Thesis (D. Tech.) - Central University of Technology, Free State, 2009

Fine-scale urban land cover information is important for a number of applications, including urban tree canopy mapping, green space analysis, and urban hydrologic modeling. Land cover information has traditionally been extracted from satellite or aerial images using automated image classification techniques, which classify pixels into different categories of land cover based on their spectral characteristics. However, in fine spatial resolution images (4 meters or better), the high degree of within-class spectral variability and between-class spectral similarity of many types of land cover leads to low classification accuracy when pixel-based, purely spectral classification techniques are used. Object-based classification methods, which involve segmenting an image into relatively homogeneous regions (i.e. image segments) prior to classification, have been shown to increase classification accuracy by incorporating the spectral (e.g. mean, standard deviation) and non-spectral (e.g. te xture, size, shape) information of image segments for classification. One difficulty with the object-based method, however, is that a segmentation parameter (or set of parameters), which determines the average size of segments (i.e. the segmentation scale), is difficult to choose. Some studies use one segmentation scale to segment and classify all types of land cover, while others use multiple scales due to the fact that different types of land cover typically vary in size. In this dissertation, two multi-scale object-based classification methods were developed and tested for classifying high resolution images of Deerfield Beach, FL and Houston, TX. These multi-scale methods achieved higher overall classification accuracies and Kappa coefficients than single-scale object-based classification methods. / Since the two dissertation methods used an automated algorithm (Random Forest) for image classification, they are also less subjective and easier to apply to other study areas than most existing multi-scale object-based methods that rely on expert knowledge (i.e. decision rules developed based on detailed visual inspection of image segments) for classifying each type of land cover. / by Brian A. Johnson. / Thesis (Ph.D.)--Florida Atlantic University, 2012. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2012. Mode of access: World Wide Web.

Image Processing and Computer Vision solutions have become commodities for software developers, thanks to the growing availability of Application Program- ming Interfaces (APIs) that encapsulate rich functionality, powered by advanced al- gorithms. To understand and create an e cient method to process faces in images by computers, one must understand how the human visual system processes them. Face processing by computers has been an active research area for about 50 years now. Face detection has become a commodity and is now incorporated into simple devices such as digital cameras and smartphones. An iOS app was implemented in Objective-C using Microsoft Cognitive Ser- vices APIs, as a tool for human vision and face processing research. Experimental work on image compression, upside-down orientation, the Thatcher e ect, negative inversion, high frequency, facial artifacts, caricatures and image degradation were completed on the Radboud and 10k US Adult Faces Databases along with other images. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2016. / FAU Electronic Theses and Dissertations Collection

