Home / Issues / 12.2015 / A Comparative Evaluation of Three Skin Color Detection Approaches
Document Actions

Citation and metadata

Back to the article.

Recommended citation

Dennis Jensch, Daniel Mohr, and Gabriel Zachmann, A Comparative Evaluation of Three Skin Color Detection Approaches. Journal of Virtual Reality and Broadcasting, 12(2015), no. 1. (urn:nbn:de:0009-6-40888)

Download Citation

Endnote

%0 Journal Article
%T A Comparative Evaluation of Three Skin Color Detection Approaches
%A Jensch, Dennis
%A Mohr, Daniel
%A Zachmann, Gabriel
%J Journal of Virtual Reality and Broadcasting
%D 2015
%V 12(2015)
%N 1
%@ 1860-2037
%F jensch2015
%X Skin segmentation is a challenging task due to several influences such as unknown lighting conditions, skin colored background, and camera limitations. A lot of skin segmentation approaches were proposed in the past including adaptive (in the sense of updating the skin color online) and non-adaptive approaches. In this paper, we compare three skin segmentation approaches that are promising to work well for hand tracking, which is our main motivation for this work. Hand tracking can widely be used in VR/AR e.g. navigation and object manipulation. The first skin segmentation approach is a well-known non-adaptive approach. It is based on a simple, pre-computed skin color distribution. Methods two and three adaptively estimate the skin color in each frame utilizing clustering algorithms. The second approach uses a hierarchical clustering for a simultaneous image and color space segmentation, while the third approach is a pure color space clustering, but with a more sophisticated clustering approach. For evaluation, we compared the segmentation results of the approaches against a ground truth dataset. To obtain the ground truth dataset, we labeled about 500 images captured under various conditions.
%L 004
%K Benchmark
%K Evaluation
%K Skin Detection
%K Skin Segmentation
%R 10.20385/1860-2037/12.2015.1
%U http://nbn-resolving.de/urn:nbn:de:0009-6-40888
%U http://dx.doi.org/10.20385/1860-2037/12.2015.1
Download

Bibtex

@Article{jensch2015,
  author = 	"Jensch, Dennis
		and Mohr, Daniel
		and Zachmann, Gabriel",
  title = 	"A Comparative Evaluation of Three Skin Color Detection Approaches",
  journal = 	"Journal of Virtual Reality and Broadcasting",
  year = 	"2015",
  volume = 	"12(2015)",
  number = 	"1",
  keywords = 	"Benchmark; Evaluation; Skin Detection; Skin Segmentation",
  abstract = 	"Skin segmentation is a challenging task due to several influences such as unknown lighting conditions, skin colored background, and camera limitations. A lot of skin segmentation approaches were proposed in the past including adaptive (in the sense of updating the skin color online) and non-adaptive approaches. In this paper, we compare three skin segmentation approaches that are promising to work well for hand tracking, which is our main motivation for this work. Hand tracking can widely be used in VR/AR e.g. navigation and object manipulation. The first skin segmentation approach is a well-known non-adaptive approach. It is based on a simple, pre-computed skin color distribution. Methods two and three adaptively estimate the skin color in each frame utilizing clustering algorithms. The second approach uses a hierarchical clustering for a simultaneous image and color space segmentation, while the third approach is a pure color space clustering, but with a more sophisticated clustering approach. For evaluation, we compared the segmentation results of the approaches against a ground truth dataset. To obtain the ground truth dataset, we labeled about 500 images captured under various conditions.",
  issn = 	"1860-2037",
  doi = 	"10.20385/1860-2037/12.2015.1",
  url = 	"http://nbn-resolving.de/urn:nbn:de:0009-6-40888"
}
Download

