Background-Invariant Robust Hand Detection based on Probabilistic One-Class Color Segmentation and Skeleton Matching

Andrey Kopylov, Oleg Seredin, Olesia Kushnir, Inessa Gracheva, Aleksandr Larin

Abstract

In this paper we present a new method of hand detection in cluttered background for video stream processing. At first, skin segmentation is performed by one-class color pixel classifier which is trained using just a face image fragment without any background training sample. The modified version of one-class classifier is proposed. For each pixel it returns the grade (probability) of its belonging to the skin category instead of common binary decision. To adjust output of the one-class classifier the structure-transferring filter built on probabilistic gamma-normal model is applied. It utilizes additional information about the structure of an image and coordinates local decisions in order to achieve more robust segmentation results. To make a final decision whether an image fragment is the image of human hand or not, the method of binary image matching based on skeletonization is employed. The experimental study on segmentation and detection quality of the proposed method shows promising results.

Download


Paper Citation


in Harvard Style

Kopylov A., Seredin O., Kushnir O., Gracheva I. and Larin A. (2018). Background-Invariant Robust Hand Detection based on Probabilistic One-Class Color Segmentation and Skeleton Matching.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 503-510. DOI: 10.5220/0006649805030510


in Bibtex Style

@conference{icpram18,
author={Andrey Kopylov and Oleg Seredin and Olesia Kushnir and Inessa Gracheva and Aleksandr Larin},
title={Background-Invariant Robust Hand Detection based on Probabilistic One-Class Color Segmentation and Skeleton Matching},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={503-510},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006649805030510},
isbn={978-989-758-276-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Background-Invariant Robust Hand Detection based on Probabilistic One-Class Color Segmentation and Skeleton Matching
SN - 978-989-758-276-9
AU - Kopylov A.
AU - Seredin O.
AU - Kushnir O.
AU - Gracheva I.
AU - Larin A.
PY - 2018
SP - 503
EP - 510
DO - 10.5220/0006649805030510