Abstract--The recognition of three-dimensional ( 3-D) objects from sequences of their two-dimensional ( 2-D) views is modeled by a family of self-organizing neural architectures, called VIEWNET, that use View Information Encoded With NETworks. VIEWNET incorporates a preprocessor that generates a compressed but 2-D invariant representation of an image, a supervised incremental learning system that classifies the preprocessed representations into 2-1) view categories whose outputs are combined into 3-D invariant object categories, and a working memory that makes a 3-D object prediction by accumulating evidence from 3-D object category nodes us multiple 2-D views are experienced. The simplest VIEWNET achieves high recognition scores without the need to explicitly code the temporal order of 2-D views in working memory. Working memories are also discussed that save memory resources by implicitly coding temporal order in terms of the relative activity of 2-D view category nodes, rather than as explicit 2-D view transitions. Variants of the VIEWNET architecture may be used for scene understanding by using a preprocessor and classifier that can determine both what objects are in a scene and where they are located. The present VIEWNET preprocessor includes the CORT-X 2 filter, which discounts the illuminant, regularizes and completes figural boundaries, and suppresses image noise. This boundary segmentation is rendered invariant under 2-D translation, rotation, and dilation by use of a log-polar transform. The invariant spectra undergo Gaassian coarse coding to further reduce noise and 3-D foreshortening effects, and to increase generalization. These compressed codes are input into the

The concepts of declarative memory and procedural memory have been used to distinguish two basic types of learning. A neural network model suggests how such memory processes work together as recognition learning, reinforcement learning, and sensory-motor learning take place during adaptive behaviors. To coordinate these processes, the hippocampal formation and cerebellum each contain circuits that learn to adaptively time their outputs. Within the model, hippocampal timing helps to maintain attention on motivationally salient goal objects during variable task-related delays, and cerebellar timing controls the release of conditioned responses. This property is part of the model's description of how cognitive-emotional interactions focus attention on motivationally valued cues, and how this process breaks down due to hippocampal ablation. The model suggests that the hippocampal mechanisms that help to rapidly draw attention to salient cues could prematurely release motor commands were no...

To recognize an object in an image one must have an internal model of how that object may appear. We describe a method for learning such models from training images. An object is modeled by a probability distribution describing the range of possible variation in the object's appearance. This distribution is organized on two levels. Large variations are handled by partitioning the training images into clusters that correspond to distinctly different views of the object. Within each cluster, smaller variations are represented by distributions that characterize the presence, position, and measurements of various discrete features of appearance. The learning process combines an incremental conceptual clustering algorithm for forming the clusters with a generalization algorithm for consolidating each cluster's training images into a single description. Recognition employs information about feature positions, numeric measurements, and relations in order to constrain and speed the search. Pre...

Diverse theories of animal navigation aim at explaining how to determine and maintain a course from one place to another in the environment, although each presents a particular perspective with its own terminologies. These vocabularies sometimes overlap, but unfortunately with different meanings. This paper attempts to precisely define the existing concepts and terminologies, so as to comprehensively describe the different theories and models within the same unifying framework. We present navigation strategies within a 4 level hierarchical framework based upon levels of complexity of required processing (Guidance, Place recognition-triggered Response, Topological navigation, Metric navigation). This classification is based upon what information is perceived, represented and processed. It contrasts with common distinctions based upon availability of certain sensors or cues and rather stresses the information structure and content of central processors. We then review computat...

A mobile agent with the task to classify its sensor pattern has to cope with ambiguous information. Active recognition of three-dimensional objects involves the observer in a search for discriminative evidence, e.g., by change of its viewpoint. This paper defines the recognition process as a sequential decision problem with the objective to disambiguate initial object hypotheses. Reinforcement learning provides then an efficient method to autonomously develop near-optimal decision strategies in terms of sensorimotor mappings. The proposed system learns object models from visual appearance and uses a radial basis function (RBF) network for a probabilistic interpretation of the two-dimensional views. The information gain in fusing successive object hypotheses provides a utility measure to reinforce actions leading to discriminative viewpoints. The system is verified in experiments with 16 objects and two degrees of freedom in sensor motion. Crucial improvements in performance are gained...

