (EMAF). Similarly to MAF, EMAF is invariant to linear transformations, utilizes spatial and spectral information of the dataset to determine its factors, and produces uncorrelated factors at all distances under certain conditions. The EMAF algorithm is fully unsupervised and produces factors ranked according to spatial autocorrelation. Unlike MAF, EMAF does not unnecessarily promote spatial artifacts oriented in one particular direction over other directions. The exact formulation of EMAF, derivations of the mentioned traits, and practical examples of EMAF are found in the following thesis. Preliminary experiments show that EMAF returns factors of improved quality compared to MAF.

Retrieving actionable information from large datasets is increasingly computationally expensive due to the current trend of ever-increasing dataset sizes. Reducing dataset sizes with dimensionality reduction techniques is often necessary for statistical analysis techniques, such as classification, to be computationally feasible. Most dimensionality reduction methods do not require any additional information to accomplish their task. However, datasets used for classification, for example, are accompanied by a set of class-labels as well. This extra information can improve dimensionality reduction techniques by explicitly preserving features that explain differences between classes. A field where high-dimensional and large datasets are standard is Imaging Mass Spectrometry (IMS), a technique that simultaneously records the abundance and spatial location of molecules throughout biological tissue samples. Classification has been applied to IMS datasets for a wide range of scenarios, including the diagnosis of disease, distinguishing between tumour types for personalized treatment, and identifying biomarkers. A recently introduced dimensionality reduction method called Soft Discriminant Map (SDM), designed to incorporate class information and prevent overfitting when used on high-dimensional datasets, is a promising candidate to reduce the size and dimensionality of IMS datasets. However, SDM currently requires manual setting of a free parameter β that influences class separation in the newly constructed feature-space. This thesis explores the use of SDM on IMS datasets in classification use cases and proposes a framework to set β in a data-driven way: Data-Driven Soft Discriminant Map (DD-SDM). Furthermore, the sensitivity of the classification performance to changes in β is examined. DD-SDM is compared to similar state-of-the-art dimensionality reduction methods in terms of classification performance. The performed experiments show that DD-SDM successfully finds a value for β where the classification performance is on par with, or in some scenarios better than, state-of-the-art dimensionality reduction methods while using fewer features. Setting β either too low or too high results in a suboptimal feature space and worsens classification performance. Golden section search, the search strategy used to find the optimal β in DD-SDM, succeeds in finding the optimal β in fewer iterations than more naive methods. With the use of an artificial dataset in combination with a novel evaluation metric, the Peak Conservation Score (PCS), the distinctive ability of DD-SDM to discard features that are common between classes and to actively select for discriminative features is demonstrated. The DD-SDM framework is furthermore applied to real-world IMS measurements of rat brain and mouse kidney tissue.

This MSc thesis presents the development of a viewpoint optimization framework to face the problem of detecting occluded fruits in autonomous harvesting. A Deep Reinforcement Learning (DRL) algorithm is developed in order to train a robotic manipulator to navigate to occlusion-free viewpoints of the tomato-target. Two Convolutional Neural Networks (CNN), You Only Look Once (YOLO) version 3 and Mask Regional Convolutional Neural Network (Mask R-CNN), are trained and evaluated in order to obtain visual information from the tomatoes. The two trained CNN achieve high detection accuracy and surpass other fruit detection methods. The instance segmentation Mask R-CNN result and an image processing algorithm are applied in an occlusion modelling method. The vision-based reward formulation for the DRL algorithm is closely related to the occlusion modelling metric. The DRL algorithm is trained and evaluated in a simulation environment by mounting a camera on a robotic arm. The use of different reward scheme and exploration strategy during DRL training shows their effect on training performance. The DRL training performance is assessed by illustrating the maximum visible tomato-target fraction per episode, the steps needed per episode, the trajectory of the robot's end-effector, and the initial and final tomato-target viewpoint in each episode. The evaluation results show a satisfactory performance, which depends on the reward and exploration strategy, as in the majority of the cases the robot can fully see the tomato-target after a few steps.

