This report gives a preliminary account of the construction of a low-cost laser system for providing data on defective solder joints on printed circuit boards. The system possesses high resolution, excellent signal-to-noise ratio, and a substantial depth of focus.
This paper describes a morphological analyzer which, when parsing a word, uses two sets of rules: describing the syntax of words, and rules describing facts about orthography.
This technical note describes a region-based data structure that is easily obtained, lends itself to description of the data in a rich manner by a process of pointer reduction, and reduces combinatorial types of search by implicitly including positional information.
A relatively simple method for handling higher-order functions (funargs) in LISP is described. It is also shown how this scheme allows extension of the LISP language to include partial application of functions.
In this paper straightforward procedures are presented for calibrating a camera, computing the equation of a plane, and combining a camera calibration and an equation of a light plane to form a "sensor" matrix.
A stochastic optimization approach to stereo matching is presented. Unlike conventional correlation matching and feature matching, the approach provides a dense array of disparities, eliminating the need for interpolation.
This document outlines a system for labeling self-repairs in spontaneous speech. The system marks the location and extent of a repair, as well as relevant words in the region of the repair.
Description of SRI's design for a comprehensive study of alternative teacher certification programs, to determine the characteristics of those that were effective.
This paper shows how a simple label propagation technique, in conjunction with some novel ideas about how labels can be applied to an image to express semantic knowledge, lead to the simplification of a number of diverse and difficult image analysis tasks.
The problem of interpreting single images of abstract figures is addressed. It is argued that neither rule-based deductive inference nor model-based matching are satisfactory computational paradigms for this problem.
