Limitations of Non Model-Based Recognition Schemes

Different approaches to visual object recognition can be divided into two general classes: model-based vs. non model-based schemes. In this paper we establish some limitation on the class of non model-based recognition schemes. We show that every function that is invariant to viewing position of all objects is the trivial (constant) function. It follows that every consistent recognition scheme for recognizing all 3-D objects must in general be model based. The result is extended to recognition schemes that are imperfect (allowed to make mistakes) or restricted to certain classes of objects.

View-Based Models of 3D Object Recognition and Class-Specific Invariances

This paper describes the main features of a view-based model of object recognition. The model tries to capture general properties to be expected in a biological architecture for object recognition. The basic module is a regularization network in which each of the hidden units is broadly tuned to a specific view of the object to be recognized.

Pose-Invariant Face Recognition Using Real and Virtual Views

The problem of automatic face recognition is to visually identify a person in an input image. This task is performed by matching the input face against the faces of known people in a database of faces. Most existing work in face recognition has limited the scope of the problem, however, by dealing primarily with frontal views, neutral expressions, and fixed lighting conditions. To help generalize existing face recognition systems, we look at the problem of recognizing faces under a range of viewpoints. In particular, we consider two cases of this problem: (i) many example views are available of each person, and (ii) only one view is available per person, perhaps a driver's license or passport photograph. Ideally, we would like to address these two cases using a simple view-based approach, where a person is represented in the database by using a number of views on the viewing sphere. While the view-based approach is consistent with case (i), for case (ii) we need to augment the single real view of each person with synthetic views from other viewpoints, views we call 'virtual views'. Virtual views are generated using prior knowledge of face rotation, knowledge that is 'learned' from images of prototype faces. This prior knowledge is used to effectively rotate in depth the single real view available of each person. In this thesis, I present the view-based face recognizer, techniques for synthesizing virtual views, and experimental results using real and virtual views in the recognizer.

The Role of Fixation and Visual Attention in Object Recognition

This research project is a study of the role of fixation and visual attention in object recognition. In this project, we build an active vision system which can recognize a target object in a cluttered scene efficiently and reliably. Our system integrates visual cues like color and stereo to perform figure/ground separation, yielding candidate regions on which to focus attention. Within each image region, we use stereo to extract features that lie within a narrow disparity range about the fixation position. These selected features are then used as input to an alignment-style recognition system. We show that visual attention and fixation significantly reduce the complexity and the false identifications in model-based recognition using Alignment methods. We also demonstrate that stereo can be used effectively as a figure/ground separator without the need for accurate camera calibration.

Three-Dimensional Recognition of Solid Objects from a Two-Dimensional Image

This thesis addresses the problem of recognizing solid objects in the three-dimensional world, using two-dimensional shape information extracted from a single image. Objects can be partly occluded and can occur in cluttered scenes. A model based approach is taken, where stored models are matched to an image. The matching problem is separated into two stages, which employ different representations of objects. The first stage uses the smallest possible number of local features to find transformations from a model to an image. This minimizes the amount of search required in recognition. The second stage uses the entire edge contour of an object to verify each transformation. This reduces the chance of finding false matches.

Automatic point correspondence and registration based on linear structures

R. Marti, R. Zwiggelaar, C.M.E. Rubin, 'Automatic point correspondence and registration based on linear structures', International Journal of Pattern Recognition and Artificial Intelligence 16 (3), 331-340 (2002)

Learning Embeddings for Indexing, Retrieval, and Classification, with Applications to Object and Shape Recognition in Image Databases

Nearest neighbor retrieval is the task of identifying, given a database of objects and a query object, the objects in the database that are the most similar to the query. Retrieving nearest neighbors is a necessary component of many practical applications, in fields as diverse as computer vision, pattern recognition, multimedia databases, bioinformatics, and computer networks. At the same time, finding nearest neighbors accurately and efficiently can be challenging, especially when the database contains a large number of objects, and when the underlying distance measure is computationally expensive. This thesis proposes new methods for improving the efficiency and accuracy of nearest neighbor retrieval and classification in spaces with computationally expensive distance measures. The proposed methods are domain-independent, and can be applied in arbitrary spaces, including non-Euclidean and non-metric spaces. In this thesis particular emphasis is given to computer vision applications related to object and shape recognition, where expensive non-Euclidean distance measures are often needed to achieve high accuracy. The first contribution of this thesis is the BoostMap algorithm for embedding arbitrary spaces into a vector space with a computationally efficient distance measure. Using this approach, an approximate set of nearest neighbors can be retrieved efficiently - often orders of magnitude faster than retrieval using the exact distance measure in the original space. The BoostMap algorithm has two key distinguishing features with respect to existing embedding methods. First, embedding construction explicitly maximizes the amount of nearest neighbor information preserved by the embedding. Second, embedding construction is treated as a machine learning problem, in contrast to existing methods that are based on geometric considerations. The second contribution is a method for constructing query-sensitive distance measures for the purposes of nearest neighbor retrieval and classification. In high-dimensional spaces, query-sensitive distance measures allow for automatic selection of the dimensions that are the most informative for each specific query object. It is shown theoretically and experimentally that query-sensitivity increases the modeling power of embeddings, allowing embeddings to capture a larger amount of the nearest neighbor structure of the original space. The third contribution is a method for speeding up nearest neighbor classification by combining multiple embedding-based nearest neighbor classifiers in a cascade. In a cascade, computationally efficient classifiers are used to quickly classify easy cases, and classifiers that are more computationally expensive and also more accurate are only applied to objects that are harder to classify. An interesting property of the proposed cascade method is that, under certain conditions, classification time actually decreases as the size of the database increases, a behavior that is in stark contrast to the behavior of typical nearest neighbor classification systems. The proposed methods are evaluated experimentally in several different applications: hand shape recognition, off-line character recognition, online character recognition, and efficient retrieval of time series. In all datasets, the proposed methods lead to significant improvements in accuracy and efficiency compared to existing state-of-the-art methods. In some datasets, the general-purpose methods introduced in this thesis even outperform domain-specific methods that have been custom-designed for such datasets.

View-Invariant Object Category Learning, Recognition, and Search: How Spatial and Object Attention Are Coordinated Using Surface-Based Attentional Shrouds

Air Force Office of Scientific Research (F49620-01-1-0397); National Science Foundation (SBE-0354378); Office of Naval Research (N00014-01-1-0624)

Large-Scale Neural Systems for Vision and Cognition

— Consideration of how people respond to the question What is this? has suggested new problem frontiers for pattern recognition and information fusion, as well as neural systems that embody the cognitive transformation of declarative information into relational knowledge. In contrast to traditional classification methods, which aim to find the single correct label for each exemplar (This is a car), the new approach discovers rules that embody coherent relationships among labels which would otherwise appear contradictory to a learning system (This is a car, that is a vehicle, over there is a sedan). This talk will describe how an individual who experiences exemplars in real time, with each exemplar trained on at most one category label, can autonomously discover a hierarchy of cognitive rules, thereby converting local information into global knowledge. Computational examples are based on the observation that sensors working at different times, locations, and spatial scales, and experts with different goals, languages, and situations, may produce apparently inconsistent image labels, which are reconciled by implicit underlying relationships that the network’s learning process discovers. The ARTMAP information fusion system can, moreover, integrate multiple separate knowledge hierarchies, by fusing independent domains into a unified structure. In the process, the system discovers cross-domain rules, inferring multilevel relationships among groups of output classes, without any supervised labeling of these relationships. In order to self-organize its expert system, the ARTMAP information fusion network features distributed code representations which exploit the model’s intrinsic capacity for one-to-many learning (This is a car and a vehicle and a sedan) as well as many-to-one learning (Each of those vehicles is a car). Fusion system software, testbed datasets, and articles are available from http://cns.bu.edu/techlab.

Participation by place-based community organisations in local development: case studies from East Cork

The past two decades have witnessed concerted efforts by theorists and policy-makers to place civil society at the centre of social, economic and environmental development processes. To this end, policies grounded in a Third Way approach have sought to forge stronger linkages between the state and voluntary community-based organisations. Concepts such as active citizenship, social capital, partnership and sustainability have underpinned this political philosophy, which reflects a movement in development theory and political science away from notions of state-led development and unfettered neo-liberalism. In the Irish context, a series of initiatives have given expression to this new policy agenda, the foremost amongst them the publication of a White Paper in 2000. New local governance structures and development schemes have multiplied since the early 1990s, while the physical planning system has also been modified. All this has taken place against the backdrop of unprecedented economic development and social change precipitated by the ‘Celtic Tiger’.This thesis examines the interaction between community organisations, state institutions and other actors in development processes in East Cork. It focuses upon place-based community organisations, who seek to represent the interests of their particular localities. A case study approach is employed to explore the realpolitik of local development and to gauge the extent to which grassroots community organisations wield influence in determining the development of their communities. The study concludes that the transfer of decision-making power to community organisations has been more illusory than real and that, in practical terms, such groups remain marginal in the circuits of power. However, the situation of community organisations operating in different geographical locales cannot be reduced to an overarching theoretical logic. The case studies show that the modus operandi of community groups varies considerably and can be influenced by specific local geographies, events and personalities.

Silica bonded stationary phases: Innovative functionalization methods and novel chromatographic separations based on molecular recognition

The research work included in this thesis examines the synthesis, characterization and chromatographic evaluation of novel bonded silica stationary phases. Innovative methods of preparation of silica hydride intermediates and octadecylsilica using a “green chemistry” approach eliminate the use of toxic organic solvents and exploit the solvating power and enhanced diffusivity of supercritical carbon dioxide to produce phases with a surface coverage of bonded ligands which is comparable to, or exceeds, that achieved using traditional organic solvent-based methods. A new stationary phase is also discussed which displays chromatographic selectivity based on molecular recognition. Chapter 1 introduces the chemistry of silica stationary phases, the retention mechanisms and theories on which reversed-phase liquid chromatography and hydrophilic interaction chromatograpy are based, the art and science of achieving a well packed liquid chromatography column, the properties of supercritical carbon dioxide and molecular recognition chemistry. Chapter 2 compares the properties of silica hydride materials prepared using supercritical carbon dioxide as the reaction medium with those synthesized in an organic solvent. A higher coverage of hydride groups on the silica surface is seen when a monofunctional silane is reacted in supercritical carbon dioxide while trifunctional silanes result in a phase which exhibits different properties depending on the reaction medium used. The differing chromatographic behaviour of these silica hydride materials prepared using supercritical carbon dioxide and using organic solvent are explored in chapter 3. Chapter 4 focusses on the preparation of octadecylsilica using mono-, di- and trifunctional alkoxysilanes in supercritical carbon dioxide and in anhydrous toluene. The surface coverage of octadecyl groups, as calculated using thermogravimetric analysis and elemental analysis, is highest when a trifunctional alkoxysilane is reacted with silica in supercritical carbon dioxide. A novel silica stationary phase is discussed in chapter 5 which displays selectivity for analytes based on their hydrogen bonding capabilities. The phase is also highly selective for barbituric acid and may have a future application in the solid phase extraction of barbiturates from biological samples.