Imaging Mass Spectrometry (IMS) is a powerful technique capable of extracting unlabeled spatial and chemical information from a biological tissue sample. Ever-increasing technological advancements have resulted in rapid growth of IMS data set sizes, scaling quadratically with the increasingly refined spatial resolution of its ion images. Dimensionality reduction techniques aim to make large data sets practically approachable by reducing the number of dimensions in the data while retaining as much information as possible. Nonlinear Dimensionality Reduction (NLDR) methods attempt to uncover an underlying nonlinear manifold or structure in the data by constructing a Low-Dimensional (LD) feature space with variables that are nonlinear combinations of the original features (i.e. mass-to-charge ratio (m/z) bins in IMS measurements). The t-Distributed Stochastic Neighbor Embedding (t-SNE) has been a common approach in NLDR methods, using force-directed graphs. Uniform Manifold Approximation and Projection (UMAP) works in a similar manner, but leans on a more versatile mathematical foundation in topology, is generally faster, and the method tends to scale better than t-SNE. In this thesis, we introduce UMAPLUS, an extension of UMAP that takes not only spectral, but also spatial information into account. Our experiments show that UMAPLUS is capable of extracting the structure of a synthetic IMS data set better than UMAP. Besides UMAP’s standard spectral and random initializations, we introduce a new spatial initialization that provides more intuitive insight into the LD embedding relative to the spatial image domain. Standard UMAP entails several parameters that influence consistency, reliability, and quality of its LD embedding. Thus far, the influence of these parameters on IMS data sets has been barely investigated, and previous studies have consistently applied the default settings of UMAP. In this thesis, a Data-Driven UMAP (DD-UMAP) is constructed, which includes optimization of UMAP parameters in a data-driven manner. Several distance metrics are investigated, with cosine similarity providing the most robust results. A naive 1-D optimization procedure is compared to a multivariate Bayesian optimization approach, capable of optimizing multiple parameters simultaneously. Using an evaluation function partly based on the cost function of UMAP and the addition of spatial information, DD-UMAP is able to estimate and utilize an optimized input parameter set for UMAP in an unsupervised manner and on unlabeled IMS data sets. This is demonstrated on generated synthetic data, and two real world IMS data sets; a full mouse pup and a murine kidney.

The Shack-Hartmann wavefront sensor is a widely-used device to measure the light wavefront. Cur- rently, the sensor is used as a gradient sensor, which is achieved by placing the microlens array in the plane conjugate to the deformable mirror and the aberration. The resulting spot pattern is then transformed into a gradient through the use of centroiding: the measurement of the relative movement of all spots compared to the reference image. As an alternative to the traditional alignment, alternative alignment moves the Shack-Hartmann wave- front sensor: the CCD is now optically conjugated to the deformable mirror and the aberrations, and not the gradients but the curvature of the wavefront is measured. This changes the behaviour of the Shack-Hartmann sensor: instead of the amount of spots remaining the same and the CCD region oc- cupied by them changing, the amount of spots starts to change but the CCD region occupied by them remains the same in the face of aberrations. Curvature measurements can be used directly to actuate bimorph and membrane deformable mirrors, bypassing the need for complex control schemes. As an alternative to centroiding Fourier demodulation can also be used to convert the information measured by the wavefront sensor into gradients. For large aberrations where the spots stray out of their subapertures and the centroiding algorithm breaks down this method is especially suited. In this thesis it is shown that a synergy exists between alternative alignment and Fourier demodulation. Large aberrations no longer occupy a huge region on the CCD, instead changing the amount of spots, and the movement of the spots outside of their subapertures is no longer a problem as there is no need for rigidly defined subapertures. The combined use of alternative alignment and Fourier demodulation was tested on simulations, both for square and circular apertures, and for cases with extra added Poisson noise. Finally real-life experi- ments were also conducted using circular apertures.

Convolutional Neural Networks (CNNs) have emerged primarily from research focusing on image classification tasks and as a result, most of the well-motivated design choices found in literature are relevant to computer vision applications. CNNs' application on Imaging Mass Spectrometry (IMS) data is quite recent and involves new challenges, such as taking into account their unique structure (e.g. both spatial and spectral dimensions). In this thesis, we suggest a 1-D CNN architecture that extracts local features along the spectral dimension. The aim is to investigate if CNNs improve the classification accuracy compared to other classic Machine Learning (ML) methods such as linear models. Furthermore, we explore Neural Networks (NNs) that employ the novel Sharpened Cosine Similarity (SCS) as a feature extraction method, opposed to convolution. We call those networks SCS-NN in correspondence to the Convolutional-NN (CNN). To evaluate these methods, we implement our pipeline for various IMS datasets, with different characteristics and classification tasks, using several performance metrics such as balanced accuracy and F1 score. Moreover, we provide a detailed description of the methodology pipeline used for the CNN architecture design. The suggested methodology is the Tree-structured Parzen Estimator (TPE) algorithm, a Bayesian optimization technique for automated architecture selection. By implementing TPE, we manage to explore and exploit efficiently a complex and large hyperparameter configuration space and automatically select optimal hyperparameters (such as number of convolutional layers, kernel size, strides, learning rates etc.). This automated approach reduces time consumption, errors, and the need for specialized knowledge in biology and biochemistry that would be associated with manual design. In addition to developing a pipeline for designing, training and evaluating a CNN for IMS data classification, we also apply a model agnostic interpretation methodology based on SHapley Additive exPlanations (SHAP) and provide SHAP score maps that visualize the importance of features in the spatial dimension of the IMS datacube. In this thesis, we present and analyse the automated selection of 1-D CNN architectures for IMS data classification based on the TPE algorithm. Furthermore, we investigate a novel alternative to convolution, SCS, and evaluate its strengths and weaknesses in IMS data classification. The experimental results show that the TPE-generated CNN architectures outperform all the other applied classifiers. Finally, our interpretation of the CNN models reveals that accuracy performance alone might not be a sufficient criterion to trust the model's output.

