Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 61 for “"Visual Classification"”.
-
Towards Robust Visual Classification through Adversarial Training
Although deep neural networks (DNNs) have demonstrated remarkable capabilities, they are vulnerable to adversarial examples. Adversarial examples are input data perturbed by the human-imperceptible noise to induce the wrong and/or malicious outcome of the victim model. The existence of such …
-
Imaging and Visual Classification by Knowledge-Enhanced Compressive Imaging
… comparing with random patterns. For image classification, we implemented two methods to generate secant projections, which are optimized to preserve the difference between image classes. Lastly we illustrate the new design of single pixel based hyperspectral design. To reach that, the …
-
SPARSE REPRESENTATION, DISCRIMINATIVE DICTIONARIES AND PROJECTIONS FOR VISUAL CLASSIFICATION
… have led to an explosion in the availability of visual data from multiple sources and modalities. Millions of cameras have been installed in buildings, streets, and airports around the world that are capable of capturing multimodal information such as light, depth, heat etc. These data are …
-
Hierarchical cluster guided labeling: efficient label collection for visual classification
Visual classification is a core component in many visually intelligent systems. For example, recognition of objects and terrains provides perception during path planning and navigation tasks performed by autonomous agents. Supervised visual classifiers are typically trained with large sets of …
-
Evaluating Visual Classification Models On Out-of-distribution Shifts With Limited Training Data
… problem settings where out-of-distribution (OOD) classification performance is measured with limited (order of thousand images) training data -- unsupervised domain adaptation and robustness to natural distribution shifts. Overall, this thesis demonstrates that (1) such models can be better …
-
A new heavy-duty vehicle visual classification and activity estimation method for regional mobile source emissions modeling
… collected with the FHWA truck classification. For the purpose of emissions modeling, the FHWA truck classes are converted to those used by the MOBILE6.2 emissions rate model by using either the EPA guidance or the National Research Council conversion factors. However, both these …
-
Classification of plaque in ultrasonic images of human arteries
… process of developing a help tool for subjective visual classification, we introduce a study on the correlation between subjective visual classification and statistical and neural-network based classification on B-mode ultrasound images of atherosclerotic plaque. Since the subjective …
-
Learning Visual Classifiers From Limited Labeled Images
… efficient machine learning techniques for visual classification from small amount of labeled training data by utilizing the structure in the testing data, labeled data in a different domain and unlabeled data. This dissertation has three main parts. In the first part of the dissertation, we …
-
Abordagem baseada em Quality by Design (QbD) para desenvolvimento de microemulsão contendo óleo de Passiflora setacea
… droplet diameter, polydispersity index and visual classification. The exploratory linear planning models were not significant, indicating the possible presence of curvature. The Box-Behnken design was satisfactory in predicting the influence of factors and their interactions, the model has …
-
Understanding Galaxy Evolution in the Local Universe: Investigating Barred Galaxies and Advancing Automated Galaxy Morphology Techniques
… in local disk galaxies. Using a large sample of visually classified barred galaxies, I constrain the bar fraction in the local universe and determine its dependence on host galaxy properties (stellar mass, color, central concentration, and HI gas). Additionally, with the visual bar length …
-
The Effect of Training on Haptic Classification of Facial Expressions of Emotion in 2D Displays by Sighted and Blind Observers
… evaluated the effects of training on the haptic classification of culturally universal facial expressions of emotion as depicted in simple 2D raised-line drawings. Blindfolded sighted (N = 60) and blind (N = 4) participants participated in Experiments 1 and 3, respectively. A small vision control …
-
Adaptive sequential feature selection in visual perception and pattern recognition
In the human visual system, one of the most prominent functions of the extensive feedback from the higher brain areas within and outside of the visual cortex is attentional modulation. The feedback helps the brain to concentrate its resources on visual features that are relevant for recognition, i. …
-
Integrating Human and Machine Intelligence in Galaxy Morphology Classification Tasks
… morphological analysis has relied on visual classification by astronomers, accessing the human brains capacity for advanced pattern recognition. However, this accurate but inefficient method falters when confronted with many thousands (or millions) of images. In the SDSS era, efforts …
-
Mejora de la caracterización mecánica de la madera estructural mediante el análisis espectral de los registros del georradar
… destructive technique for improving the current visual classification of structural wood and evaluation of wooden structures to rehabilitate and reduce the discard of new structural timber sawmill. For this purpose have been tested pieces of new wood of Pinus sylvestris L, using a new …
-
Tidal Features as Tracers of Galaxy Merger Histories
… is a time-intensive process, often relying on visual classification or methods that cannot easily be adapted for application on the latest generation of large imaging surveys outputting millions of galaxy images. We develop a self-supervised machine learning model to automate the detection of …
-
Evaluation of web search engines
… search engines are represented by histograms for visual inspection. The histograms are classified into groups to facilitate the interpretation of the performance metrics and examination of the associated behaviours of the search engines. An automated classification method is developed that …
-
Mapping multivariate measures of brain response onto stimulus information during emotional face classification
The relationship between feature processing and visual classification in the brain has been explored through a combination of reverse correlation methods (i.e.“Bubbles” [22]) and electrophysiological measurements (EEG) taken during a facial emotion categorization task [63]. However, in the absence …
-
Lower Ordovican acritarchs from successions in England and North Wales.
… preservation of acritarchs are discussed and a visual classification scheme is presented which takes into account fragmentation, degree of corrosion, and colour.
-
Biologically Plausible Cortical Hierarchical-Classifier Circuit Extensions in Spiking Neurons
… of categories. A thalamo-cortical, hierarchical classification and sequence learning “Core” circuit implemented as a linear matrix simulation and was published by Rodriguez, Whitson & Granger in 2004. In the brain, these functions are implemented by cortical and thalamic circuits composed of …
Page 1 of 4