We propose a framework and a complete implementation of a translation and scale invariant image recognition system for natural indoor scenes. The system employs higher order autocorrelation features of scale space data which permit linear classification. An optimal linear classification method is presented, which is able to cope with a large number of classes represented by many, as well as very few samples. In the course of the analysis of our system, we examine which numerical methods for feature transformation and classification show sufficient stability to fulfill these demands. The implementation has been extensively tested. We present the results of our own application and several classification benchmarks. Image recognition Face recognition Scale invariancy Scale space Higher order autocorrelation Optimal linear classification 1. INTRODUCTION The task of visual recognition which was defined by Marr (1) with the question: "What objects are where in the environment?" is still ...

this paper, we track changes in the appearance of the object as it moves from one frame to the next. At a symbolic level, an aspect graph clusters all the views of an object into a set of topologically distinct classes in terms of which surfaces of an object are visible from a given viewpoint (Koenderink and van Doorn [9]). Two nodes (or aspects) in the aspect graph are connected

This paper presents a new approach for shape description and invariant recognition by geometric-normalization implemented by neural networks. The neural system consists of a shape description network, a normalization network and a recognition stage based on fuzzy pyramidal neural networks. The description network uses a novel approach for hierar-chical shape segmentation and representation which expands the image shapes into localized feature tokens. These feature tokens form a compact description of the shape and its com-ponents that include information on their location, size and orientation. The description network, which is composed of a novel pyramidal architecture called the Vectorial Gradual Lattice Pyramid, processes in parallel a new vectorial scale space representation of the shape. A novel measure called Cancellation Energy is used to determine the feature tokens. The normalization network utilizes the location, size, and orientation information in the feature tokens to geometric-normalize the shape or its components with respect to these parame-ters. The recognition network which has a pyramidal structure, uses a fuzzy representation of these normalized feature tokens to achieve robust invariant recognition. Experimental results demonstrate robust recognition in large variations of scale, rotation, translation and

Three experiments investigated the role of visual attention in priming for object images and their left-right reflections. Objects to which participants attended were visually primed in both the same view and in the left-right reflected view; ignored objects were primed only in the same view. The effects of attention (attended vs. ignored) and view (same vs. reflected) were strictly additive. These results suggest that 2 separate representations mediate human object recognition (J. E. Hummel & B. J. Stankiewicz, 1996): One requires attention but is invariant with left-right reflection, whereas the other can be activated automatically but is sensitive to left-right reflection. Both representations appear to be invariant with translation across the visual field. The human visual system recognizes objects with remark-able speed and accuracy. A fraction of a second after an image falls on the retina, a person knows what the object is. This is true even if the object is presented in a novel viewpoint or is a new member of a familiar category. Although humans are extremely proficient at recognizing objects, they are limited in the number of objects that can be recognized simultaneously (see Biederman, Blickle, Teitel-baum, & Klatsky, 1988; Ruthruff & Miller, 1995; Treisman & Gelade, 1980). This capacity limitation suggests that attention plays a critical role in object recognition. What is the role of attention in object recognition? Visual attention is known to influence feature selection (LaBerge & Brown,

Figure 1. Best views generated by our approach. An approach to automatically select stable and salient representative views of a given 3D object is proposed. Initially, a set of viewpoints are uniformly sampled along the surface of a bounding sphere. The sampled viewpoints are connected to their closest points to form a spherical graph in which each edge is weighted by a similarity measure between the two views from its incident vertices. Partitions of similar views are obtained using a graph partitioning procedure and their “centroids ” are considered to be their representative views. Finally, the views are ranked based on a saliency measure to form the object’s representative views. This leads to a compact, human-oriented 2D description of a 3D object, and as such, is useful both for traditional applications like presentation and analysis of 3D shapes, and for emerging ones like indexing and retrieval in large shape repositories. 1