Abstract
Consider two classifiers C1 and C2 each partitioning a collection A of n objects into classes based on respective sets of features. In a number in pattern recognition and knowledge engineering applications, the following problems arise: given the two partitions generated by C1 and C2, compute new partitions by considering (i) the features common to both classifiers, and (ii) the features of either of the classifiers. We show that both problems can be solved in Θ (n log n) time using very simple algorithms.
Original language | English |
---|---|
Pages (from-to) | 163-167 |
Number of pages | 5 |
Journal | Pattern Recognition Letters |
Volume | 17 |
Issue number | 2 |
DOIs | |
State | Published - Feb 8 1996 |
Funding
* The work of the first author is supported in part by NSF grant CCR-9407180 and by ONR grant N00014-95-1-0779. The work of the second author is sponsored by the Engineering Research Program of the Office of Basic Energy Sciences, of the U. S. Department of Energy, under Contract No. DE-AC05-84OR21400 with Martin Marietta Energy Systems, Inc. * Corresponding author. Email: [email protected]
Keywords
- Classification
- Equivalence relations
- Partitions
- Pattern recognition
- Refinement