One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training. It can be treated as a Network Compression problem on the architecture parameters from an overparameterized network. However, there are two issues associated with most one-shot NAS methods. First, dependencies between a node and its predecessors and successors are often disregarded which result in improper treatment over zero operations. Second, architecture parameters pruning based on their magnitude is questionable. In this thesis, classic Bayesian learning approach is applied to alleviate these two issues. Unlike other NAS methods, we train the over-parameterized network for only one epoch before update network architecture. Impressively, this enabled us to find the optimal architecture in both proxy and proxyless tasks on CIFAR-10 within only 0.2 GPU days using a single GPU. As a byproduct, our approach can be transferred directly to convolutional neural networks compression by enforcing structural sparsity that is able to achieve extremely sparse networks without accuracy deterioration.

The ability to locate specific objects within images is an essential step in various computer vision based engineering applications. Image segmentation is the task of dividing an image into "segments" that are uniform as well as homogeneous with respect to some characteristics, for example grey tone or texture as in Haralick et al. This thesis seeks to perform image segmentation using a Deep Learning (DL) approach in the area of warehouse automation, specifically focusing on an order picking use case of Vanderlande Industries (VI). Generally in literature, DL algorithms for image segmentation are split into two main classes: algorithms for RGB images and algorithms for RGB-D images. RGB stands for the Red, Green, and Blue values of a pixel. RGB-D stands for the Red, Green, Blue, and Depth values of a pixel. The depth value in this case differs from the RGB values in that it does not give a value for a colour intensity, but rather it gives a value for physical distance between the camera and the object it is capturing. The challenge addressed by this thesis focuses on whether the introduction of depth data results in a substantially better performance than using RGB-only images, based on a data-set provided by VI. Also, this thesis looks into the maximum allowed deviation along the X-axis in the registration of the depth data to the RGB images. Two networks from literature were investigated and implemented in MATLAB for this purpose: the SegNet architecture proposed by Badrinarayanan et al. and the FuseNet architecture proposed by Hazirbas et al. Through experiments we have found that, for this use case, the introduction of complementary depth data leads to an improvement over the use of RGB-only images. We also find that, for this use case, the maximum allowed deviation along the X-axis in the registration of the depth data to the RGB images is approximately equal to 1.67 millimetres. The results in this thesis seem to indicate that investing in acquiring an additional depth band does have a positive effect on the accuracy of image segmentation for order picking in warehouse automation.

Specular light reflections are the mirror-like reflections from a material interface. They appear in the observation of any illuminated surface. Specular reflections can be set apart from the diffuse reflection type, which has a random distribution of reflection directions. The radiance of the specular reflected light is governed by the Fresnel ratio and depends on both geometrical and spectral properties. A clear distinction can be made between the reflection properties of dielectric and the much more reflective non-dielectric material types. In certain cases the presence of specular reflections is useful, for example in object identification or computer graphics applications. However, often the presence of specular reflection causes bright spots on the image of an object, which results in loss of detail in these areas. Particularly in computer vision applications it is important to only observe the intrinsic diffuse reflection. Hence, a variety of specular reflection removal methods have been developed. Color-space analysis specular reflection removal methods are able to accurately recover the intrinsic diffuse color of the image of an object. Optimization based methods based on a non-negative matrix factorization of the data are considered. The reduced characteristic representation of the data allows the specular and diffuse reflection component to be separated more easily. A multi-image approach is considered because it provides more available information on the intrinsic diffuse reflection component, which is typically a relatively weak signal for non-dielectric surface reflections. A specular reflection removal method is developed, that combines a new reflection model for colored illumination with a sparse Non-negative Matrix Factorization (NMF) optimization in a multi-image framework. The proposed method is evaluated on synthetic data and real data images of non-dielectric materials acquired conform the proposed reflection model.

