We present an approach for image database retrieval using a very large number of highly-selective features and simple on-line learning. Our approach is predicated on the assumption that each image is generated by a sparse set of visual "causes" and that images which are visually similar share causes. We propose a mechanism for generating a large number of complex features which capture some aspects of this causal structure. Boosting is used to learn simple and efficient classifiers in this complex feature space. Finally we will describe a practical implementation of our retrieval system on a database of 3000 images.

In this thesis we study the general problem of reconstructing a function, defined on a finite lattice from a set of incomplete, noisy and/or ambiguous observations. The goal of this work is to demonstrate the generality and practical value of a probabilistic (in particular, Bayesian) approach to this problem, particularly in the context of Computer Vision. In this approach, the prior knowledge about the solution is expressed in the form of a Gibbsian probability distribution on the space of all possible functions, so that the reconstruction task is formulated as an estimation problem. Our main contributions are the following: (1) We introduce the use of specific error criteria for the design of the optimal Bayesian estimators for several classes of problems, and propose a general (Monte Carlo) procedure for approximating them. This new approach leads to a substantial improvement over the existing schemes, both regarding the quality of the results (particularly for low signal to noise ratios) and the computational efficiency. (2) We apply the Bayesian appraoch to the solution of several problems, some of which are formulated and solved in these terms for the first time. Specifically, these applications are: teh reconstruction of piecewise constant surfaces from sparse and noisy observationsl; the reconstruction of depth from stereoscopic pairs of images and the formation of perceptual clusters. (3) For each one of these applications, we develop fast, deterministic algorithms that approximate the optimal estimators, and illustrate their performance on both synthetic and real data. (4) We propose a new method, based on the analysis of the residual process, for estimating the parameters of the probabilistic models directly from the noisy observations. This scheme leads to an algorithm, which has no free parameters, for the restoration of piecewise uniform images. (5) We analyze the implementation of the algorithms that we develop in non-conventional hardware, such as massively parallel digital machines, and analog and hybrid networks.

Wireless Sensor Networks (WSNs) are rapidly gaining popularity in various critical domains like health care, critical infrastructure, and climate monitoring, where application builders have diversified development needs. Independent of the functionalities provided by the WSN applications, many of the developers use visualization, simulation, and programming tools. However, these tools are designed as separate stand-alone applications, which force developers to use multiple tools. This situation often poses confusion and hampers an efficient development experience. To avoid the complexity of using multiple tools, a new, extensible, multi-platform, scalable, and open-source framework called PROVIZ is designed. PROVIZ is an integrated visualization and programming framework with the following features: PROVIZ 1) visualizes sensor nodes and WSN traffic by parsing the data received either from a packet sniffer (e.g., a sensor-based sniffer, or a commercial TI SmartRF 802.15.4 packet sniffer), or from a simulator (e.g., OMNeT); 2) visualizes a heterogeneous WSN consisting of different sensor nodes sending packets with different packet payload formats; and 3) provides a programming framework, which provides a graphical and script-based programming functionality, for developing WSN applications. Also, PROVIZ includes built-in extensible visual demo deployment capabilities that allow users to quickly craft network scenarios and share them with other users. Additionally, a secure and energy efficient wireless code dissemination protocol, named SIMAGE, was developed. SIMAGE is used by PROVIZ to wirelessly reprogram the sensor nodes. SIMAGE uses a link quality cognizant adaptive packet-sizing technique along with energy-efficient encryption protocols for secure and efficient code dissemination. In this thesis, the various features of PROVIZ's visualization and programming framework are explained, the functionality and performance of SIMAGE protocol is described, an example WSN security attack scenario is analyzed, and how PROVIZ can be used as a visual debugging tool to identify the security attack and aid in providing a software fix are discussed.