The first area of work is to assess image quality by measuring the similarity between edge map of a distorted image and that of its original version using classical edge quality evaluation metrics.  Experiments show that comparing edge maps of original and distorted images gives a better result than comparing the images themselves.  Based on redefined source and distortion models, a novel FR image quality assessment metric DQM is proposed, which is proved by subsequent experiments to be competitive with state-of-the-art metrics (SSIM, IFC, VIF, etc.).  The thesis also proposes several image quality metrics based on a framework for developing image quality assessment algorithms with the help of data-driven models (multiple linear regression, artificial neural network and support vector machine). Among them, CAM_BPNN and CAM_SVM perform better than SSIM and can even compete with its improved multi-scale version MSSIM.  Apart from the research about FR image quality assessment, a novel RR image quality assessment system is proposed, based on low-level features (corner, edge and symmetry).

Object localization is the task of locating objects in an image, typically by finding bounding boxes that isolate those objects. Identifying objects in images that have not had regions of interest labeled by humans often requires object localization to be performed first. The sliding window method is a common naïve approach, wherein the image is covered with bounding boxes of different sizes that form windows in the image. An object classifier is then run on each of these windows to determine if each given window contains a given object. However, because object classification algorithms tend to be computationally expensive, it is helpful to have an effective filter to reduce the number of times those classifiers have to be run. In this thesis I evaluate one promising approach to object localization: the objectness algorithm proposed by Alexe et al. Specifically, I verify the results given by Alexe et al., and further explore the weaknesses and strengths of their "objectness"

No description available.

Call number: LD2668 .T4 1986 H53 / Master of Science / Electrical and Computer Engineering

This thesis introduces and explores the notion of a real-world environment with respect to adaptive pattern recognition and neural network systems. It then examines the individual properties of a real-world environment and proposes Continuous Adaptation, Persistence of information and Context-sensitive recognition to be the major design criteria a neural network system in a real-world environment should satisfy. Based on these criteria, it then assesses the performance of Hopfield networks and Associative Memory systems and identifies their operational limitations. This leads to the introduction of Randomized Internal Representations, a novel class of neural network systems which stores information in a fully distributed way yet is capable of encoding and utilizing context. It then assesses the performance of Competitive Learning and Adaptive Resonance Theory systems and again having identified their operational weakness, it describes the Dynamic Adaptation Scheme which satisfies all three design criteria for a real-world environment.

Sustained resonance in a linear oscillator is achievable with a drive whose constant frequency matches the resonant frequency of the oscillator. In oscillators with nonlinear restoring forces, i.e., Dung-type oscillators, resonant frequency changes with amplitude, so a constant frequency drive generates a beat oscillation instead of sustained resonance. Dung-type oscillators can be driven into sustained resonance, called autoresonance (AR), when drive frequency is swept in time to match the changing resonant frequency of the oscillator. It is found that near-optimal drive linear sweep rates for autoresonance can be estimated from the beat oscillation resulting from constant frequency excitation. Specically, a least squares estimate of the slope of the Teager-Kaiser instantaneous frequency versus time plot for the rising half-cycle of the beat response to a stationary drive provides a near-optimal estimate of the linear drive sweep rate that sustains resonance in the pendulum, Dung and Dung-Van der Pol oscillators. These predictions are confirmed with model-based numerical simulations. A closed-form approximation to the AM-FM nonlinear resonance beat response of a Dung oscillator driven at its low-amplitude oscillator frequency is obtained from a solution to an associated Mathieu equation. AR time responses are found to evolve along a Mathieu equation primary resonance stability boundary. AR breakdown occurs at sweep rates just past optimal and map to a single stable point just off the Mathieu equation primary resonance stability boundary. Optimal AR sweep rates produce oscillating phase dierences with extrema near 90 degrees, allowing extended time in resonance. AR breakdown occurs when phase difference equals 180 degrees. Nonlinear resonance of the van der Pol type may play a role in the extraordinary sensitivity of the human ear. / The mechanism for maintaining the cochlear amplifier at its critical point is currently unknown. The possibility of open-loop control of cochlear operating point, maintaining criticality on average through periodically varying damping (super-regeneration) motivates a study of spontaneous otoacoustic emission (SOAE) amplitude modulation on a short (msec) time scale. An example of periodic amplitude modulation within a wide filter bandwidth is found that appears to be a beat oscillation of two SOAEs. / by Carey Witkov. / Thesis (Ph.D.)--Florida Atlantic University, 2011. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2011. Mode of access: World Wide Web.

