Electrical and Electronics Commons^™

A Deep Recurrent Neural Network With Iterative Optimization For Inverse Image Processing Applications, Masaki Ikuta

Theses and Dissertations

Many algorithms and methods have been proposed for inverse image processing applications, such as super-resolution, image de-noising, and image reconstruction, particularly with the recent surge of interest in machine learning and deep learning methods.

As for Computed Tomography (CT) image reconstruction, the most recently proposed methods are limited to image domain processing, where deep learning is used to learn the mapping between a true image data set and a noisy image data set in the image domain. While deep learning-based methods can produce higher quality images than conventional model-based algorithms, these methods have a limitation. Deep learning-based methods used in …

Machine Intelligence For Advanced Medical Data Analysis: Manifold Learning Approach, Fereshteh S Bashiri

Theses and Dissertations

In the current work, linear and non-linear manifold learning techniques, specifically Principle Component Analysis (PCA) and Laplacian Eigenmaps, are studied in detail. Their applications in medical image and shape analysis are investigated.

In the first contribution, a manifold learning-based multi-modal image registration technique is developed, which results in a unified intensity system through intensity transformation between the reference and sensed images. The transformation eliminates intensity variations in multi-modal medical scans and hence facilitates employing well-studied mono-modal registration techniques. The method can be used for registering multi-modal images with full and partial data.

Next, a manifold learning-based scale invariant global shape …

Hyperspectral Tomographic Ftir Imaging Using Two Illumination Geometries For Polymer Phantoms, Zahrasadat Alavi

Theses and Dissertations

The purpose of this dissertation is to carry out non-destructive 3D imaging by applying Fourier Transform Infrared (FTIR) spectro-microtomographic techniques, and develop corresponding methods of data analysis. This is done by collecting 3D synchrotron-based and lab-based (Thermal) FTIR hyper spectral data at the Synchrotron Radiation Center (SRC) for the first time. Despite other 2D imaging techniques, this does not manipulate the sample, and suppresses the need to microtome 3D biological, material or biomedical samples into slices to study by spectroscopic imaging techniques. Spectro-micro-tomography is applicable for scientific, industrial, energy, biomedical samples such as stem cell characterization and materials such as …

Discovery And Correction Of Bias In Precision Landmark Location, Colin Foster

Theses and Dissertations

Precision Landmark Location (PLL) estimation is an integral part of 3D motion tracking. Circular landmark location estimation is one method of PLL. Current methods of estimation lead to systematic errors with a magnitude of up to .02 pixels. Estimation inaccuracies of this magnitude lead to unacceptable errors in depth measurement, the largest source of error. In the scope of this thesis, inadequacies in circular landmark location are uncovered and techniques to correct these errors are analyzed, tested, and demonstrated. Deviations in simulated images are seen to be reduced by a factor of three and the variances of real-world data were …