No description available.

In this thesis, we focus on the problem of image classification and investigate how its performance can be systematically improved. Improving the performance of different computer vision methods has been the subject of many studies. While different studies take different approaches to achieve this improvement, in this thesis we address this problem by investigating the relevance of the statistics collected from the image. We propose a framework for gradually improving the quality of an already existing image descriptor. In our studies, we employ a descriptor which is composed the response of a series of discriminative components for summarizing each image. As we will show, this descriptor has an ideal form in which all categories become linearly separable. While, reaching this form is not possible, we will argue how by replacing a small fraction of these components, it is possible to obtain a descriptor which is, on average, closer to this ideal form. To do so, we initially identify which components do not contribute to the quality of the descriptor and replace them with more robust components. As we will show, this replacement has a positive effect on the quality of the descriptor. While there are many ways of obtaining more robust components, we introduce a joint feature selection problem to obtain image features that retains class discriminative properties while simultaneously generalising between within class variations. Our approach is based on the concept of a joint feature where several small features are combined in a spatial structure. The proposed framework automatically learns the structure of the joint constellations in a class dependent manner improving the generalisation and discrimination capabilities of the local descriptor while still retaining a low-dimensional representations. The joint feature selection problem discussed in this thesis belongs to a specific class of latent variable models that assumes each labeled sample is associated with a set of different features, with no prior knowledge of which feature is the most relevant feature to be used. Deformable-Part Models (DPM) can be seen as good examples of such models. These models are usually considered to be expensive to train and very sensitive to the initialization. Here, we focus on the learning of such models by introducing a topological framework and show how it is possible to both reduce the learning complexity and produce more robust decision boundaries. We will also argue how our framework can be used for producing robust decision boundaries without exploiting the dataset bias or relying on accurate annotations. To examine the hypothesis of this thesis, we evaluate different parts of our framework on several challenging datasets and demonstrate how our framework is capable of gradually improving the performance of image classification by collecting more robust statistics from the image and improving the quality of the descriptor. / <p>QC 20140506</p>

One of the most active research areas in computer vision is image classification. Although there have been many research efforts in this area, it remains a difficult problem, especially when the number of categories is large. Most of the previous work in image classification uses low-level image features. We believe low-level features ignore a lot of the semantic structures of the image classes. In this thesis, we go beyond simple low-level features and propose new approaches for constructing mid-level visual features for image classification. We represent an image using the outputs of a collection of binary classifiers. These binary classifiers are trained to differentiate pairs of object classes in an object hierarchy. Our feature representations implicitly capture the hierarchical structure in object classes. We show that our proposed approach outperforms other baseline methods in image classification.

Learning discriminative feature representations has attracted a great deal of attention since it is a critical step to facilitate the subsequent classification, retrieval and recommendation tasks. In this dissertation, besides incorporating prior knowledge about image labels into the image classification as most prevalent feature learning methods currently do, we also explore some other general-purpose priors and verify their effectiveness in the discriminant feature learning. As a more powerful representation can be learned by implementing such general priors, our approaches achieve state-of-the-art results on challenging benchmarks. We elaborate on these general-purpose priors and highlight where we have made novel contributions. We apply sparsity and hierarchical priors to the explanatory factors that describe the data, in order to better discover the data structure. More specifically, in the first approach we propose that we only incorporate sparse priors into the feature learning. To this end, we present a support discrimination dictionary learning method, which finds a dictionary under which the feature representation of images from the same class have a common sparse structure while the size of the overlapped signal support of different classes is minimised. Then we incorporate sparse priors and hierarchical priors into a unified framework, that is capable of controlling the sparsity of the neuron activation in deep neural networks. Our proposed approach automatically selects the most useful low-level features and effectively combines them into more powerful and discriminative features for our specific image classification problem. We also explore priors on the relationships between multiple factors. When multiple independent factors exist in the image generation process and only some of them are of interest to us, we propose a novel multi-task adversarial network to learn a disentangled feature which is optimized with respect to the factor of interest to us, while being distraction factors agnostic. When common factors exist in multiple tasks, leveraging common factors cannot only make the learned feature representation more robust, but also enable the model to generalise from very few labelled samples. More specifically, we address the domain adaptation problem and propose the re-weighted adversarial adaptation network to reduce the feature distribution divergence and adapt the classifier from source to target domains.

