The perceptual recognition of objects is conceptualized to be a process in which the image of the input is segmented at regions of deep concavity into an arrangement of simple geometric components, such as blocks, cylinders, wedges, and cones. The fundamental assumption of the proposed theory, recognition-by-components (RBC), is that a modest set of generalized-cone components, called geons (N ^ 36), can be derived from contrasts of five readily detectable properties of edges in a two-dimensional image: curvature, collinearity, symmetry, parallelism, and cotermmation. The detection of these properties is generally invariant over viewing position and image quality and consequently allows robust object perception when the image is projected from a novel viewpoint or is degraded. RBC thus provides a principled account of the heretofore undecided relation between the classic principles of perceptual organization and pattern recognition: The constraints toward regularization (Pragnanz) characterize not the complete object but the object's components. Representational power derives from an allowance of free combinations of the geons. A Principle of Componential Recovery can account for the major phenomena of object recognition: If an arrangement of two or three geons can be recovered from the input, objects can be quickly recognized even when they are occluded, novel, rotated in depth, or extensively degraded. The results from experiments on the perception of briefly presented pictures by human observers provide empirical support for the theory. Any single object can project an infinity of image configura-tions to the retina. The orientation of the object to the viewer can vary continuously, each giving rise to a different two-dimen-sional projection. The object can be occluded by other objects or texture fields, as when viewed behind foliage. The object need not be presented as a full-colored textured image but in-stead can be a simplified line drawing. Moreover, the object can even be missing some of its parts or be a novel exemplar of its

Belief networks are directed acyclic graphs in which the nodes represent propositions (or variables), the arcs signify direct dependencies between the linked propositions, and the strengths of these dependencies are quantified by conditional probabilities. A network of this sort can be used to represent the generic knowledge of a domain expert, and it turns into a computational architecture if the links are used not merely for storing factual knowledge but also for directing and activating the data flow in the computations which manipulate this knowledge. The first part of the paper deals with the task of fusing and propagating the impacts of new information through the networks in such a way that, when equilibrium is reached, each proposition will be assigned a measure of belief consistent with the axioms of probability theory. It is shown that if the network is singly connected (e.g. tree-structured), then probabilities can be updated by local propagation in an isomorphic network of parallel and autonomous processors and that the impact of new information can be imparted to all propositions in time proportional to the longest path in the network. The second part of the paper deals with the problem of finding a tree-structured representation for a collection of probabilistically coupled propositions using auxiliary (dummy) variables, colloquially called "hidden causes. " It is shown that if such a tree-structured representation exists, then it is possible to uniquely uncover the topology of the tree by observing pairwise dependencies among the available propositions (i.e., the leaves of the tree). The entire tree structure, including the strengths of all internal relationships, can be reconstructed in time proportional to n log n, where n is the number of leaves.

Consistency techniques have been studied extensively in the past as a way of tackling constraint satisfaction problems (CSP). In particular, various arc-consistency algorithms have been proposed, originating from Waltz's filtering algorithm [26] and culminating in the optimal algorithm AC-4 of Mohr and Henderson [15]. AC-4 runs in O(ed 2 ) in the worst case, where e is the number of arcs (or constraints) and d is the size of the largest domain. Being applicable to the whole class of (binary) CSP, these algorithms do not take into account the semantics of constraints. In this paper, we present a new generic arc-consistency algorithm AC-5. This algorithm is parametrized on two specified procedures and can be instantiated to reduce to AC-3 and AC-4. More important, AC-5 can be instantiated to produce an O(ed) algorithm for a number of important classes of constraints: functional, anti-functional, monotonic and their generalization to (functional, anti-functional, and monotonic) piecewise constraints. We also show that AC-5 has an important application in constraint logic programming over finite domains [23]. The kernel of the constraint solver for such a programming language is an arc-consistency algorithm for a set of basic constraints. We prove that AC-5, in conjunction with node consistency, provides a decision procedure for these constraints running in time O(ed).

