Browsing University of Waterloo by Supervisor "Wong, Alexander"
Now showing items 1-20 of 40
-
An Analysis Framework for the Quantization-Aware Design of Efficient, Low-Power Convolutional Neural Networks
(University of Waterloo, 2022-04-29)Deep convolutional neural network (CNN) algorithms have emerged as a powerful tool for many computer vision tasks such as image classification, object detection, and semantic segmentation. However, these algorithms are ... -
Automatic Identification of Algae using Low-cost Multispectral Fluorescence Digital Microscopy, Hierarchical Classification & Deep Learning
(University of Waterloo, 2019-12-05)Harmful algae blooms (HABs) can produce lethal toxins and are a rising global concern. In response to this threat, many organizations are monitoring algae populations to determine if a water body might be contaminated. ... -
Class Based Strategies for Understanding Neural Networks
(University of Waterloo, 2020-02-07)One of the main challenges for broad adoption of deep learning based models such as Convolutional Neural Networks (CNN), is the lack of understanding of their decisions. In many applications, a simpler, less capable model ... -
Collaborative design and feasibility assessment of computational nutrient sensing for simulated food-intake tracking in a healthcare environment
(University of Waterloo, 2021-11-19)One in four older adults (65 years and over) are living with some form of malnutrition. This increases their odds of hospitalization four-fold and is associated with decreased quality of life and increased mortality. In ... -
Compensated Row-Column Ultrasound Imaging System
(University of Waterloo, 2020-03-12)Ultrasound imaging is a valuable tool in many applications ranging from material science to medical imaging. While 2-D ultrasound imaging is more commonly used, 3-D ultrasound imaging offers unique opportunities that can ... -
Comprehensive Framework for Computer-Aided Prostate Cancer Detection in Multi-Parametric MRI
(University of Waterloo, 2016-08-30)Prostate cancer is the most diagnosed form of cancer and one of the leading causes of cancer death in men, but survival rates are relatively high with sufficiently early diagnosis. The current clinical model for initial ... -
Computational Depth from Defocus via Active Quasi-random Pattern Projections
(University of Waterloo, 2018-08-22)Depth information is one of the most fundamental cues in interpreting the geometric relationship of objects. It enables machines and robots to perceive the world in 3D and allows them to understand the environment far ... -
Computational Polarimetry: A Bayesian Framework for Polarimetric System Design
(University of Waterloo, 2019-09-10)In this thesis, we propose a novel polarimetric system design framework that computationally evaluates a design to solve an optical problem. It does this by explicitly formulating the logical connections and dependencies ... -
A Content Enhancement Framework for Multi-Projector Systems
(University of Waterloo, 2018-09-04)Projectors are a convenient technology for displaying content on large, abnormal, or temporary surfaces where mounting other forms of light emitting devices is too impractical or too expensive. Common uses of projectors ... -
Contour Integration in Artifical Neural Networks
(University of Waterloo, 2022-02-08)Under difficult viewing conditions, the brain's visual system uses a variety of modulatory techniques to supplement its core feedforward signal. One such technique is contour integration, whereby contextual stimuli from ... -
Dermal Radiomics: a new approach for computer-aided melanoma screening system
(University of Waterloo, 2016-08-19)Skin cancer is the most common form of cancer in North America, and melanoma is the most dangerous type of skin cancer. Melanoma originates from melanocytes in the epidermis and has a high tendency to develop away from the ... -
Efficient Deep Learning-Driven Systems for Real-Time Video Expression Recognition
(University of Waterloo, 2021-01-18)The ability to detect, recognize, and interpret facial expressions is an important skill for humans to have due to the abundance of social interactions one faces on a daily basis, but it is also something that most take ... -
Exploring New Forms of Random Projections for Prediction and Dimensionality Reduction in Big-Data Regimes
(University of Waterloo, 2018-05-01)The story of this work is dimensionality reduction. Dimensionality reduction is a method that takes as input a point-set P of n points in R^d where d is typically large and attempts to find a lower-dimensional representation ... -
Fair Compression of Machine Learning Vision Systems
(University of Waterloo, 2023-09-01)Model pruning is a simple and effective method for compressing neural networks. By identifying and removing the least influential parameters of a model, pruning is able to transform networks into smaller, faster networks ... -
Highly Efficient Deep Intelligence via Multi-Parent Evolutionary Synthesis of Deep Neural Networks
(University of Waterloo, 2020-02-11)Machine learning methods, and particularly deep neural networks, are a rapidly growing field and are currently being employed in domains such as science, business, and government. However, the significant success of neural ... -
Hockey Pose Estimation and Action Recognition using Convolutional Neural Networks to Ice Hockey
(University of Waterloo, 2018-09-19)Human pose estimation and action recognition in ice hockey are one of the biggest challenges in computer vision-driven sports analytics, with a variety of difficulties such as bulky hockey wear, color similarity between ... -
Investigating Scene Understanding for Robotic Grasping: From Pose Estimation to Explainable AI
(University of Waterloo, 2023-09-22)In the rapidly evolving field of robotics, the ability to accurately grasp and manipulate objects—known as robotic grasping—is a cornerstone of autonomous operation. This capability is pivotal across a multitude of ... -
Issues in Computer Vision Data Collection: Bias, Consent, and Label Taxonomy
(University of Waterloo, 2020-09-30)Recent success of the convolutional neural network in image classification has pushed the computer vision community towards data-rich methods of deep learning. As a consequence of this shift, the data collection process ... -
Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustness
(University of Waterloo, 2020-08-19)Deep neural networks have been achieving state-of-the-art performance across a wide variety of applications, and due to their outstanding performance, they are being deployed in safety and security critical systems. However, ... -
Neural Network Classifiers for Human Tissue Classification in NIR Biomedical Multispectral Imaging
(University of Waterloo, 2018-06-11)Near infrared imaging (NIR) is an imaging modality that has gained traction for solving biomedical problems in recent years. By leveraging the NIR spectrum, multiple spectra from the NIR range can be used to extract ...