Is (N)PRI suitable for evaluating automated segmentation of cutaneous lesions?

Authors:
Enoch Peserico;Alberto Silletti
Affiliations:
Dip. Ingegneria dell'Informazione, Univ. Padova, Italy;Dip. Ingegneria dell'Informazione, Univ. Padova, Italy
Venue:
Pattern Recognition Letters
Year:
2010

Citing 2
Cited 0

Color image segmentation using fuzzy C-means and eigenspace projections

Signal Processing
Measures of Similarity

WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01

Quantified Score

Hi-index	0.10

Visualization

Abstract

An example of anomalous behaviour of the (Normalised) Probabilistic Rand Index - due to its non-monotonicity with the fraction of misclassified pixels - raises doubts on its suitability as a metric for cutaneous lesion segmentation.