University of Macau / Faculty of Science and Technology. / Department of Computer and Information Science

University of Macau / Faculty of Science and Technology. / Department of Computer and Information Science

by Cheung Wai-Hung Wellis. / Thesis (M.Sc.)--Chinese University of Hong Kong, 1992. / Includes bibliographical references (leaves 52-54). / ACKNOWLEDGEMENTS / ABSTRACT / Chapter 1 --- INTRODUCTION --- p.1 / Chapter 1.1 --- CLASSIFICATION OF CHARACTER RECOGNITION --- p.1 / Chapter 1.2 --- HISTORICAL DEVELOPMENT --- p.3 / Chapter 1.3 --- RECOGNITION METHODOLOGY --- p.4 / Chapter 2 --- ORGANIZATION OF THIS REPORT --- p.7 / Chapter 3 --- DATA SAMPLING --- p.8 / Chapter 3.1 --- GENERAL CONSIDERATION --- p.8 / Chapter 3.2 --- IMPLEMENTATION --- p.9 / Chapter 4 --- PREPROCESSING --- p.10 / Chapter 4.1 --- GENERAL CONSIDERATION --- p.10 / Chapter 4.2 --- IMPLEMENTATION --- p.12 / Chapter 4.2.1 --- Stroke connection --- p.12 / Chapter 4.2.2 --- Rotation --- p.12 / Chapter 4.2.3 --- Scaling --- p.14 / Chapter 4.2.4 --- De-skewing --- p.15 / Chapter 5 --- STROKE SEGMENTATION --- p.17 / Chapter 5.1 --- CONSIDERATION --- p.17 / Chapter 5.2 --- IMPLEMENTATION --- p.20 / Chapter 6 --- LEARNING --- p.26 / Chapter 7 --- PROTOTYPE MANAGEMENT --- p.27 / Chapter 8 --- RECOGNITION --- p.29 / Chapter 8.1 --- CONSIDERATION --- p.29 / Chapter 8.1.1 --- Delayed Stroke Tagging --- p.29 / Chapter 8.1.2 --- Bi-gram --- p.29 / Chapter 8.1.3 --- Character Scoring --- p.30 / Chapter 8.1.4 --- Ligature Handling --- p.32 / Chapter 8.1.5 --- Word Scoring --- p.32 / Chapter 8.2 --- IMPLEMENTATION --- p.33 / Chapter 8.2.1 --- Simple Matching --- p.33 / Chapter 8.2.2 --- Best First Search Matching --- p.33 / Chapter 8.2.3 --- Multiple Track Method --- p.35 / Chapter 8.3 --- SYSTEM PERFORMANCE TUNING --- p.37 / Chapter 9 --- POST-PROCESSING --- p.38 / Chapter 9.1 --- PROBABILITY MODEL --- p.38 / Chapter 9.2 --- WORD DICTIONARY APPROACH --- p.39 / Chapter 10 --- SYSTEM IMPLEMENTATION AND PERFORMANCE --- p.41 / Chapter 11 --- DISCUSSION --- p.43 / Chapter 12 --- EPILOG --- p.47 / Chapter APPENDIX I - --- PROBLEMS ENCOUNTERED AND SUGGESTED ENHANCEMENTS ON THE SYSTEM --- p.48 / Chapter APPENDIX II - --- GLOSSARIES --- p.51 / REFERENCES --- p.52

Lam, Hiu Man. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2013. / Includes bibliographical references (leaves 143-148). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts also in Chinese.