https://apps.dtic.mil/sti/pdfs/ADA157550.pdf

The TRACE model of speech perception.

In this article we review some new evidence relating to early visual processing and propose an explanatory framework. A series of search experiments tested detection of targets distinguished from the distractors by differences on a single dimension. Our aim was to use the pattern of search latencies to infer which features are coded automatically in early vision. For each of 12 different dimensions, one or more pairs of contrasting stimuli were tested. Each member of a pair played the role of target in one condition and the role of distractor in the other condition. Many pairs gave rise to a marked asymmetry in search latencies, such that one stimulus in the pair was detected either through parallel processing or with small increases in latency as display size increased, whereas the other gave search functions that increased much more steeply. Targets denned by larger values on the quantitative dimensions of length, number, and contrast, by line curvature, by misaligned orientation, and by values that deviated from a standard or prototypical color or shape were detected easily, whereas targets defined by smaller values on the quantitative dimensions, by straightness, by frame-aligned orientation, and by prototypical colors or shapes required slow and apparently serial search. These values appear to be coded by default, as the absence of the contrasting values. We found no feature of line arrangements that allowed automatic, preattentive detection; nor did connectedness or containment—the two examples of topological features that we tested. We interpret the results as evidence that focused attention to single items or to groups is required to reduce background activity when the Weber fraction distinguishing the pooled feature activity with displays containing a target and with displays containing only distractors is too small to allow reliable discrimination.

Feature analysis in early vision : evidence from search asymmetries

A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

http://ieeexplore.ieee.org/iel2/815/3148/00100651.pdf

Robot vision

Research aimed at correcting words in text has focused on three progressively more difficult problems:(1) nonword error detection; (2) isolated-word error correction; and (3) context-dependent work correction. In response to the first problem, efficient pattern-matching and n-gram analysis techniques have been developed for detecting strings that do not appear in a given word list. In response to the second problem, a variety of general and application-specific spelling correction techniques have been developed. Some of them were based on detailed studies of spelling error patterns. In response to the third problem, a few experiments using natural-language-processing tools or statistical-language models have been carried out. This article surveys documented findings on spelling error patterns, provides descriptions of various nonword detection and isolated-word error correction techniques, reviews the state of the art of context-dependent word correction techniques, and discusses research issues related to all three areas of automatic error correction in text.

Techniques for automatically correcting words in text

Parts of recognition (A)

Computer Vision Systems

Context in word recognition

levels of abstraction is yet another source of potential parallelism. Moreover, processing within each level presents many possibilities for exploiting parallelism. Part of the allure of developing a vision machine. from a computer architect's perspective, is this tremendous quantity. diversity, and complexity of latent parallelism. By comparison, most scientific and engineering applications have simple organizations with straightforward requirements for parallelism. (For more detailed analysis of the potential for parallelism in image understanding, see Weems.')

The three overviews that follow are short reports of ongoing research in image understanding architecture, SIMD parallelism in computer vision, and software environments for parallel computer vision. Image Understanding Architecture: Exploiting Potential Parallelism in Machine Vision

: A layered hierarchical parallel array architecture for image analysis applications, referred to as a processing cone, is described and sample algorithms are presented. A fundamental characteristic of the structure is its hierarchical organization into two-dimensional arrays of decreasing resolution. In this architecture, a protypical function is defined on a local window of data and applied uniformly to all windows in a parallel manner. Three basic modes of processing are supported in the cone: reduction operations (upward processing), horizontal operations (processing at a single level) and projection operations (downward processing). Complex image analysis algorithms are specified as temporal sequences of function applications. The cone structure forms the basis of a sophisticated operating system for an image analysis environment. (Author)

Processing Cones: A Computational Structure for Image Analysis.

This report summarizes progress in image understanding research at the University of Massachsuetts over the past year Many of the individual efforts discussed in this paper are further developed in other papers in this proceedings The summary is organized into several areas: l Image Exploitation under RADIUS 2 Learning in Vision 3 Mobile Vehicle Navigation 4 Recovering 3D Structure 5 The Image Understanding Architecture The Research program in computer vision at UMass has as one of its goals the integration of a diverse set of research efforts into a system that is ultimately intended to achieve real-time image interpretation in a variety of vision applications

Allen R. Hanson

Papers

Computer Vision Systems

Context in word recognition

The three overviews that follow are short reports of ongoing research in image understanding architecture, SIMD parallelism in computer vision, and software environments for parallel computer vision. Image Understanding Architecture: Exploiting Potential Parallelism in Machine Vision

Processing Cones: A Computational Structure for Image Analysis.

Progress in computer vision at the University of Massachusetts