Physical Sciences and Mathematics Commons^™

Unpaired Style Transfer Conditional Generative Adversarial Network For Scanned Document Generation, David Jonathan Hawbaker

Dissertations and Theses

Neural networks are a powerful machine learning tool, especially when trained on a large dataset of relevant high-quality data. Generative adversarial networks, image super resolution and most other image manipulation neural networks require a dataset of images and matching target images for training. Collecting and compiling that data can be time consuming and expensive. This work explores an approach for building a dataset of paired document images with a matching scanned version of each document without physical printers or scanners. A dataset of these document image pairs could be used to train a generative adversarial network or image super resolution …

Dictionary Learning For Image Reconstruction Via Numerical Non-Convex Optimization Methods, Lewis M. Hicks

University Honors Theses

This thesis explores image dictionary learning via non-convex (difference of convex, DC) programming and its applications to image reconstruction. First, the image reconstruction problem is detailed and solutions are presented. Each such solution requires an image dictionary to be specified directly or to be learned via non-convex programming. The solutions explored are the DCA (DC algorithm) and the boosted DCA. These various forms of dictionary learning are then compared on the basis of both image reconstruction accuracy and number of iterations required to converge.

Sensory Relevance Models, Walt Woods

Dissertations and Theses

This dissertation concerns methods for improving the reliability and quality of explanations for decisions based on Neural Networks (NNs). NNs are increasingly part of state-of-the-art solutions for a broad range of fields, including biomedical, logistics, user-recommendation engines, defense, and self-driving vehicles. While NNs form the backbone of these solutions, they are often viewed as "black box" solutions, meaning the only output offered is a final decision, with no insight into how or why that particular decision was made. For high-stakes fields, such as biomedical, where lives are at risk, it is often more important to be able to explain a …

Localizing Little Landmarks With Transfer Learning, Sharad Kumar

Dissertations and Theses

Locating a small object in an image -- like a mouse on a computer desk or the door handle of a car -- is an important computer vision problem to solve because in many real life situations a small object may be the first thing that gets operated upon in the image scene. While a significant amount of artificial intelligence and machine learning research has focused on localizing prominent objects in an image, the area of small object detection has remained less explored. In my research I explore the possibility of using context information to localize small objects in an …

Investigations Of An "Objectness" Measure For Object Localization, Lewis Richard James Coates

Dissertations and Theses

Object localization is the task of locating objects in an image, typically by finding bounding boxes that isolate those objects. Identifying objects in images that have not had regions of interest labeled by humans often requires object localization to be performed first. The sliding window method is a common naïve approach, wherein the image is covered with bounding boxes of different sizes that form windows in the image. An object classifier is then run on each of these windows to determine if each given window contains a given object. However, because object classification algorithms tend to be computationally expensive, it …

Using Gist Features To Constrain Search In Object Detection, Joanna Browne Solmon

Dissertations and Theses

This thesis investigates the application of GIST features [13] to the problem of object detection in images. Object detection refers to locating instances of a given object category in an image. It is contrasted with object recognition, which simply decides whether an image contains an object, regardless of the object's location in the image.

In much of computer vision literature, object detection uses a "sliding window" approach to finding objects in an image. This requires moving various sizes of windows across an image and running a trained classifier on the visual features of each window. This brute force method can …

Computational Techniques For Reducing Spectra Of The Giant Planets In Our Solar System, Holly L. Grimes

Dissertations and Theses

The dynamic atmospheres of Jupiter, Saturn, Uranus, and Neptune provide a rich source of meteorological phenomena for scientists to study. To investigate these planets, scientists obtain spectral images of these bodies using various instruments including the Cooled Mid-Infrared Camera and Spectrometer (COMICS) at the Subaru Telescope Facility at Mauna Kea, Hawaii. These spectral images are two-dimensional arrays of double precision floating point values that have been read from a detector array. Such images must be reduced before the information they contain can be analyzed. The reduction process for spectral images from COMICS involves several steps:

1. Sky subtraction: the …