Neighborhood Counting Measure and Minimum Risk Metric

H Wang

doi:10.1109/TPAMI.2010.16

Neighborhood Counting Measure and Minimum Risk Metric

H Wang

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

Abstract

The neighborhood counting measure (NCM) is a similarity measure based on the counting of all common neighborhoods in a data space. The minimum risk metric (MRM) is a distance measure based on the minimization of the risk of misclassification. The paper by Argentini and Blanzieri refutes a remark about the time complexity of MRM, and presents an experimental comparison of MRM and NCM. This paper addresses the questions raised by Argentini and Blanzieri. 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.

Original language	English
Pages (from-to)	766-768
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	32
Issue number	4
DOIs	https://doi.org/10.1109/TPAMI.2010.16
Publication status	Published (in print/issue) - Apr 2010

Access to Document

10.1109/TPAMI.2010.16

Cite this

@article{56a6574b602a4a2cb2da6c20156ab375,

title = "Neighborhood Counting Measure and Minimum Risk Metric",

abstract = "The neighborhood counting measure (NCM) is a similarity measure based on the counting of all common neighborhoods in a data space. The minimum risk metric (MRM) is a distance measure based on the minimization of the risk of misclassification. The paper by Argentini and Blanzieri refutes a remark about the time complexity of MRM, and presents an experimental comparison of MRM and NCM. This paper addresses the questions raised by Argentini and Blanzieri. 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.",

author = "H Wang",

year = "2010",

month = apr,

doi = "10.1109/TPAMI.2010.16",

language = "English",

volume = "32",

pages = "766--768",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

publisher = "IEEE Computer Society",

number = "4",

}

TY - JOUR

T1 - Neighborhood Counting Measure and Minimum Risk Metric

AU - Wang, H

PY - 2010/4

Y1 - 2010/4

N2 - The neighborhood counting measure (NCM) is a similarity measure based on the counting of all common neighborhoods in a data space. The minimum risk metric (MRM) is a distance measure based on the minimization of the risk of misclassification. The paper by Argentini and Blanzieri refutes a remark about the time complexity of MRM, and presents an experimental comparison of MRM and NCM. This paper addresses the questions raised by Argentini and Blanzieri. 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.

AB - The neighborhood counting measure (NCM) is a similarity measure based on the counting of all common neighborhoods in a data space. The minimum risk metric (MRM) is a distance measure based on the minimization of the risk of misclassification. The paper by Argentini and Blanzieri refutes a remark about the time complexity of MRM, and presents an experimental comparison of MRM and NCM. This paper addresses the questions raised by Argentini and Blanzieri. 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.

U2 - 10.1109/TPAMI.2010.16

DO - 10.1109/TPAMI.2010.16

M3 - Article

VL - 32

SP - 766

EP - 768

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 4

ER -

Neighborhood Counting Measure and Minimum Risk Metric

Abstract

Access to Document

Fingerprint

Cite this