Home // MMEDIA 2014, The Sixth International Conferences on Advances in Multimedia // View article

Hair Segmentation for Color Estimation in Surveillance Systems

Authors:
Aleš Křupka
Jiří Přinosil
Kamil Říha
Jiří Minář
Malay Kishore Dutta

Keywords: segmentation, hair, color, face detection, video subtraction, floodfilling

Abstract:
The paper proposes a novel method for hair segmentation, that can be used in real-time video surveillance systems or multimedia services. The method utilizes an approach of video subtraction to obtain a person silhouette. Subsequently, the head part can be identified on the silhouette by exploiting information about face position. From the head, the skin is separated using floodfilling procedure and the hair area is determined as the difference between the head and the skin. The precision of the method is evaluated using manually extracted hair masks. The purpose of the segmentation method is to specify a hair area which can be then used for a hair color estimation. Therefore, the usability of the hair segmentation procedure is tested by a proposed scheme of hair color estimation.

Pages: 102 to 107

Copyright: Copyright (c) IARIA, 2014

Publication date: February 23, 2014

Published in: conference

ISSN: 2308-4448

ISBN: 978-1-61208-320-9

Location: Nice, France

Dates: from February 23, 2014 to February 27, 2014