Many problems can be expressed in terms of a numeric constraint satisfaction problem over finite or continuous domains (numeric CSP). The purpose of this paper is to show that the consistency techniques that have been developed for CSPs can be adapted to numeric CSPs. Since the numeric domains are ordered the underlying idea is to handle domains only by their bounds. The semantics that have been elaborated, plus the complexity analysis and good experimental results, confirm that these techniques can be used in real applications. 1

Abstract — Two forms of cooperation in distributed problem solving are considered: task-sharing and result-sharing. In the former, nodes assist each other by sharing the computational load for the execution of subtasks of the overall problem. In the latter, nodes assist each other by sharing partial results which are based on somewhat different perspectives on the overall problem. Different perspectives arise because the nodes use different knowledge sources (KS’s) (e.g., syntax versus acoustics in the case of a speech-understanding system) or different data (e.g., data that is sensed at different locations in the case of a distributed sensing system). Particular attention is given to control and to internode communication for the two forms of cooperation. For each, the basic methodology is presented and systems in which it has been used are described. The two forms are then compared and the types of applications for which they are suitable are considered. I. DISTRIBUTED PROBLEM SOLVING

Introduction 1.1 Preliminaries Constraint programming is an alternative approach to programming in which the programming process is limited to a generation of requirements (constraints) and a solution of these requirements by means of general or domain specific methods. The general methods are usually concerned with techniques of reducing the search space and with specific search methods. In contrast, the domain specific methods are usually provided in the form of special purpose algorithms or specialised packages, usually called constraint solvers. Typical examples of constraint solvers are: ffl a program that solves systems of linear equations, ffl a package for linear programming, ffl an implementation of the unification algorithm, a cornerstone of automated theorem proving. Problems that can be solved in a natural way by means of constraint programming are usually those for which efficient algorithms are

Constraint programming is newly flowering in industry. Several companies have recently started up to exploit the technology, and the number of industrial applications is now growing very quickly. This survey will seek, by examples,

. We show that several constraint propagation algorithms (also called (local) consistency, consistency enforcing, Waltz, filtering or narrowing algorithms) are instances of algorithms that deal with chaotic iteration. To this end we propose a simple abstract framework that allows us to classify and compare these algorithms and to establish in a uniform way their basic properties. Note. This is a full, revised version of our article "From Chaotic Iteration to Constraint Propagation", Proc. of 24th International Colloquium on Automata, Languages and Programming (ICALP '97), (invited lecture) , Springer-Verlag Lecture Notes in Computer Science 1256, pp. 3655, (1997). Keywords: constraint propagation, chaotic iteration, generic algorithms. 1 Introduction 1.1 Motivation Over the last ten years constraint programming emerged as an interesting and viable approach to programming. In this approach the programming process is limited to a generation of requirements ("constraints") and a solut...

Constraint logic programming (CLP) is a new class of declarative programming lan-guages whose primitive operations are based on constraints (e.g. constraint solving and constraint entailment). CLP languages naturally combine constraint propagation with nondeterministic choices. As a consequence, they are particularly appropriate for solv-ing a variety of combinatorial search problems, using the global search paradigm, with short development time and efficiency comparable to procedural tools based on the same approach. In this paper, we describe how the CLP language cc(FD), a successor of CHIP using consistency techniques over finite domains, can be used to solve two practical applications: test-pattern generation and car sequencing. For both applications, we present the cc(FD) program, describe how constraint solving is performed, report experimental results, and compare the approach with existing tools.

Understanding how line drawings convey tri-dimensionality is of fundamental importance in explaining surface perception when photometry is either uninformative or too compex to model analytically. We put forward here a computational model for interpreting line drawings as three-dimensional surfaces, based on constraints on local surface orientation along extremal and discontinuity boundaries. Specific techniques are described for two key processes recovering the three-dimensional conformation of a space curve (e.g., a surface boundary) from its two-dimensional projection in an image, and interpolating smooth surfaces from orientation constraints along extremal boundaries. The relevance of the model to a general theory of low-level vision is discussed.