Boundaries in multispectral imagery by clustering
- 1 December 1970
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 9, 114
- https://doi.org/10.1109/sap.1970.269984
Abstract
In classifying multispectral, digitized, pictorial data it is necessary to locate spatial boundaries in the data to assist the researcher in the selection of training and test samples. Applications also exist in the areas of data compression, information storage and retrieval, sample classification schemes and image registration.Keywords
This publication has 6 references indexed in Scilit:
- Information processing of remotely sensed agricultural dataProceedings of the IEEE, 1969
- Pattern recognition with measurement space and spatial clustering for multiple imagesProceedings of the IEEE, 1969
- The physical basis of system design for remote sensing in agricultureProceedings of the IEEE, 1969
- On Some Invariant Criteria for Grouping DataJournal of the American Statistical Association, 1967
- Image transmission by two-dimensional contour codingProceedings of the IEEE, 1967
- Distance and decision rulesAnnals of the Institute of Statistical Mathematics, 1964