Isoperimetric Graph Partitioning for Data Clustering and Image Segmentation

Spectral methods of graph partitioning have been shown to provide a powerful approach to the image segmentation problem. In this paper, we adopt a different approach, based on estimating the isoperimetric constant of an image graph. Our algorithm produces the high quality segmentations and data clustering of spectral methods, but with improved speed and stability.

The What-And-Where Filter: A Spatial Mapping Neural Network for Object Recognition and Image Understanding

The What-and-Where filter forms part of a neural network architecture for spatial mapping, object recognition, and image understanding. The Where fllter responds to an image figure that has been separated from its background. It generates a spatial map whose cell activations simultaneously represent the position, orientation, ancl size of all tbe figures in a scene (where they are). This spatial map may he used to direct spatially localized attention to these image features. A multiscale array of oriented detectors, followed by competitve and interpolative interactions between position, orientation, and size scales, is used to define the Where filter. This analysis discloses several issues that need to be dealt with by a spatial mapping system that is based upon oriented filters, such as the role of cliff filters with and without normalization, the double peak problem of maximum orientation across size scale, and the different self-similar interpolation properties across orientation than across size scale. Several computationally efficient Where filters are proposed. The Where filter rnay be used for parallel transformation of multiple image figures into invariant representations that are insensitive to the figures' original position, orientation, and size. These invariant figural representations form part of a system devoted to attentive object learning and recognition (what it is). Unlike some alternative models where serial search for a target occurs, a What and Where representation can he used to rapidly search in parallel for a desired target in a scene. Such a representation can also be used to learn multidimensional representations of objects and their spatial relationships for purposes of image understanding. The What-and-Where filter is inspired by neurobiological data showing that a Where processing stream in the cerebral cortex is used for attentive spatial localization and orientation, whereas a What processing stream is used for attentive object learning and recognition.

The Practice and Understanding of the Eucharist in the United Church of Christ: A Practical Theological Study

This dissertation explores the complexity of the understanding and practice of the Eucharist in the United Church of Christ as revealed in a textual analysis of the UCC Book of Worship (1986) and a qualitative study of five representative UCC congregations. Little has been written on this topic, save for several brief articles on the history of the theology of the sacrament in the two bodies that merged to form the UCC in 1957: the Congregational Christian Churches (CC) and the Evangelical and Reformed Church (E&R). This dissertation advances the topic through a practical-theological study that brings into critical conversation contemporary eucharistic practices in five congregations and a historical theological analysis of liturgical traditions in the UCC and antecedent denominations. Through this conversation, the study articulates common themes of a UCC eucharistic theology and explores implications for ongoing theology and practice in the denomination. The introduction explicates the methodology employed in this study, guided by Don Browning's work. The first two chapters present the findings of the focus group interviews and an interpretation of those results respectively. Chapter three analyzes the eucharistic liturgies in three historic books of worship used in the E&R heritage. In chapter four, two of the antecedent resources utilized in the CC tradition are analyzed. The short-lived Hymnal of the United Church of Christ, published in 1974, includes liturgies that would find fuller expression in the 1986 Book of Worship. That hymnal is examined in chapter five. Chapter six interprets the two services of "Word and Sacrament" found in the Book of Worship. Chapter seven offers a comparative analysis of the focus group findings and the theology inherent in the Book of Worship. The final chapter offers strategic recommendations for revised theory and practice. The conclusion points toward areas for further research: it propels a critical conversation around the notion of covenant, Christ's presence in the meal, and who can receive and officiate at the Eucharist. This dissertation concludes that the UCC lives within a balance of multiple, complementary theologies and challenges the denomination to make stronger connections between the meal and mission, reconciliation, and tradition.

Color Region Grouping and Shape Recognition with Deformable Models

A new deformable shape-based method for color region segmentation is described. The method includes two stages: over-segmentation using a traditional color region segmentation algorithm, followed by deformable model-based region merging via grouping and hypothesis selection. During the second stage, region merging and object identification are executed simultaneously. A statistical shape model is used to estimate the likelihood of region groupings and model hypotheses. The prior distribution on deformation parameters is precomputed using principal component analysis over a training set of region groupings. Once trained, the system autonomously segments deformed shapes from the background, while not merging them with similarly colored adjacent objects. Furthermore, the recovered parametric shape model can be used directly in object recognition and comparison. Experiments in segmentation and image retrieval are reported.

Example-Based Image Restoration via Boosted Classifiers

We propose a novel image registration framework which uses classifiers trained from examples of aligned images to achieve registration. Our approach is designed to register images of medical data where the physical condition of the patient has changed significantly and image intensities are drastically different. We use two boosted classifiers for each degree of freedom of image transformation. These two classifiers can both identify when two images are correctly aligned and provide an efficient means of moving towards correct registration for misaligned images. The classifiers capture local alignment information using multi-pixel comparisons and can therefore achieve correct alignments where approaches like correlation and mutual-information which rely on only pixel-to-pixel comparisons fail. We test our approach using images from CT scans acquired in a study of acute respiratory distress syndrome. We show significant increase in registration accuracy in comparison to an approach using mutual information.