This thesis establishes a stochastic framework for tracking curves in visual clutter, using a Bayesian random-sampling algorithm. The approach is rooted in ideas from statistics, control theory and computer vision. The problem is to track outlines and features of foreground objects, modelled as curves, as they move in substantial clutter, and to do it at, or close to, video frame-rate. The algorithm, named Condensation, for Conditional density propagation, has recently been derived independently by several researchers, and is generating signi cant interest in the statistics and signal processing communities. This thesis contributes to the literature on Condensation-like lters by presenting some novel applications of and extensions to the basic algorithm, and contributes to the visual motion estimation literature by demonstrating high tracking performance in cluttered environments. Despite its power the Condensation algorithm has a remarkably simple form and this allows the use of non-linear motion models which combine characteristics of discrete Hidden Markov Models with the continuous Auto-Regressive Process motion models traditionally used in Kalman lters. These mixed discrete-continuous models have promising applications to the emerging eld of perception of action. This thesis also implements two algorithms to smooth the output of the Condensation lter which improves the accuracy of motion estimation in a batch-mode procedure after tracking is complete.

We develop a novel time-selection strategy for iterative image restoration techniques: the stopping time is chosen so that the correlation of signal and noise in the filtered image is minimised. The new method is applicable to any images where the noise to be removed is uncorrelated with the signal; no other knowledge (e.g. the noise variance, training data etc.) is needed. We test the performance of our time estimation procedure experimentally, and demonstrate that it yields near-optimal results for a wide range of noise levels and for various filtering methods.

This paper presents a watermarking scheme for copyright protection of digital images. A binary logo is the copyright label which is embedded in grayscale or color digital images. A set of integer parameters, selected by the legal owner, controls the watermarking algorithm via a strongly chaotic (mixing) system. Watermark detection is performed without resorting to the original image. The embedded binary logo is reconstructed or the statistical detection certainty is provided indicating the watermark existence. Numerical experiments testify the efficiency of a particular watermarking algorithm as a reliable verification tool for proving copyright ownership of the digital image. 1 Introduction Copyright protection of digital images, audio and video, is a novel and very interesting research topic. The technology of digital services grows rapidly and distributed access to such services through computer networks is a matter of urgency. However, network access does not protect the intellect...

Can stochastic search algorithms outperform existing deterministic heuristics for the NP-hard problem Number Partitioning if given a sufficient, but practically realizable amount of time? In a thorough empirical investigation using a straightforward implementation of one such algorithm, simulated annealing, Johnson et al. (1991) concluded tentatively that the answer is "no." In this paper we show that the answer can be "yes" if attention is devoted to the issue of problem representation (encoding). We present results from empirical tests of several encodings of Number Partitioning with problem instances consisting of multiple-precision integers drawn from a uniform probability distribution. With these instances and with an appropriate choice of representation, stochastic and deterministic searches can---routinely and in a practical amount of time---find solutions several orders of magnitude better than those constructed by the best heuristic known (Karmarkar and Karp, 1982), which does...

The shape of if-part fuzzy sets affects how well feedforward fuzzy systems approximate continuous functions. We explore a wide range of candidate if-part sets and derive supervised learning laws that tune them. Then we test how well the resulting adaptive fuzzy systems approximate a battery of test functions. No one set shape emerges as the best shape. The sinc function often does well and has a tractable learning law. But its undulating sidelobes may have no linguistic meaning. This suggests that the engineering goal of function-approximation accuracy may sometimes have to outweigh the linguistic or philosophical interpretations of fuzzy sets that have accompanied their use in expert systems. We divide the if-part sets into two large classes. The first class consists of-dimensional joint sets that factor into scalar sets as found in almost all published fuzzy systems. These sets ignore the correlations among vector components of input vectors. Fuzzy systems that use factorable if-part sets suffer in general from exponential rule explosion in high dimensions when they blindly approximate functions without knowledge of the functions. The factorable fuzzy sets themselves also suffer from what we call the second curse of dimensionality: The fuzzy sets tend to become binary spikes in high dimension. The second class of if-part sets consists of the more general but less common-dimensional joint sets that do not factor into scalar fuzzy sets. We present a method for constructing such unfactorable joint sets from scalar distance measures. Fuzzy systems that use unfactorable if-part sets need not suffer from exponential rule explosion but their increased complexity may lead to intractable learning laws and inscrutable if-then rules. We prove that some of these unfactorable join...

This paper shows how adaptive systems can learn to add an optimal amount of noise to some nonlinear feedback systems. Noise can improve the signal-to-noise ratio of many nonlinear dynamical systems. This "stochastic resonance" effect occurs in a wide range of physical and biological systems. The SR effect may also occur in engineering systems in signal processing, communications, and control. The noise energy can enhance the faint periodic signals or faint broadband signals that force the dynamical systems. Most SR studies assume full knowledge of a system's dynamics and its noise and signal structure. Fuzzy and other adaptive systems can learn to induce SR based only on samples from the process. These samples can tune a fuzzy system's if-then rules so that the fuzzy system approximates the dynamical system and its noise response. The paper derives the SR optimality conditions that any stochastic learning system should try to achieve. The adaptive system learns the SR effect as the sys...

An automatic compound retrieval method is proposed to extract compounds within a text message. It uses n-gram mutual information, relative frequency count and parts of speech as the features for compound extraction. The problem is modeled as a two-class classification problem based on the distributional characteristics of n-gram tokens in the compound and the non-compound clusters. The recall and precision using the proposed approach are 96.2% and 48.2% for bigram compounds and 96.6% and 39.6% for trigram compounds for a testing corpus of 49,314 words. A significant cutdown in processing time has been observed.

The power of sampling methods in Bayesian reconstruction of noisy signals is well known. The extension of sampling to temporal problems is discussed. Efficacy of sampling over time is demonstrated with visual tracking.

The rise of social media sites — blogs, wikis, and Digg — underscores the transformation of the Web to a participatory medium in which users are collaboratively creating, evaluating and distributing information. The innovations introduced by social media have lead to a new paradigm for interacting with information: social information processing. We study how the social news aggregator Digg exploits social information processing to solve the problems of document recommendation and rating. First, we show that social networks play an important role in document recommendation. The second contribution of this paper consists of a mathematical model that describes how collaborative evaluation of documents emerges from the independent decisions made by many users. The model takes into account users behavior: e.g., whether they are reading stories on the front page or through a Friends interface. Solutions of the model reproduce the observed ratings received by actual stories on Digg. 1

DPDF OF STANDARD HMM This paper presents research on integrating context-dependent durational knowledge into HMM-based speech recognition. The first part of the paper presents work on obtaining relations between the parameters of the context-free HMMs and their durational behaviour, in preparation for the context-dependent durational modelling presented in the second part. Duration integration is realised via rescoring in the post-processing step of our N-best monophone recogniser. We use the multi-speaker TIMIT database for our analyses.