archives@tulane.edu / 1 / Sabrina Martinez

Ulcerative colitis (UC) is a chronic inflammatory disease characterized by periods of relapses and remissions affecting more than 500,000 people in the United States. To achieve the therapeutic goals of UC, which are to first induce and then maintain disease remission, doctors need to evaluate the severity of UC of a patient. However, it is very difficult to evaluate the severity of UC objectively because of non-uniform nature of symptoms and large variations in their patterns. To address this, in our previous works, we developed two different approaches in which one is using the image textures, and the other is using CNN (convolutional neural network) to measure and classify objectively the severity of UC presented in optical colonoscopy video frames. But, we found that the image texture based approach could not handle larger number of variations in their patterns, and the CNN based approach could not achieve very high accuracy. In this paper, we improve our CNN based approach in two ways to provide better accuracy for the classification. We add more thorough and essential preprocessing, and generate more classes to accommodate large variations in their patterns. The experimental results show that the proposed preprocessing can improve the overall accuracy of evaluating the severity of UC.

Defect inspection is one of the most critical tasks in the industry as it can reduce risks of production stops and assure quality control. In recent years, multiple industries have been adopting computer vision systems, especially based on deep learning techniques, as their main detection methods to improve efficiency, reduce risks and human resources, and enhance real-time performance. However, its adoption in the industry is still limited by the labor-intense and time-consuming process of collecting high-quality custom training datasets. At the same time, many industries have access to the CAD models of the components they want to detect or classify as part of the design process. Taking this into account, in the present work, we analyze the performance of various image classification models to visually detect defects in production. Our method systematically generates synthetic datasets from CAD models using Blender to train neural networks under different settings. The proposed method shows that image classification models benefit from a diversity of the range of defect values during training but struggle to identify low-resolution defects, even for state-of-the-art architectures like Vision Transformer and ConvNext or SqueezeNet, which proved to have comparable performance to these networks. Similarly, adding background, texture, and camera pose to training examples provides more contextual information to image classification models but does not necessarily help them detect the defects accurately. Finally, we observed that using a unique tolerance value for all flange pipe sizes can negatively impact the detection accuracy because, for larger pipe flanges, minor defects are not as perceptible as for small flanges.