Tao Dacheng. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 70-75). / Abstracts in English and Chinese. / Chapter Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Content-based Image Retrieval --- p.1 / Chapter 1.2 --- SVM based RF in CBIR --- p.3 / Chapter 1.3 --- DA based RF in CBIR --- p.4 / Chapter 1.4 --- Existing CBIR Engines --- p.5 / Chapter 1.5 --- Practical Applications of CBIR --- p.10 / Chapter 1.6 --- Organization of this thesis --- p.11 / Chapter Chapter 2 --- Statistical Learning Theory and Support Vector Machine --- p.12 / Chapter 2.1 --- The Recognition Problem --- p.12 / Chapter 2.2 --- Regularization --- p.14 / Chapter 2.3 --- The VC Dimension --- p.14 / Chapter 2.4 --- Structure Risk Minimization --- p.15 / Chapter 2.5 --- Support Vector Machine --- p.15 / Chapter 2.6 --- Kernel Space --- p.17 / Chapter Chapter 3 --- Discriminant Analysis --- p.18 / Chapter 3.1 --- PCA --- p.18 / Chapter 3.2 --- KPCA --- p.18 / Chapter 3.3 --- LDA --- p.20 / Chapter 3.4 --- BDA --- p.20 / Chapter 3.5 --- KBDA --- p.21 / Chapter Chapter 4 --- Random Sampling Based SVM --- p.24 / Chapter 4.1 --- Asymmetric Bagging SVM --- p.25 / Chapter 4.2 --- Random Subspace Method SVM --- p.26 / Chapter 4.3 --- Asymmetric Bagging RSM SVM --- p.26 / Chapter 4.4 --- Aggregation Model --- p.30 / Chapter 4.5 --- Dissimilarity Measure --- p.31 / Chapter 4.6 --- Computational Complexity Analysis --- p.31 / Chapter 4.7 --- QueryGo Image Retrieval System --- p.32 / Chapter 4.8 --- Toy Experiments --- p.35 / Chapter 4.9 --- Statistical Experimental Results --- p.36 / Chapter Chapter 5 --- SSS Problems in KBDA RF --- p.42 / Chapter 5.1 --- DKBDA --- p.43 / Chapter 5.1.1 --- DLDA --- p.43 / Chapter 5.1.2 --- DKBDA --- p.43 / Chapter 5.2 --- NKBDA --- p.48 / Chapter 5.2.1 --- NLDA --- p.48 / Chapter 5.2.2 --- NKBDA --- p.48 / Chapter 5.3 --- FKBDA --- p.49 / Chapter 5.3.1 --- FLDA --- p.49 / Chapter 5.3.2 --- FKBDA --- p.49 / Chapter 5.4 --- Experimental Results --- p.50 / Chapter Chapter 6 --- NDA based RF for CBIR --- p.52 / Chapter 6.1 --- NDA --- p.52 / Chapter 6.2 --- SSS Problem in NDA --- p.53 / Chapter 6.2.1 --- Regularization method --- p.53 / Chapter 6.2.2 --- Null-space method --- p.54 / Chapter 6.2.3 --- Full-space method --- p.54 / Chapter 6.3 --- Experimental results --- p.55 / Chapter 6.3.1 --- K nearest neighbor evaluation for NDA --- p.55 / Chapter 6.3.2 --- SSS problem --- p.56 / Chapter 6.3.3 --- Evaluation experiments --- p.57 / Chapter Chapter 7 --- Medical Image Classification --- p.59 / Chapter 7.1 --- Introduction --- p.59 / Chapter 7.2 --- Region-based Co-occurrence Matrix Texture Feature --- p.60 / Chapter 7.3 --- Multi-level Feature Selection --- p.62 / Chapter 7.4 --- Experimental Results --- p.63 / Chapter 7.4.1 --- Data Set --- p.64 / Chapter 7.4.2 --- Classification Using Traditional Features --- p.65 / Chapter 7.4.3 --- Classification Using the New Features --- p.66 / Chapter Chapter 8 --- Conclusion --- p.68 / Bibliography --- p.70

