A computer vision system has been implemented that can recognize threedimensional objects from unknown viewpoints in single gray-scale images. Unlike most other approaches, the recognition is accomplished without any attempt to reconstruct depth information bottom-up from the visual input. Instead, three other mechanisms are used that can bridge the gap between the two-dimensional image and knowledge of three-dimensional objects. First, a process of perceptual organization is used to form groupings and structures in the image that are likely to be invariant over a wide range of viewpoints. Second, a probabilistic ranking method is used to reduce the size of the search space during model based matching. Finally, a process of spatial correspondence brings the projections of three-dimensional models into direct correspondence with the image by solving for unknown viewpoint and model parameters. A high level of robustness in the presence of occlusion and missing data can be achieved through full application of a viewpoint consistency constraint. It is argued that similar mechanisms and constraints form the basis for recognition in human vision. This paper has been published in Artificial Intelligence, 31, 3 (March 1987), pp. 355–395. 1 1

Abstract not found

For many centuries, philosophers and scientists have pondered the origins and nature of human intuitions about the properties of points, lines, and figures on the Euclidean plane, with most hypothesizing that a system of Euclidean concepts either is innate or is assembled by general learning processes. Recent research from cognitive and developmental psychology, cognitive anthropology, animal cognition, and cognitive neuroscience suggests a different view. Knowledge of geometry may be founded on at least two distinct, evolutionarily ancient, core cognitive systems for representing the shapes of large-scale, navigable surface layouts and of small-scale, movable forms and objects. Each of these systems applies to some but not all perceptible arrays and captures some but not all of the three fundamental Euclidean relationships of distance (or length), angle, and direction (or sense). Like natural number (Carey, 2009), Euclidean geometry may be constructed through the productive combination of representations from these core systems, through the use of uniquely human symbolic systems.

Perceptual organization refers to the process of organizing sensory input into coherent and interpretable perceptual structures. This process is challenging due to the chicken-and-egg nature between the various sub-processes such as image segmentation, figure-ground segregation and object recognition. Low-level processing requires the guidance of high-level knowledge to overcome noise; while high-level processing relies on low-level processes to reduce the computational complexity. Neither process can be sufficient on its own. Consequently, any system that carries out these processes in a sequence is bound to be brittle. An alternative system is one in which all processes interact with each other simultaneously. In this thesis, we develop a set of simple yet realistic interactive processing models for perceptual organization. We model the processing in the framework of spectral graph theory, with a criterion encoding the overall goodness of perceptual organization. We derive fast solutions for near-global optima of the criterion, and demonstrate the efficacy of the models on segmenting a wide range of real images. Through these models, we are able to capture a variety of perceptual phenomena: a unified treatment of various grouping, figure-ground and depth cues to produce popout, region segmentation and depth segregation in one step; and a unified framework for integrating bottom-up and top-down information to produce an object segmentation from spatial and object attention. We achieve these goals by empowering current spectral graph methods with a principled solution for multiclass spectral graph partitioning; expanded repertoire of grouping cues to include similarity, dissimilarity and ordering relationships; a theory for integrating sparse grouping cues; and a model ...

Parallel lines are important features for object recognition by grouping. Regular 2 \Theta 2=2 curve pyramids are hierarchical symbolic representations of curves that can be constructed and processed in logarithmic time. The rigidity of the regular structure causes an unstable, shift variant representation of parallel lines. In order to usefully apply the concept of the curve pyramid on grouping problems, the shift variance problem had to be overcome by extending the concept to irregular pyramids. These have a structure that adapts to the image data by deriving control information from curve relations. The algorithm that builds the irregular curve pyramid by deriving higher levels of abstraction from a set of relations goes far beyond merely solving the shift variance problem. It can reduce the computational complexity in comparable applications where all possible combinations of parts have to be checked in order to reassemble complex objects.

While significant progress has been made in the computer vision field over the past decade, and machines capable of performing specialised visual inspection tasks are now being used in many industrial applications, the problem of recognising three-dimensional objects from two-dimensional imagery remains an area of ongoing research. Vision is undoubtedly our most important sense, and solutions to the problem of general threedimensional machine vision must be found if the long term goal of autonomous robotic agents interacting naturally with humans in the real world is to be realised. In this work the problem of recognising polyhedra from two-dimensional images is investigated. The use of perceptual grouping and intermediate-level geometric features is considered, in particular the "edge-triple " feature. The edge-triple feature consists of three connected straight edges of an object, projecting to a triple of connected lines in the image, and can be used as a key feature, or indexing primitive, in model-based object recognition. The geometric constraints provided by matching such a configuration of image lines to an edge-triple are sufficient to uniquely determine the pose of the object. A

People with aphasia, a condition that impairs the ability to understand or generate written or spoken language, are aided by assistive technology that helps them communicate through a vocabulary of icons. These systems are akin to language translation systems, translating icon arrangements into spoken or written language and vice versa. However, these icon-based systems have little vocabulary breadth or depth, making it difficult for people with aphasia to apply their usage to multiple real world situations. Pictures from the web are numerous, varied, and easily accessible and thus, could potentially address the small size issues of iconbased systems. We present results from two studies that investigate this potential and demonstrate that images can be as effective as icons when used as a replacement for English language communication. The first study uses elderly subjects to investigate the efficacy of images vs. icons in conveying word meaning; the second study examines the retention of word-level meaning by both images and icons with a population of aphasics. We conclude that images collected from the web are as functional as icons in conveying information and thus, are feasible to use in assistive technology that supports people with aphasia.

Applying several names to an entity (polynomy) reflects the ability to categorize entities in different ways. Two experiments demonstrate preschoolers ' abilities to apply multiple labels to representational objects and to people. In Experiment 1, 3- and 4-year-olds labeled representational objects and verified labels for story characters. In both tasks children reliably produced or accepted several words per entity and accepted a high percentage of both class-inclusive and overlapping word pairs. These results were replicated in Experiment 2; 3- to 5-year-olds also completed appearance-reality and receptive vocabulary tests. The mean number of words produced in the labeling task was significantly related to receptive vocabulary, but not to appearance-reality performance. The results indicate that preschoolers represent an entity as belonging to multiple categories (e.g., dinosaur and crayon). Implications for cognitive and language development, particularly the appearance-reality distinctic/n and the mutual exclusivity bias, are discussed. The objects and organisms that inhabit our environment are complex and multifaceted, with many aspects and attributes. Any entity belongs to many different categories defined by particular aspects and attributes. Adults can conceptualize these categories and represent them by using a variety of words (i.e.,

Representationalism is the position that the phenomenal character of an experience is either identical with, or supervenes on, the content of that experience. Many representationalists hold that the relevant content of experience is nonconceptual. I propose a counter-example to this form of representationalism that arises from the phenomenon of Gestalt switching, which occurs when viewing ambiguous figures. First, I argue that one does not need to appeal to the conceptual content of experience or to judgements to account for Gestalt switching. I then argue that experiences of certain ambiguous figures are problematic because they have different phenomenal characters but that no difference in the nonconceptual content of these experiences can be identified. I consider three solutions to this problem that have been proposed by both philosophers and psychologists and conclude that none can account for all the ambiguous figures that pose the problem. I conclude that the onus is on representationalists to specify the relevant difference in content or to abandon their position. 1.

This investigation examined whether infants display boundary extensionFa tendency to remember more of a visual scene than was presented. Three- to 7-month-olds were familiarized with a photograph of a visual scene, and tested with wide-angle versus close-up views of the scene. Infants preferred the close-up, indicating that they perceived the wide angle (the one consistent with boundary extension) as more familiar. Converging experiments showed that: (a) infants did not spontaneously prefer the close-up, (b) adults did not judge the wide angle to be more similar to the familiarization stimulus, and (c) infants spontaneously preferred the close-up when the photographs depicted outline objects without backgrounds. The findings suggest that infants anticipate information that lies beyond the borders of a scene view. This research was supported by NIH Grants HD-42451, HD-46526, and MH-54688. We thank John Seamon and three anonymous reviewers for their comments on an earlier draft, and Laurie Yarzab for her assistance in testing infants. Correspondence concerning this article should be addressed to