Dans cette thèse, nous nous intéressons à la classification des images de textures avec aucune connaissance a priori sur les conditions de numérisation. Cette classification selon des définitions pré-établies de matériaux repose sur des algorithmes qui extraient des descripteurs visuels.A cette fin, nous introduisons tout d'abord une variante de descripteurs par motifs binaires locaux (Local Binary Patterns).Dans cette proposition, une approche statistique est suivie pour représenter les textures statiques.Elle incorpore la quantité d'information complémentaire des niveaux de gris des images dans des opérateurs basés LBP.Nous avons nommé cette nouvelle méthode "Completed Local Entropy Binary Patterns (CLEBP)".CLEBP capture la distribution des relations entre les mesures statistiques des données aléatoires d'une image, l'ensemble étant calculé pour tous les pixels au sein d'une structure locale.Sans la moindre étape préalable d'apprentissage, ni de calibration automatique, les descriptions CLEBP contiennent à la fois des informations locales et globales des textures, tout en étant robustes aux variations externes.En outre, nous utilisons le filtrage inspiré par la biologie, ou biologically-inspired filtering (BF), qui simule la rétine humaine via une phase de prétraitement.Nous montrons que notre approche est complémentaire avec les LBP conventionnels, et les deux combinés offrent de meilleurs résultats que l'une des deux méthodes seule.Les résultats expérimentaux sur quatre bases de texture, Outex, KTH-TIPS-2b, CURet, et UIUC montrent que notre approche est plus performante que les méthodes actuelles.Nous introduisons également un cadre formel basé sur une combinaison de descripteurs pour la classification de textures.Au sein de ce cadre, nous combinons des descripteurs LBP invariants en rotation et en échelle, et de faible dimension, avec les réseaux de dispersion, ou scattering networks (ScatNet).Les résultats expérimentaux montrent que l'approche proposée est capable d'extraire des descripteurs riches à de nombreuses orientations et échelles.Les textures sont modélisées par une concaténation des codes LBP et valeurs moyennes des coefficients ScatNet.Nous proposons également d'utiliser le filtrage inspiré par la biologie, ou biologically-inspired filtering (BF), pour améliorer la resistance des descripteurs LBP.Nous démontrons par l'expérience que ces nouveaux descripteurs présentent de meilleurs résultats que les approches usuelles de l'état de l'art.Ces résultats sont obtenus sur des bases réelles qui contiennent de nombreuses avec des variations significatives.Nous proposons aussi un nouveau réseau conçu par l'expertise appelé réseaux de convolution normalisée, ou normalized convolution network.Celui-ci est inspiré du modèle des ScatNet, auquel deux modifications ont été apportées.La première repose sur l'utilisation de la convolution normalisé en lieu et place de la convolution standard.La deuxième propose de remplacer le calcul de la valeur moyenne des coefficients du réseaux par une agrégation avec la méthode des vecteurs de Fisher.Les expériences montrent des résultats compétitifs sur de nombreuses bases de textures.Enfin, tout au long de cette thèse, nous avons montré par l'expérience qu'il est possible d'obtenir de très bons résultats de classification en utilisant des techniques peu coûteuses en ressources. / This thesis investigates the complementary approaches for classifying texture images.The thesis begins by proposing a Local Binary Pattern (LBP) variant for efficient texture classification.In this proposed method, a statistical approach to static texture representation is developed. It incorporates the complementary quantity information of image intensity into the LBP-based operators. We name our LBP variant `the completed local entropy binary patterns (CLEBP)'. CLEBP captures the distribution of the relationships between statistical measures of image data randomness, calculated over all pixels within a local structure. Without any pre-learning process and any additional parameters to be learned, the CLEBP descriptors convey both global and local information about texture while being robust to external variations. Furthermore, we use biologically-inspired filtering (BF) which simulates the performance of human retina as preprocessing technique. It is shown that our approach and the conventional LBP have the complementary strength and that by combining these algorithms, one obtains better results than either of them considered separately. Experimental results on four large texture databases show that our approach is more efficient than contemporary ones.We then introduce a framework which is a feature combination approach to the problem of texture classification. In this framework, we combine Local Binary Pattern (LBP) features with low dimensional, rotation and scale invariant counterparts, the handcrafted scattering network (ScatNet). The experimental results show that the proposed approach is capable of extracting rich features at multiple orientations and scales. Textures are modeled by concatenating histogram of LBP codes and the mean values of ScatNet coefficients. Then, we propose using Biological Inspired Filtering (BF) preprocessing technique to enhance the robustness of LBP features. We have demonstrated by experiment that the novel features extracted from the proposed framework achieve superior performance as compared to their traditional counterparts when benchmarked on real-world databases containing many classes with significant imaging variations.In addition, we propose a novel handcrafted network called normalized convolution network. It is inspired by the model of ScatNet with two important modification. Firstly, normalized convolution substitute for standard convolution in ScatNet model to extract richer texture features. Secondly, Instead of using mean values of the network coefficients, Fisher vector is exploited as an aggregation method. Experiments show that our proposed network gains competitive classification results on many difficult texture benchmarks.Finally, throughout the thesis, we have proved by experiments that the proposed approaches gain good classification results with low resource required.

No description available.

Master of Science / Department of Statistics / Haiyan Wang / We introduce a new classification method that is applicable to classify image pixels. This work was motivated by the test-based classification (TBC) introduced by Liao and Akritas(2007). We found that direct application of TBC on image pixel classification can lead to high mis-classification rate. We propose a method that combines the minimum distance and evidence from hypothesis testing to classify image pixels. The method is implemented in R programming language. Our method eliminates the drawback of Liao and Akritas (2007).Extensive experiments show that our modified method works better in the classification of image pixels in comparison with some standard methods of classification; namely, Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Classification Tree(CT), Polyclass classification, and TBC. We demonstrate that our method works well in the case of both grayscale and color images.