Current Search:   Gong, Boqing (x)

View All Items

  • CSV Spreadsheet
(1 - 3 of 3)
Visionary Ophthalmics: Confluence of Computer Vision and Deep Learning for Ophthalmology
Title
Visionary Ophthalmics: Confluence of Computer Vision and Deep Learning for Ophthalmology.
Creator
Morley, Dustin, Foroosh, Hassan, Bagci, Ulas, Gong, Boqing, Mohapatra, Ram, University of Central Florida
Abstract / Description
Ophthalmology is a medical field ripe with opportunities for meaningful application of computer vision algorithms. The field utilizes data from multiple disparate imaging techniques, ranging from conventional cameras to tomography, comprising a diverse set of computer vision challenges. Computer vision has a rich history of techniques that can adequately meet many of these challenges. However, the field has undergone something of a revolution in recent times as deep learning techniques have...
Show moreOphthalmology is a medical field ripe with opportunities for meaningful application of computer vision algorithms. The field utilizes data from multiple disparate imaging techniques, ranging from conventional cameras to tomography, comprising a diverse set of computer vision challenges. Computer vision has a rich history of techniques that can adequately meet many of these challenges. However, the field has undergone something of a revolution in recent times as deep learning techniques have sprung into the forefront following advances in GPU hardware. This development raises important questions regarding how to best leverage insights from both modern deep learning approaches and more classical computer vision approaches for a given problem. In this dissertation, we tackle challenging computer vision problems in ophthalmology using methods all across this spectrum. Perhaps our most significant work is a highly successful iris registration algorithm for use in laser eye surgery. This algorithm relies on matching features extracted from the structure tensor and a Gabor wavelet (-) a classically driven approach that does not utilize modern machine learning. However, drawing on insight from the deep learning revolution, we demonstrate successful application of backpropagation to optimize the registration significantly faster than the alternative of relying on finite differences. Towards the other end of the spectrum, we also present a novel framework for improving RANSAC segmentation algorithms by utilizing a convolutional neural network (CNN) trained on a RANSAC-based loss function. Finally, we apply state-of-the-art deep learning methods to solve the problem of pathological fluid detection in optical coherence tomography images of the human retina, using a novel retina-specific data augmentation technique to greatly expand the data set. Altogether, our work demonstrates benefits of applying a holistic view of computer vision, which leverages deep learning and associated insights without neglecting techniques and insights from the previous era.
Show less
Date Issued
2018
Identifier
CFE0007058, ucf:52001
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0007058
DESIGNING LIGHT FILTERS TO DETECT SKIN USING A LOW-POWERED SENSOR
Title
DESIGNING LIGHT FILTERS TO DETECT SKIN USING A LOW-POWERED SENSOR.
Creator
Tariq, Muhammad, Wisniewski, Pamela, Gong, Boqing, Leavens, Gary, University of Central Florida
Abstract / Description
Detection of nudity in photos and videos, especially prior to uploading to the internet, is vital to solving many problems related to adolescent sexting, the distribution of child pornography, and cyber-bullying. The problem with using nudity detection algorithms as a means to combat these problems is that: 1) it implies that a digitized nude photo of a minor already exists (i.e., child pornography), and 2) there are real ethical and legal concerns around the distribution and processing of...
Show moreDetection of nudity in photos and videos, especially prior to uploading to the internet, is vital to solving many problems related to adolescent sexting, the distribution of child pornography, and cyber-bullying. The problem with using nudity detection algorithms as a means to combat these problems is that: 1) it implies that a digitized nude photo of a minor already exists (i.e., child pornography), and 2) there are real ethical and legal concerns around the distribution and processing of child pornography. Once a camera captures an image, that image is no longer secure. Therefore, we need to develop new privacy-preserving solutions that prevent the digital capture of nude imagery of minors. My research takes a first step in trying to accomplish this long-term goal: In this thesis, I examine the feasibility of using a low-powered sensor to detect skin dominance (defined as an image comprised of 50% or more of human skin tone) in a visual scene. By designing four custom light filters to enhance the digital information extracted from 300 scenes captured with the sensor (without digitizing high-fidelity visual features), I was able to accurately detect a skin dominant scene with 83.7% accuracy, 83% precision, and 85% recall. The long-term goal to be achieved in the future is to design a low-powered vision sensor that can be mounted on a digital camera lens on a teen's mobile device to detect and/or prevent the capture of nude imagery. Thus, I discuss the limitations of this work toward this larger goal, as well as future research directions.
Show less
Date Issued
2017
Identifier
CFE0006806, ucf:51792
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0006806
Sampling and Subspace Methods for Learning Sparse Group Structures in Computer Vision
Title
Sampling and Subspace Methods for Learning Sparse Group Structures in Computer Vision.
Creator
Jaberi, Maryam, Foroosh, Hassan, Pensky, Marianna, Gong, Boqing, Qi, GuoJun, Pensky, Marianna, University of Central Florida
Abstract / Description
The unprecedented growth of data in volume and dimension has led to an increased number of computationally-demanding and data-driven decision-making methods in many disciplines, such as computer vision, genomics, finance, etc. Research on big data aims to understand and describe trends in massive volumes of high-dimensional data. High volume and dimension are the determining factors in both computational and time complexity of algorithms. The challenge grows when the data are formed of the...
Show moreThe unprecedented growth of data in volume and dimension has led to an increased number of computationally-demanding and data-driven decision-making methods in many disciplines, such as computer vision, genomics, finance, etc. Research on big data aims to understand and describe trends in massive volumes of high-dimensional data. High volume and dimension are the determining factors in both computational and time complexity of algorithms. The challenge grows when the data are formed of the union of group-structures of different dimensions embedded in a high-dimensional ambient space.To address the problem of high volume, we propose a sampling method referred to as the Sparse Withdrawal of Inliers in a First Trial (SWIFT), which determines the smallest sample size in one grab so that all group-structures are adequately represented and discovered with high probability. The key features of SWIFT are: (i) sparsity, which is independent of the population size; (ii) no prior knowledge of the distribution of data, or the number of underlying group-structures; and (iii) robustness in the presence of an overwhelming number of outliers. We report a comprehensive study of the proposed sampling method in terms of accuracy, functionality, and effectiveness in reducing the computational cost in various applications of computer vision. In the second part of this dissertation, we study dimensionality reduction for multi-structural data. We propose a probabilistic subspace clustering method that unifies soft- and hard-clustering in a single framework. This is achieved by introducing a delayed association of uncertain points to subspaces of lower dimensions based on a confidence measure. Delayed association yields higher accuracy in clustering subspaces that have ambiguities, i.e. due to intersections and high-level of outliers/noise, and hence leads to more accurate self-representation of underlying subspaces. Altogether, this dissertation addresses the key theoretical and practically issues of size and dimension in big data analysis.
Show less
Date Issued
2018
Identifier
CFE0007017, ucf:52039
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0007017