RIS

TY  - JOUR
AU  - Jensch, Dennis
AU  - Mohr, Daniel
AU  - Zachmann, Gabriel
PY  - 2015
DA  - 2015//
TI  - A Comparative Evaluation of Three Skin Color Detection Approaches
JO  - Journal of Virtual Reality and Broadcasting
VL  - 12(2015)
IS  - 1
KW  - Benchmark
KW  - Evaluation
KW  - Skin Detection
KW  - Skin Segmentation
AB  - Skin segmentation is a challenging task due to several influences such as unknown lighting conditions, skin colored background, and camera limitations. A lot of skin segmentation approaches were proposed in the past including adaptive (in the sense of updating the skin color online) and non-adaptive approaches. In this paper, we compare three skin segmentation approaches that are promising to work well for hand tracking, which is our main motivation for this work. Hand tracking can widely be used in VR/AR e.g. navigation and object manipulation. The first skin segmentation approach is a well-known non-adaptive approach. It is based on a simple, pre-computed skin color distribution. Methods two and three adaptively estimate the skin color in each frame utilizing clustering algorithms. The second approach uses a hierarchical clustering for a simultaneous image and color space segmentation, while the third approach is a pure color space clustering, but with a more sophisticated clustering approach. For evaluation, we compared the segmentation results of the approaches against a ground truth dataset. To obtain the ground truth dataset, we labeled about 500 images captured under various conditions.
SN  - 1860-2037
UR  - http://nbn-resolving.de/urn:nbn:de:0009-6-40888
DO  - 10.20385/1860-2037/12.2015.1
ID  - jensch2015
ER  -
Download

Wordbib

<?xml version="1.0" encoding="UTF-8"?>
<b:Sources SelectedStyle="" xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography"  xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" >
<b:Source>
<b:Tag>jensch2015</b:Tag>
<b:SourceType>ArticleInAPeriodical</b:SourceType>
<b:Year>2015</b:Year>
<b:PeriodicalTitle>Journal of Virtual Reality and Broadcasting</b:PeriodicalTitle>
<b:Volume>12(2015)</b:Volume>
<b:Issue>1</b:Issue>
<b:Url>http://nbn-resolving.de/urn:nbn:de:0009-6-40888</b:Url>
<b:Url>http://dx.doi.org/10.20385/1860-2037/12.2015.1</b:Url>
<b:Author>
<b:Author><b:NameList>
<b:Person><b:Last>Jensch</b:Last><b:First>Dennis</b:First></b:Person>
<b:Person><b:Last>Mohr</b:Last><b:First>Daniel</b:First></b:Person>
<b:Person><b:Last>Zachmann</b:Last><b:First>Gabriel</b:First></b:Person>
</b:NameList></b:Author>
</b:Author>
<b:Title>A Comparative Evaluation of Three Skin Color Detection Approaches</b:Title>
<b:Comments>Skin segmentation is a challenging task due to several influences such as unknown lighting conditions, skin colored background, and camera limitations. A lot of skin segmentation approaches were proposed in the past including adaptive (in the sense of updating the skin color online) and non-adaptive approaches. In this paper, we compare three skin segmentation approaches that are promising to work well for hand tracking, which is our main motivation for this work. Hand tracking can widely be used in VR/AR e.g. navigation and object manipulation. The first skin segmentation approach is a well-known non-adaptive approach. It is based on a simple, pre-computed skin color distribution. Methods two and three adaptively estimate the skin color in each frame utilizing clustering algorithms. The second approach uses a hierarchical clustering for a simultaneous image and color space segmentation, while the third approach is a pure color space clustering, but with a more sophisticated clustering approach. For evaluation, we compared the segmentation results of the approaches against a ground truth dataset. To obtain the ground truth dataset, we labeled about 500 images captured under various conditions.</b:Comments>
</b:Source>
</b:Sources>
Download

ISI

PT Journal
AU Jensch, D
   Mohr, D
   Zachmann, G
TI A Comparative Evaluation of Three Skin Color Detection Approaches
SO Journal of Virtual Reality and Broadcasting
PY 2015
VL 12(2015)
IS 1
DI 10.20385/1860-2037/12.2015.1
DE Benchmark; Evaluation; Skin Detection; Skin Segmentation
AB Skin segmentation is a challenging task due to several influences such as unknown lighting conditions, skin colored background, and camera limitations. A lot of skin segmentation approaches were proposed in the past including adaptive (in the sense of updating the skin color online) and non-adaptive approaches. In this paper, we compare three skin segmentation approaches that are promising to work well for hand tracking, which is our main motivation for this work. Hand tracking can widely be used in VR/AR e.g. navigation and object manipulation. The first skin segmentation approach is a well-known non-adaptive approach. It is based on a simple, pre-computed skin color distribution. Methods two and three adaptively estimate the skin color in each frame utilizing clustering algorithms. The second approach uses a hierarchical clustering for a simultaneous image and color space segmentation, while the third approach is a pure color space clustering, but with a more sophisticated clustering approach. For evaluation, we compared the segmentation results of the approaches against a ground truth dataset. To obtain the ground truth dataset, we labeled about 500 images captured under various conditions.
ER
Download

