Browsing Theses by Supervisor "Zelek, John"
Now showing items 1-20 of 20
-
3D Mesh and Pose Recovery of a Foot from Single Image
(University of Waterloo, 2022-01-18)The pandemic and the major shift to online shopping has highlighted the current difficulties in getting proper sizing for clothing and shoes. Being able to accurately measure shoes using readily available smartphones would ... -
Anomaly Detection in Textured Surfaces
(University of Waterloo, 2019-12-17)Detecting anomalies in textured surfaces is an important and interesting problem that has practical applications in industrial defect detection and infrastructure asset management with a lot of potential financial benefits. ... -
Automated Cataract Grading using Smartphone Images
(University of Waterloo, 2021-02-02)A cataract is an age-related eye disease and is one of the leading ophthalmological public health problems in developed and developing countries. Early detection of cataracts is necessary to preserve sight and prevent the ... -
Automated Segmentation of Retinal Optical Coherence Tomography Images
(University of Waterloo, 2018-08-21)Aim. Optical Coherence Tomography (OCT) is a fast and non-invasive medical imaging technique which helps in the investigation of each individual retinal layer structure. For early detection of retinal diseases and the study ... -
Automating Manufacturing Surveillance Processes Using External Observers
(University of Waterloo, 2022-09-29)An automated assembly system is an integral part of various manufacturing industries as it reduces production cycle-time resulting in lower costs and a higher rate of production. The modular system design integrates main ... -
Cancer Classification in Human Brain and Prostate Using Raman Spectroscopy and Machine Learning
(University of Waterloo, 2017-09-27)Real-time assisted classification of cancerous and healthy human tissue is useful to surgeons since visual classification of cancer boundaries is almost impossible to the naked eye. Raman spectroscopy can be used to ... -
Deep Generative Modeling Based Retinal Image Analysis
(University of Waterloo, 2020-06-16)In the recent past, deep learning algorithms have been widely used in retinal image analysis (fundus and OCT) to perform tasks like segmentation and classification. But to build robust and highly efficient deep learning ... -
Deep Learning 3D Scans for Footwear Fit Estimation from a Single Depth Map
(University of Waterloo, 2018-01-02)In clothing and particularly in footwear, the variance in the size and shape of people and of clothing poses a problem of how to match items of clothing to a person. This is specifically important in footwear, as fit is ... -
Developing algorithms for the analysis of retinal Optical Coherence Tomography images
(University of Waterloo, 2018-09-04)Vision loss, with a prevalence loss greater than 42 million in the United States is one of the major challenges of today's health-care industry and medical science. Early detection of different retinal-related diseases ... -
Diabetic retinopathy grading with respect to the segmented lesions
(University of Waterloo, 2022-05-19)One of the leading causes of irreversible vision loss is Diabetic Retinopathy (DR). The International Clinical Diabetic Retinopathy scale (ICDRS) provides grading criteria for DR. Deep Convolutional Neural Networks (DCNNs) ... -
Efficient Image-Based Localization Using Context
(University of Waterloo, 2015-12-22)Image-Based Localization (IBL) is the problem of computing the position and orientation of a camera with respect to a geometric representation of the scene. A fundamental building block of IBL is searching the space of a ... -
Explainable AI for retinal OCT diagnosis
(University of Waterloo, 2021-01-20)Artificial intelligence methods such as deep learning are leading to great progress in complex tasks that are usually associated with human intelligence and experience. Deep learning models have matched if not bettered ... -
Model Compression via Generalized Kronecker Product Decomposition
(University of Waterloo, 2022-09-26)Modern convolutional neural network (CNN) architectures, despite their superiority in solving various problems, are generally too large to be deployed on resource constrained edge devices. In practice, this limits many ... -
Modern Object and Visual Relationship Detection in Images from a Critical, Cognitive and Data Perspective
(University of Waterloo, 2023-04-27)Deep learning has dominated the landscape of computer vision for the past decade. Deep learning networks are the top performers on a slew of computer vision challenges (e.g., object detection or image segmentation) and on ... -
Multi-sensor Fusion for Positioning and Semantic Information Extraction in Indoor Environments
(University of Waterloo, 2023-05-30)This thesis focuses on three significant challenges in multi-sensor data fusion for real-world uses: (1) Lack of multisensory datasets for mapping and positioning datasets in underground environments, (2) inefficient and ... -
Multivariate Time Series Data Causal Discovery
(University of Waterloo, 2021-10-05)One of the goals for Artificial Intelligence is to achieve human-like intelligence. To that end, several solutions were proposed over the decades, where causal structure discovery was proposed as a viable tool for enabling ... -
Municipal Road Infrastructure Assessment Using Street View Images
(University of Waterloo, 2016-09-23)Road quality assessment is a crucial part in Municipalities' work to maintain their infrastructure, plan upgrades, and manage their budgets. Properly maintaining this infrastructure relies heavily on consistently monitoring ... -
RGB-D Scene Flow via Grouping Rigid Motions
(University of Waterloo, 2016-09-06)Robotics and artificial intelligence have seen drastic advancements in technology and algorithms over the last decade. Computer vision algorithms play a crucial role in enabling robots and machines to understand their ... -
Text Detection and Recognition in the Wild
(University of Waterloo, 2022-07-19)Text detection and recognition (TDR) in highly structured environments with a clean background and consistent fonts (e.g., office documents, postal addresses and bank cheque) is a well understood problem (i.e., OCR), however ... -
A Unified Hybrid Formulation for Visual SLAM
(University of Waterloo, 2021-02-16)Visual Simultaneous Localization and Mapping (Visual SLAM (VSLAM)), is the process of estimating the six degrees of freedom ego-motion of a camera, from its video feed, while simultaneously constructing a 3D model of the ...