The Community for Technology Leaders
Green Image
Issue No. 04 - April (2010 vol. 32)
ISSN: 0162-8828
pp: 766-768
Hui Wang , University of Ulster, Jordanstown, Newtownabbey, Co. Antrim
ABSTRACT
The neighborhood counting measure (NCM) is a similarity measure based on the counting of all common neighborhoods in a data space [5]. The minimum risk metric (MRM) [2] is a distance measure based on the minimization of the risk of misclassification. The paper by Argentini and Blanzieri [1] refutes a remark in [5] about the time complexity of MRM, and presents an experimental comparison of MRM and NCM. This paper is a response to the paper by Argentini and Blanzieri [1]. The original remark is clarified by a combination of theoretical analysis of different implementations of MRM and experimental comparison of MRM and NCM using straightforward implementations of the two measures.
INDEX TERMS
Minimum risk metric, neighborhood counting measure, k-nearest neighbor.
CITATION
Hui Wang, "Neighborhood Counting Measure and Minimum Risk Metric", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 32, no. , pp. 766-768, April 2010, doi:10.1109/TPAMI.2010.16
105 ms
(Ver 3.1 (10032016))