by Chi-Min Pang. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1996. / Includes bibliographical references (leaves 110-[115]). / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Range Images --- p.1 / Chapter 1.2 --- Rigid Body Model --- p.3 / Chapter 1.3 --- Motivation --- p.4 / Chapter 1.4 --- Thesis Outline --- p.6 / Chapter 2 --- Object Recognition by Relaxation Processes --- p.7 / Chapter 2.1 --- An Overview of Probabilistic Relaxation Labelling --- p.8 / Chapter 2.2 --- Formulation of Model-matching Problem Solvable by Probabilistic Relaxation --- p.10 / Chapter 2.2.1 --- Compatibility Coefficient --- p.11 / Chapter 2.2.2 --- Match Score --- p.13 / Chapter 2.2.3 --- Iterative Algorithm --- p.14 / Chapter 2.2.4 --- A Probabilistic Concurrent Matching Scheme --- p.15 / Chapter 2.3 --- Formulation of Model-merging Problem Solvable by Fuzzy Relaxation --- p.17 / Chapter 2.3.1 --- Updating Mechanism --- p.17 / Chapter 2.3.2 --- Iterative Algorithm --- p.19 / Chapter 2.3.3 --- Merging Sub-Rigid Body Models --- p.20 / Chapter 2.4 --- Simulation Results --- p.21 / Chapter 2.4.1 --- Experiments in Model-matching Using Probabilistic Relaxation --- p.22 / Chapter 2.4.2 --- Experiments in Model-matching Using Probabilistic Concur- rent Matching Scheme --- p.26 / Chapter 2.4.3 --- Experiments in Model-merging Using Fuzzy Relaxation --- p.33 / Chapter 2.5 --- Summary --- p.36 / Chapter 3 --- Object Recognition by Hopfield Network --- p.37 / Chapter 3.1 --- An Overview of Hopfield Network --- p.38 / Chapter 3.2 --- Model-matching Problem Solved by Hopfield Network --- p.41 / Chapter 3.2.1 --- Representation of the Solution --- p.41 / Chapter 3.2.2 --- Energy Function --- p.42 / Chapter 3.2.3 --- Equations of Motion --- p.46 / Chapter 3.2.4 --- Interpretation of Solution --- p.49 / Chapter 3.2.5 --- Convergence of the Hopfield Network --- p.50 / Chapter 3.2.6 --- Iterative Algorithm --- p.51 / Chapter 3.3 --- Estimation of Distance Threshold Value --- p.53 / Chapter 3.4 --- Cooperative Concurrent Matching Scheme --- p.55 / Chapter 3.4.1 --- Scheme for Recognizing a Single Object --- p.56 / Chapter 3.4.2 --- Scheme for Recognizing Multiple Objects --- p.60 / Chapter 3.5 --- Simulation Results --- p.60 / Chapter 3.5.1 --- Experiments in the Model-matching Problem Using a Hopfield Network --- p.61 / Chapter 3.5.2 --- Experiments in Model-matching Problem Using Cooperative Concurrent Matching --- p.69 / Chapter 3.5.3 --- Experiments in Model-merging Problem Using Hopfield Network --- p.77 / Chapter 3.6 --- Summary --- p.80 / Chapter 4 --- Genetic Generation of Weighting Parameters for Hopfield Network --- p.83 / Chapter 4.1 --- An Overview of Genetic Algorithms --- p.84 / Chapter 4.2 --- Determination of Weighting Parameters for Hopfield Network --- p.86 / Chapter 4.2.1 --- Chromosomal Representation --- p.87 / Chapter 4.2.2 --- Initial Population --- p.88 / Chapter 4.2.3 --- Evaluation Function --- p.88 / Chapter 4.2.4 --- Genetic Operators --- p.89 / Chapter 4.2.5 --- Control Parameters --- p.91 / Chapter 4.2.6 --- Iterative Algorithm --- p.94 / Chapter 4.3 --- Simulation Results --- p.95 / Chapter 4.3.1 --- Experiments in Model-matching Problem using Hopfield Net- work with Genetic Generated Parameters --- p.95 / Chapter 4.3.2 --- Experiments in Model-merging Problem Using Hopfield Network --- p.101 / Chapter 4.4 --- Summary --- p.104 / Chapter 5 --- Conclusions --- p.106 / Chapter 5.1 --- Conclusions --- p.106 / Chapter 5.2 --- Suggestions for Future Research --- p.109 / Bibliography --- p.110 / Chapter A --- Proof of Convergence of Fuzzy Relaxation Process --- p.116

Two related image processing problems are addressed in this thesis. First, the problem of identification of 3-D objects in real time is explored. An algorithm to solve this problem and a hardware system for parallel implementation of this algorithm are proposed. The classification scheme is based on the "Invariant Numerical Shape Modeling" (INSM) algorithm originally developed for 2-D pattern recognition such as alphanumeric characters. This algorithm is then extended to 3-D and is used for general 3-D object identification. The hardware system is an SIMD parallel processor, designed in bit slice fashion for expandability. It consists of a library of images coded according to the 3-D INSM algorithm and the SIMD classifier which compares the code of the unknown image to the library codes in a single clock pulse to establish its identity. The output of this system consists of three signals: U, for unique identification; M, for multiple identification; and N, for non-identification of the object. Second, the problem of real time image compaction is addressed. The quad tree data structure is described. Based on this structure, a parallel processor with a tree architecture is developed which is independent of the data entry process, i.e., data may be entered pixel by pixel or all at once. The hardware consists of a tree processor containing a tree generator and three separate memory arrays, a data transfer processor, and a main memory unit. The tree generator generates the quad tree of the input image in tabular form, using the memory arrays in the tree processor for storage of the table. This table can hold one picture frame at a given time. Hence, for processing multiple picture frames the data transfer processor is used to transfer their respective quad trees from the tree processor memory to the main memory. An algorithm is developed to facilitate the determination of the connections in the circuit.

