Human skin detection, i.e. the process of discriminating “skin” and “non-skin” pixel in an image or a video, is a very important task for several applications including face detection, video surveillance, body tracking, hand gesture recognition, and many others. Skin detection has been widely studied from the research community resulting in several methods based on hand-crafted rules or deep learning. In this work we propose a novel post-processing approach for skin detectors based on trained morphological operators. The first step, consisting in skin segmentation, is performed according to an existing skin detection approach, and then a second step is carried out consisting in the application of a set of morphological operators to refine the resulting mask. Extensive experimental evaluation, performed considering two different detection approaches (one based on deep learning and a handcrafted one), carried on 10 different datasets confirms the quality of the proposed method. To encourage future comparisons the MATLAB source code is freely available in the GitHub repository: https://github.com/LorisNanni.

Learning morphological operators for skin detection

Lumini, Alessandra;
2019

Abstract

Human skin detection, i.e. the process of discriminating “skin” and “non-skin” pixel in an image or a video, is a very important task for several applications including face detection, video surveillance, body tracking, hand gesture recognition, and many others. Skin detection has been widely studied from the research community resulting in several methods based on hand-crafted rules or deep learning. In this work we propose a novel post-processing approach for skin detectors based on trained morphological operators. The first step, consisting in skin segmentation, is performed according to an existing skin detection approach, and then a second step is carried out consisting in the application of a set of morphological operators to refine the resulting mask. Extensive experimental evaluation, performed considering two different detection approaches (one based on deep learning and a handcrafted one), carried on 10 different datasets confirms the quality of the proposed method. To encourage future comparisons the MATLAB source code is freely available in the GitHub repository: https://github.com/LorisNanni.
2019
Lumini, Alessandra; Nanni, Loris; Codogno, Alice; Berno, Filippo
File in questo prodotto:
Eventuali allegati, non sono esposti

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/11585/759012
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact