Skin detection is a preliminary step in many applications. We analyze some of the most frequently cited binary skin classifiers based on explicit color cluster definition and present possible strategies to improve their performance. In particular, we demonstrate how this can be accomplished by using genetic algorithms to redefine the cluster boundaries. We also show that the fitness function can be tuned to favor either recall or precision in pixel classification. Some combining strategies are then proposed to further improve the performance of these binary classifiers in terms of recall or precision. Finally, we show that, whatever the method or the strategy employed, the performance can be enhanced by preprocessing the images with a white balance algorithm. All the experiments reported here have been run on a large and heterogeneous image database

Schettini, R., Gasparini, F., Corchs, S. (2008). Recall or precision oriented strategies for binary classification of skin pixels. JOURNAL OF ELECTRONIC IMAGING, 17(2) [10.1117/1.2916715].

Recall or precision oriented strategies for binary classification of skin pixels

SCHETTINI, RAIMONDO;GASPARINI, FRANCESCA;CORCHS, SILVIA ELENA
2008

Abstract

Skin detection is a preliminary step in many applications. We analyze some of the most frequently cited binary skin classifiers based on explicit color cluster definition and present possible strategies to improve their performance. In particular, we demonstrate how this can be accomplished by using genetic algorithms to redefine the cluster boundaries. We also show that the fitness function can be tuned to favor either recall or precision in pixel classification. Some combining strategies are then proposed to further improve the performance of these binary classifiers in terms of recall or precision. Finally, we show that, whatever the method or the strategy employed, the performance can be enhanced by preprocessing the images with a white balance algorithm. All the experiments reported here have been run on a large and heterogeneous image database
Articolo in rivista - Articolo scientifico
recall, precision, binary classification, color skin
English
2008
17
2
0123017
none
Schettini, R., Gasparini, F., Corchs, S. (2008). Recall or precision oriented strategies for binary classification of skin pixels. JOURNAL OF ELECTRONIC IMAGING, 17(2) [10.1117/1.2916715].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/13386
Citazioni
  • Scopus 20
  • ???jsp.display-item.citation.isi??? 10
Social impact