Abstract not available

Abstract not available

Identifying material parameters in composite plates is a necessary first step in a variety of structural applications. For example, understanding the material parameters of carbon fiber composite is important in investigating sensor and actuator placement on micro-air-vehicle wings for control and wing morphing purposes. Knowing the material parameters can also help examine the health of composite structures and detect wear or defects. Traditional testing methods for finding material parameters such as stiffness and damping require multiple types of experiments such as tensile tests and shaker tests. These tests are not without complications. Methods such as tensile testing can be destructive to the test specimens while use of strain gages and accelerometers can be inappropriate due to the lightweight nature of the structures. The proposed inverse problem testing methods using digital image correlation via high speed cameras can potentially eliminate the disadvantages of traditional methods as well as determine the required material parameters including stiffness and damping by conducting only one type of experiment. These material parameters include stiffness and damping for both isotropic and orthotropic materials, and ply angle layup specifically for carbon fiber materials. A finite element model based on the Kirchoff-Love thin plate theory is used to produce theoretical data for comparison with experimental data collected using digital image correlation. Shaker experiments are also carried out using digital image correlation to investigate the modal frequencies as validation of the results of the inverse problem. We apply these techniques first to an aluminum plate for which material parameters are known to test the performance and efficiency of the method. We then apply the method to a composite plates to determine not only these parameters, but also the layup angle. The inverse problem successfully estimates the Young's modulus and damping for the aluminum material. In addition, the vibration analysis produces consistent resonance frequencies for the first two modes for both theoretical and experimental data. However, carbon fiber plates present challenges due to limitations of the Kirchoff-Love plate theory used as the underlining theoretical model for the finite element approximation used in the inverse problem, resulting in a persistent mismatch of resonance frequencies in experimental data. / Graduation date: 2012

The global objectives of this research are to develop a liver-specific magnetic resonance (MR) image registration and segmentation algorithms and to find highly correlated MR imaging features that help automatically score the severity of chronic liver disease (CLD). For a concise analysis of liver disease, time sequences of 3-D MR images should be preprocessed through an image registration to compensate for the patient motion, respiration, or tissue motion. To register contrast-enhanced MR image volume sequences, we propose a novel version of the demons algorithm that is based on a bi-directional local correlation coefficient (Bi-LCC) scheme. This scheme improves the speed at which a convergent sequence approaches to the optimum state and achieves the higher accuracy. Furthermore, the simple and parallelizable hierarchy of the Bi-LCC demons can be implemented on a graphics processing unit (GPU) using OpenCL. To automate segmentation of the liver parenchyma regions, an edge function-scaled region-based active contour (ESRAC), which hybridizes gradient and regional statistical information, with approximate partitions of the liver was proposed. Next, a significant purpose in grading liver disease is to assess the level of remaining liver function and to estimate regional liver function. On motion-corrected and segmented liver parenchyma regions, for quantitative analysis of the hepatic extraction of liver-specific MRI contrast agent, liver signal intensity change is evaluated from hepatobiliary phases (3-20 minutes), and parenchymal texture features are deduced from the equilibrium (3 minutes) phase. To build a classifier using texture features, a set of training input and output values, which is estimated by experts as a score of malignancy, trains the supervised learning algorithm using a multivariate normal distribution model and a maximum a posterior (MAP) decision rule. We validate the classifier by assessing the prediction accuracy with a set of testing data.