PE&RS May 1996

Cover Image

Eastman Kodak Company, Rochester, New York, obtained the color infrared cover imagery of Rochester, NY at an altitude of 12,000 feet. The natural color inset photo, also of Rochester, NY, is on Kodak Aerocolor Negative Film 2445 and was taken from an altitude of 5,000 feet.

Peer-Reviewed Articles (Click the linked titles to see the full abstract)

483-490 A Model to Support the Integration of Image Understanding Techniques within a GIS
Mark Gahegan and Julien Flack

Image understanding methods, and expert knowledge governing the application of those methods, are chosen automatically to best emphasize the types of features that the user is currently investigat-ing, and the type of imagery available.  

491-499 Relating the Land-Cover Composition of Mixed Pixels to Artificial Neural Network Classifica-tion Output
Giles M. Foody

The land-cover composition of mixed pixels was found to be significantly correlated to measures output from an artificial neural network.  

501-511 An Operational GIS Expert System for Mapping Forest Soils
Andrew K. Skidmore, Fiona Watford, Paisan Luckananurug, and P.J. Ryan

Forest soils were mapped into five soil landscape classes by utilizing a digital terrain model and vegetation, as well as knowledge provided by a soil scientist.  

513-523 Integrated Analysis of Spatial Data from Multiple Sources: Using Evidential Reasoning and Artificial Neural Network Techniques for Geological Mapping
P. Gong

A evidental reasoning and a back-propagation feed-forward neural network algorithm are introduced, and their applications to classification problems are evaluated.

525-531 Automatic Extraction and Evaluation of Geological Linear Features from Digital Remote Sensing Data Using a Hough Transform
Arnon Karnieli, Amnon Meisels, Leonid Fisher, and Yaacov Arkin

Automatic extraction and mapping of linements conformed well to interpretation of lineaments by human performance.  

533-538 Vision-Based Image Processing of Digitized Cadastral Maps
Liang-Hwei Lee and Tsu-Tse Su

The method includes two major algorithms: a segmentation algorithm, which obtains the positions and sizes of symbols and characters, and a raster-to-vector conversion, which obtains topological information.