No description available.

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

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.

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.

Modern microscopy and automation technologies enable experiments which can produce millions of images each day. The valuable information is often sparse, and requires clever methods to find useful data. In this thesis a general image classification tool for fluorescence microscopy images was developed usingfeatures extracted from a general Convolutional Neural Network (CNN) trained on natural images. The user selects interesting regions in a microscopy image and then, through an iterative process, using active learning, continually builds a training data set to train a classifier that finds similar regions in other images. The classifier uses conformal prediction to find samples that, if labeled, would most improve the learned model as well as specifying the frequency of errors the classifier commits. The result show that with the appropriate choice of significance one can reach a high confidence in true positive. The active learning approach increased the precision with a downside of finding fewer examples.

Complex wavelet structural similarity (CW-SSIM) index has been recognized as a novel image similarity measure of broad potential applications due to its robustness to small geometric distortions such as translation, scaling and rotation of images. Nevertheless, how to make the best use of it in image classification problems has not been deeply investi- gated. In this study, we introduce a series of novel image classification algorithms based on CW-SSIM and use handwritten digit and face image recognition as examples for demonstration, including CW-SSIM based nearest neighbor method, CW-SSIM based k means method, CW-SSIM based support vector machine method (SVM) and CW-SSIM based SVM using affinity propagation. Among the proposed approaches, the best compromise between accuracy and complexity is obtained by the CW-SSIM support vector machine algorithm, which combines an unsupervised clustering method to divide the training images into clusters with representative images and a supervised learning method based on support vector machines to maximize the classification accuracy. Our experiments show that such a conceptually simple image classification method, which does not involve any registration, intensity normalization or sophisticated feature extraction processes, and does not rely on any modeling of the image patterns or distortion processes, achieves competitive performance with reduced computational cost.

Complex wavelet structural similarity (CW-SSIM) index has been recognized as a novel image similarity measure of broad potential applications due to its robustness to small geometric distortions such as translation, scaling and rotation of images. Nevertheless, how to make the best use of it in image classification problems has not been deeply investi- gated. In this study, we introduce a series of novel image classification algorithms based on CW-SSIM and use handwritten digit and face image recognition as examples for demonstration, including CW-SSIM based nearest neighbor method, CW-SSIM based k means method, CW-SSIM based support vector machine method (SVM) and CW-SSIM based SVM using affinity propagation. Among the proposed approaches, the best compromise between accuracy and complexity is obtained by the CW-SSIM support vector machine algorithm, which combines an unsupervised clustering method to divide the training images into clusters with representative images and a supervised learning method based on support vector machines to maximize the classification accuracy. Our experiments show that such a conceptually simple image classification method, which does not involve any registration, intensity normalization or sophisticated feature extraction processes, and does not rely on any modeling of the image patterns or distortion processes, achieves competitive performance with reduced computational cost.

[pt] Neste trabalho, diversas técnicas de classificação automática de imagens de sensoriamento remoto são investigadas. Na análise, incluem-se um método não- paramétrico, denominado K-Médias. Adaptativos Hierárquico (KMAH), e seis paramétricos: o Classificador de Máxima Verossimilhança (MV), o de Máxima Probabilidade a Posteriori (MAP), o MAP Adaptativo (MAPA), por Subimagens (MAPSI), o Contextual Tilton-Swain (CXTS) e o Contextual por Subimagens (CXSI). O treinamento necessário à implementação das técnicas paramétricas foi realizado de forma não-supervisionada, usando-se para tanto a classificação efetuada pelo KMAH. Considerações a respeito das vantagens e desvantagens dos classificadores, de acordo com a observação das taxas de erros e dos tempos de processamento, apontaram as técnicas MAPA e MAPSI com as mais convenientes / [en] In this thesis, several techniques of automatic classfication of remote sensing impeages are investigated. Included in the analysis are ane non-parametric method, known as Adaptative hierarchical K-means (KMAH), and six parametric ones: the Maximum Likelihood (MV), the Maximum a Posteriori Probability (MAP), the Adaptative MAP (MAPA), the Subimages MAP (MAPSI), the tilton-Swain Contextual, (CXTS) and the Subimages Contextual (CXSI) classifiers. The necessary training for the parametric case was done in a non-supervised form, by using the KMAH classification. Considerations about the advantages and disadvantages of the classifiers were made and, based on the observation of the error rates and processing time, the MAPA and MAPSI have shown the best performances.