Mods

<mods>
  <titleInfo>
    <title>A Comparative Evaluation of Three Skin Color Detection Approaches</title>
  </titleInfo>
  <name type="personal">
    <namePart type="family">Jensch</namePart>
    <namePart type="given">Dennis</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Mohr</namePart>
    <namePart type="given">Daniel</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Zachmann</namePart>
    <namePart type="given">Gabriel</namePart>
  </name>
  <abstract>Skin segmentation is a challenging task due to several influences such as unknown lighting conditions, skin colored background, and camera limitations. A lot of skin segmentation approaches were proposed in the past including adaptive (in the sense of updating the skin color online) and non-adaptive approaches. In this paper, we compare three skin segmentation approaches that are promising to work well for hand tracking, which is our main motivation for this work. Hand tracking can widely be used in VR/AR e.g. navigation and object manipulation. The first skin segmentation approach is a well-known non-adaptive approach. It is based on a simple, pre-computed skin color distribution. Methods two and three adaptively estimate the skin color in each frame utilizing clustering algorithms. The second approach uses a hierarchical clustering for a simultaneous image and color space segmentation, while the third approach is a pure color space clustering, but with a more sophisticated clustering approach. For evaluation, we compared the segmentation results of the approaches against a ground truth dataset. To obtain the ground truth dataset, we labeled about 500 images captured under various conditions.</abstract>
  <subject>
    <topic>Benchmark</topic>
    <topic>Evaluation</topic>
    <topic>Skin Detection</topic>
    <topic>Skin Segmentation</topic>
  </subject>
  <classification authority="ddc">004</classification>
  <relatedItem type="host">
    <genre authority="marcgt">periodical</genre>
    <genre>academic journal</genre>
    <titleInfo>
      <title>Journal of Virtual Reality and Broadcasting</title>
    </titleInfo>
    <part>
      <detail type="volume">
        <number>12(2015)</number>
      </detail>
      <detail type="issue">
        <number>1</number>
      </detail>
      <date>2015</date>
    </part>
  </relatedItem>
  <identifier type="issn">1860-2037</identifier>
  <identifier type="urn">urn:nbn:de:0009-6-40888</identifier>
  <identifier type="doi">10.20385/1860-2037/12.2015.1</identifier>
  <identifier type="uri">http://nbn-resolving.de/urn:nbn:de:0009-6-40888</identifier>
  <identifier type="citekey">jensch2015</identifier>
</mods>
Download

Full Metadata

Bibliographic Citation JVRB, 12(2015), no. 1.
Title

A Comparative Evaluation of Three Skin Color Detection Approaches (eng)
Author Dennis Jensch, Daniel Mohr, Gabriel Zachmann
Language eng
Abstract Skin segmentation is a challenging task due to several influences such as unknown lighting conditions, skin colored background, and camera limitations. A lot of skin segmentation approaches were proposed in the past including adaptive (in the sense of updating the skin color online) and non-adaptive approaches. In this paper, we compare three skin segmentation approaches that are promising to work well for hand tracking, which is our main motivation for this work. Hand tracking can widely be used in VR/AR e.g. navigation and object manipulation. The first skin segmentation approach is a well-known non-adaptive approach. It is based on a simple, pre-computed skin color distribution. Methods two and three adaptively estimate the skin color in each frame utilizing clustering algorithms. The second approach uses a hierarchical clustering for a simultaneous image and color space segmentation, while the third approach is a pure color space clustering, but with a more sophisticated clustering approach. For evaluation, we compared the segmentation results of the approaches against a ground truth dataset. To obtain the ground truth dataset, we labeled about 500 images captured under various conditions.
Subject Benchmark, Evaluation, Skin Detection, Skin Segmentation
Classified Subjects
swd
  • 4006684-8, Bildverarbeitung
  • 4159296-7, Hautfarbe
  • 4144457-7, Benchmark
  • 4145448-0, Bildsegmentierung
DDC 004
Rights DPPL
URN: urn:nbn:de:0009-6-40888
DOI https://doi.org/10.20385/1860-2037/12.2015.1