TL;DR: The method for recognition of rib images is described in detail, and the procedure employed here is very unique as a processing method for complex pictures and constitutes the most important part of the system for deriving final decisions correctly.

TL;DR: Three algorithms for reconstructing objects from their projections are compared, useful in locating the position and shape of tumors from X rays taken of a patient and in finding the structure of viruses and macromolecules from electron micrographs.

TL;DR: This work shall concentrate on the process of isolation of meaningful regions with respect to their interpretation and present a mathematical model, known as topological sheaves, for formalizing the region-forming process.

TL;DR: A method is proposed for partitioning input scenes into regions in which selected picture properties are regarded as uniform, but the uniformity of complex picture properties such as shape, size, or arrangement of subpattems in the pictures is examined by a structural analysis.

TL;DR: For an important class of unknowns exact reconstructions can be performed from a concentric squares raster from a finite number of projections, and a single projection is sufficient.

TL;DR: This paper reports preliminary work on a knowledge-based perceptual system for a robot that must function in an actual office environment that relies heavily on multisensory data to increase the likelihood of finding distinguishing surface attributes for a particular object.

TL;DR: The purpose of the program described herein is to provide such information for the case in which the model is an edge or corner of a model of a line or a corner with two or three edges.

TL;DR: A systein is proposed which utilizes a graph to model the program control and the scene and is applied to chest X-rays and printed circuit hoards.

TL;DR: Stochastic syntax analysis procedures for the recognition of noisy patterns and a procedure for the estimation of production probabilities of a stochastic context-free language from sample strings are presented.

TL;DR: This paper introduces some methods of extracting useful information from raw data that can be used effectively on a higher level, to extract local features of small areas from light-intensity data and to guess edges of curved objects.

TL;DR: This paper describes three algorithms for determining points which are common to the boundaries of three regions in terms of discrete representations of the boundaries.

TL;DR: A method of recognizing polyhedra is described which matches “noisy models” to the models derived from analyzing the real scene.

TL;DR: An algorithm is presented for computing points of a circle that uses only integers and rather simple operations such as addition and subtraction of one to yield a suitable number of points with increasing radius.

TL;DR: The application of a storage tube with silicon target to various types of analog image processing and examples of contrast enhancement by multiple writing, subtraction, lowpass filtering, spatial differentiation, and defocused masking of images are shown.

TL;DR: The National Aeronautics and Space Administration/Jet Propulsion Laboratory breadboard mobile robot is a test system for developing adaptive variably autonomous capabilities in support of future missions to the planets as discussed by the authors.

TL;DR: This paper suggests two algorithms that, using some heuristic hints on the features of the preexisting contour, reconstruct the blob.

TL;DR: From the initial concern with X-ray image processing, this research in image processing as applied to biomedicine has been expanded to include a system for the automated analysis of images from light and electron microscopes.

TL;DR: It is shown by examples that the distribution function of direction of density gradient is a convenient representational feature for a class of patterns whose meaningful information is primarily carried by their possibly smeared edges.

TL;DR: In order to increase resolution and/or number of displayed gray levels for given refresh memory capacity, run length coding is used, and the optimum value of the longest admissible run length is determined.

TL;DR: The technical feasibility and effectiveness of color picture processing is discussed, some research efforts toward color pictureprocessing in the laboratory are described, and the importance of using color information in picture processing by computer is suggested.

TL;DR: The development of a small-scale chromosome analysis system that will permit automatic stage control, focusing, and metaphase spread screening, and interactive processing of spreads is described.

TL;DR: Binary data arising from graphical information can be compressed by using a linear transformation if the linear transformation is based on a binary field (modulo 2), the compressed data is also binary.

TL;DR: A software technique is described which makes it very easy for an experimenter to specify and to modify simple Boolean functions of bits contained within an arbitrary window.

TL;DR: The model building process is explained and how picture properties can be extracted from the model are shown, showing how the topological structure of the picture would change if the picture were subjected to thickening or thinning operations.

TL;DR: The effect of given spatial frequency components of a picture on picture quality is studied and a coefficient of contribution of a given component to quality is derived.

TL;DR: The system employs system-subsystem organization; the minicomputer and input/output devices form a satellite subsystem called GIRLS (Graphical-data Interpretation and Reconstruction in Local Satellite), which not only functions as a pre-/postprocessor but also can carry out some intelligent jobs independently of and/or cooperatively with the host.

TL;DR: A computer method for obtaining the depth map which mirrors the detail in the original scene and is incorporated as an aid in the solution of the correspondence problem is described.

TL;DR: It appears that an iterative prediction and correction method can be suitable for the efficient and accurate measurement of elevation from stereo images made on stereo pairs of aerial images.

TL;DR: A method is described for the automatic recognition of congenital heart abnormalities via digitized images of posteroanterior chest radiographs, capable of performing real-time diagnoses at the rate of about two minutes per radiograph.