Harry G. Barrow

Interpreting line drawings as three-dimensional surfaces

We propose 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.

VERIFY: a program for proving correctness of digital hardware designs

Abstract verify is a prolog program that attempts to prove the correctness of a digital design. It does so by showing that the behavior inferred from the interconnection of its parts and their behaviors is equivalent to the specified behavior. It has successfully verified large designs involving many thousands of transistors.

Experiments in interpretation-guided segmentation

This paper presents a new approach for integrating the segmentation and interpretation phases of scene analysis. Knowledge from a variety of sources is used to make inferences about the interpretations of regions, and regions are merged in accordance with their possible interpretations. The deduction of region interpretations is performed using a generalization of Waltzs filtering algorithm. Deduction proceeds by eliminating possible region interpretations that are not consistent with any possible interpretation of an adjacent region. Different sources of knowledge are expressed uniformly as constraints on the possible interpretations of regions. Multiple sources of knowledge can thus be combined in a straightforward way such that incremental additions of knowledge (or equivalently, human guidance) will effect incremental improvements in performance. Experimental results are reported in three scene domains, landscapes, mechanical equipment, and rooms, using, respectively, a human collaborator, a geometric model and a set of relational constraints as sources of knowledge. These experiments demonstrate that segmentation is much improved when integrated with interpretation. Moreover, the integrated approach incurs only a small computational overhead over unguided segmentation. Applications of the approach in cartography, photointerpretation, vehicle guidance, medicine, and motion picture analysis are suggested.

A versatile system for computer-controlled assembly

Abstract A versatile assembly system, using TV cameras and computer-controlled arm and moving table, is described. It makes simple assemblies such as a peg and rings and a toy car. It separates parts from a heap, recognizing them with an overhead camera, then assembles them by feel. It can be instructed to perform a new task with different parts by spending an hour or two showing it the parts and a day programming the assembly manipulations. A hierarchical description of parts, views, outlines, etc. is used to construct models, and a structure matching algorithm is used in recognition.

The role of weight normalization in competitive learning

The effect of different kinds of weight normalization on the outcome of a simple competitive learning rule is analyzed. It is shown that there are important differences in the representation formed depending on whether the constraint is enforced by dividing each weight by the same amount (divisive enforcement) or subtracting a fixed amount from each weight (subtractive enforcement). For the divisive cases weight vectors spread out over the space so as to evenly represent typical inputs, whereas for the subtractive cases the weight vectors tend to the axes of the space, so as to represent extreme inputs. The consequences of these differences are examined.

SOME TECHNIQUES FOR RECOGNISING STRUCTURES IN PICTURES

Publisher Summary This chapter discusses some techniques for recognizing structures in pictures. The research aims to develop techniques whereby a machine may observe its surroundings and then use its observations to achieve goals in an effective and efficient manner. To fulfill such requirements, the machine will inevitably use knowledge gained from past experience and observation to plan its activities, and also to interpret its sensory data. The chapter discusses the idea of a finite relational structure, that is, a set of elements with given properties and relations among them, as a useful mathematical tool for describing pictures, and to describe general techniques for matching such structures against each other. The matching process for relational structures attempts to find whether one structure occurs in or is a substructure of another structure. More precisely one need a function that assigns to each element of the first structure a distinct element of the second structure in such a way as to preserve the properties and relations which subsist in the first structure.

Scene modeling: A structural basis for image description

Abstract Conventional statistical approaches to image modeling are fundamentally limited because they take no account of the underlying physical structure of the scene nor of the image formation process. The image features being modeled are frequently artifacts of viewpoint and illumination that have no intrinsic significance for higher-level interpretation. This paper argues for a structural approach to modeling that explicitly relates image appearance to the scene characteristics from which it arose. After establishing the necessity for structural modeling in image analysis, a specific representation for scene structure is proposed and then a possible computational paradigm for recovering this description from an image is described.

A self-organizing model of “color blob” formation

This paper explores the possibility that the formation of color blobs in primate striate cortex can be partly explained through the process of activity-based self-organization. We present a simulation of a highly simplified model of visual processing along the parvocellular pathway, that combines precortical color processing, excitatory and inhibitory cortical interactions, and Hebbian learning. The model self-organizes in response to natural color images and develops islands of unoriented, color-selective cells within a sea of contrast-sensitive, orientation-selective cells. By way of understanding this topography, a principal component analysis of the color inputs presented to the network reveals that the optimal linear coding of these inputs keeps color information and contrast information separate.

Representation and use of knowledge in vision

This paper summarizes the present state of research in scene analysis. It identifies fundamental information processing principles relevant to representation and Use of knowledge in vision and traces limitations of existing progams to compromises of these principles necessitated by extant processors Some specific and general recommendations are offered regarding a productive course of research for the next decade.

A Model of Adaptive Development of Complex Cortical Cells

We present in this paper some initial results from a model of activity-dependent development of complex cortical cell receptive fields. We hypothesize that, in general, cortical layers II and III may be the locus of classical conditioning, and that complex cells in primary visual cortex may develop through conditioning to low-level visual information. We demonstrate that an unsupervised time-derivative adaptation rule can yield characteristics of complex cell fields, in both a simplified abstract model and a more detailed, large-scale model with 57,000 cells.