Human joint admittance changes with numerous factors constituting the operational point. For large changes of the operational point, joint admittance can be identified using Linear Time-Varying methods on torque and angular position signals measured on human joints. Out of the available methods, the Skirt Decomposition method was selected due to its nonparametric structure and the limited number of a priori assumptions it makes. Its employment on the identification of human joint admittance was completely novel. The method was applied to a simulation model representing joint admittance and on experimental data measured from the wrist joint. In the experiment, the subjects were changing the applied torque to follow a desired trajectory, while the angle of the wrist was perturbed by the manipulator.With a properly designed multisine input, taking into consideration the speed and complexity of the time variation, a variance accounted for (VAF) close to 100 % was obtained in the simulation study on all the tested conditions. From the experiment, it was seen that the contribution of the time variation in the frequency domain was partially masked by the output noise. The noise level could be decreased by lowering the amplitude of the desired torque, and by removing the voluntary torque from the analyzed data. With a desired torque level ranging between 5% and 20%, and considering the bandwidth between 2 Hz and 20 Hz, the mean power of the output residuals in the frequency domain ranged between 16.2 and 27.1 for all the tested conditions. Furthermore, the time-varying dynamics retrieved from the system function showed a clear correlation with the desired torque trajectory.

The scientific analysis of historical paintings has been traditionally restricted to the analysis of paint cross-section samples. This invasive method provides extensive information but is inherently limited in scope due to the extreme heterogeneity of paintings. In the last decade, non-invasive spot analyses and spectral imaging methods have become increasingly widespread in cultural heritage science. Two of these methods are macroscopic X-ray fluorescence imaging spectroscopy (MA-XRF) and reflectance imaging spectroscopy (RIS). These methods allow for 2D-scanning the entire surface of a painting and provide complementary information on elemental and molecular composition and distribution of the paint. However, these methods are often used only for qualitative analysis of the paint based on relative distribution maps, revealing only limited information about the paint layer stratigraphy. This thesis is an exploration of a combined approach for quantitative analysis of paint composition and layer stratigraphy using MA-XRF and RIS. The research used a set of specially prepared paint samples of mixtures and multiple layer applications based on historically relevant pigments which were scanned using MA-XRF and RIS in the visible and Near IR range (400-2500 nm). The spectral data acquired were processed and analyzed in a variety of ways, including Non-negative Matrix Factorization, Non-Linear Least Square Fitting, among other methods; in an attempt to gather quantitative compositional and stratigraphic data. In these trials, using characteristic reflectance features in the visible range together with a comparison of highly and lightly absorbed X-ray fluorescence lines allowed for the identification and quantification of surface specific compounds related to the top paint layer. Further comparison of fluorescence lines and absorption features in the Near IR range provided a potential avenue for quantification of subsurface paint layers. The results confirm that the combination of these methods allows to reveal the paint stratigraphy. The project provides samples and data sets which may serve as the basis for the development of a robust algorithm to address this issue in the future.

Visual surveillance technologies are increasingly being used to monitor public spaces. These technologies process the recordings of surveillance cameras. Such recordings contain depictions of human actions such as "running", "waving", and "aggression". In the field of computer vision, automated detection of human actions in videos is known as action detection. Recently, deep learning models have been proposed for the task of action detection. Deep learning models for this task can be grouped into single-frame models and multi-frame models. Single-frame models detect actions using individual frames of videos whereas multi-frame models detect actions using sequences of frames. This thesis proposes to use multi-frame models as compared to single-frame models for action detection in surveillance videos. To compare multi-frame and single-frame models, we implement the ACT-detector. The ACT-detector is a deep learning model that takes as input a sequence of K frames and outputs tubelets (labeled sequences of bounding boxes). We train and evaluate ACT for various values of K on the VIRAT dataset. In our comparison, K=1 serves as the single-frame model and K>1 as the multi-frame models. When compared qualitatively, we find that multi-frame models have less missed detections. When compared quantitatively, we find that multi-frame models outperform single-frame models in performance measures such as classification accuracy, MABO, frame-mAP, and video-mAP. To assess whether the improvements of multi-frame models yield purely from the increased number of frames, or also from the temporal order encoded by those frames, we experiment with training multi-frame models on unordered sequences of frames, i.e., sequences for which the frames are shuffled in time. When compared qualitatively, we find that multi-frame models have less precise localization when trained on unordered sequences. When compared quantitatively, we find that multi-frame models perform worse when trained on unordered sequences, indicating that multi-frame models learn temporal dynamics of actions. Nevertheless, even when trained on unordered sequences, multi-frame models outperform single-frame models for action detection in surveillance videos.