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

Abstract not found

In theoretical analyses of visual form perception, it is often assumed that the 3-dimensional structures of smoothly curved surfaces are perceptually represented as point-by-point mappings of metric depth and/or orientation relative to the observer. This article describes an alternative theory in which it is argued that our visual knowledge of smoothly curved surfaces can also be denned in terms of local, nonmetric order relations. A fundamental prediction of this analysis is that relative depth judgments between any two surface regions should be dramatically influenced by the monotonicity of depth change (or lack of it) along the intervening portions of the surface through which they are separated. This prediction is confirmed in a series of experiments using surfaces depicted with either shading or texture. Additional experiments are reported, moreover, that demonstrate that smooth occlusion contours are a primary source of information about the ordinal structure of a surface and that the depth extrema in between contours can be optically specified by differences in luminance at the points of occlusion. For many higher organisms, including humans, a primary source of knowledge about objects and events in the surrounding environment is provided by vision. Because of the ecological

this paper, we propose the short-cut rule, which states that, other things being equal, human vision prefers to use the shortest possible cuts to parse silhouettes. We motivate this rule, and the well-known Petters rule for modal completion, by the principle of transversality. We present five psychophysical experiments that test the short-cut rule, show that it successfully predicts part cuts which connect boundary points given by the minima rule, and show that it can also create new boundary points

The use of outline shape in recognizing objects was investigated in four experiments. In Experiment 1, subjects matched a shaded image to either another shaded image or a silhouette. In Experiment 2, subjects initially named shaded images; later they named either shaded images or silhouettes. Performance in both experiments was predicted by changes in the outline shape of the stimuli. The same matching (Experiment 3) and priming (Experiment 4) paradigms were then used to investigate recognition with objects that were rotated between presentations so as to change the outline shape of the object. Recognition was predicted by changes to outline shape. These results place constraints on models of object recognition, and are most compatible with viewpoint-dependent models of recognition.

A system for part-based segmentation of range data and their interpretation as a composition of deformable superquadrics is described. Segmentation and reconstruction phases are performed using the same algorithm at different scales. First, the data set is partitioned in regions corresponding approximately to simple convex objects, and then single deformable models are fitted to each region. Refinements of the model can be achieved by recursively applying the method. The proposed Moving Target (MT) algorithm is an original variation of the well known approach by Solina, ideated to avoid the classical inconvenient of the minimization procedure where the solution escapes the global minimum and/or gets stuck in a local one. Motivations of the proposed approach along with its theoretical formulation are presented and discussed in detail. The whole system has been validated using a several range images.

Many objects have component parts, and these parts often differ in their visual salience. In this paper we present a theory of part salience. The theory builds on the minima rule for defining part boundaries. According to this rule, human vision defines part boundaries at negative minima of curvature on silhouettes, and along negative minima of the principal curvatures on surfaces. We propose that the salience of a part depends on (at least) three factors: its size relative to the whole object, the degree to which it protrudes, and the strength of its boundaries. We present evidence that these factors influence visual processes which determine the choice of figure and ground. We give quantitative definitions for the factors, visual demonstrations of their effects, and results of psychophysical experiments. 1997 Elsevier Science B.V.

this paper, we will address the questionof whetherparsing at negativeminima of curvature occurs preattentively --- or at least, rapidly and early in visual processing. Traditionally, the processing of certain visual features has been 1039 Copyright 2002 Psychonomic Society, Inc. Y.X. is supported by a McDonnell-Pew Investigator Initiated Grant and M.S. by NSF BCS-0216944.For many useful discussions, we thank Bart Anderson, Roland Fleming, Don Hoffman, and Mary C. Potter. We also thank Bart Anderson for his kind support at M.I.T. Correspondence concerning this article may be addressed either to Y. Xu, Vision Sciences Laboratory, Psychology Department, Harvard University, Cambridge, MA 02138 (e-mail: yaoda@wjh.harvard. edu) or to M. Singh, Department of Psychology, Rutgers University, New Brunswick Campus, 152 FrelinghuysenRoad, Piscataway, NJ 08854-8020(e-mail: manish @ruccs.rutgers.edu)

We investigated perceptual segmentation in the context of a perceived-orientation task. Stimuli were dot clusters formed by the union of a large elliptical sub-cluster and a secondary circular sub-cluster. We manipulated the separation between the two sub-clusters, their common dot density, and the size of the secondary sub-cluster. As the separation between sub-clusters increased, the orientation perceived by observers shifted gradually from the global principal axis of the entire cluster to that of the main sub-cluster alone. Thus, with increasing separation, the dots within the secondary sub-cluster were assigned systematically lower weights in the principal-axis computation. In addition, this shift occurred at smaller separations for higher dot densitiesVconsistent with the idea that reliable segmentation is possible with smaller separations when the dot density is high. We propose that the visual system employs a robust statistical estimator in this task and that data points are weighted differentially based on the likelihood that they arose from a separate generative process. However, unlike in standard robust estimation, weights based on residuals are insufficient to characterize human segmentation. Rather, these must be computed based on more comprehensive generative models of dot clusters.

This thesis introduces a novel representation for three-dimensional (3D) objects in terms of local affine-invariant descriptors of their appearance and the spatial relationships between the corresponding affine regions. Geometric constraints associated with different views of the same surface patches are combined with a normalized representation of their appearance to guide matching and reconstruction, allowing the acquisition of true 3D models from multiple unregistered images, as well as their recognition in photographs and image sequences. The proposed approach is applied to two domains: 1) Photographs – Models of rigid objects are constructed from photos and recognized in highly cluttered shots taken from arbitrary viewpoints. 2) Video – Dynamic scenes containing multiple moving objects observed by a moving camera are segmented into rigid components, and the 3D models constructed from these components are matched across different image sequences, with