scispace - formally typeset
Search or ask a question
Proceedings Article•DOI•

Efficient Skin Region Segmentation Using Low Complexity Fuzzy Decision Tree Model

Rajen B. Bhatt1, Gaurav Sharma1, Abhinav Dhall1, Santanu Chaudhury2•
Samsung1, Indian Institute of Technology Delhi2
01 Dec 2009-pp 1-4
TL;DR: An efficient skin region segmentation methodology using low complexity fuzzy decision tree constructed over B, G, R colour space is proposed for various face and human detection applications for embedded platforms.
Abstract: We propose an efficient skin region segmentation methodology using low complexity fuzzy decision tree constructed over B, G, R colour space. Skin and nonskin training dataset has been generated by using various skin textures obtained from face images of diversity of age, gender, and race people and nonskin pixels obtained from arbitrary thousands of random sampling of nonskin textures. Compact fuzzy model with very few numbers of rules allow to raster scan consumer photographs and classify each pixel as skin or nonskin for various face and human detection applications for embedded platforms.

Summary (1 min read)

Jump to: [Introduction] – [A. The Proposed Approach] – [III. COMPUTATIONAL EXPERIMENTS] and [IV. CONCLUSIONS]

Introduction

  • Various colour space-based approaches have been proposed by researchers [7-11].
  • Further, applications in to consumer electronics products should work with very good timeaccuracy trade-off for deployment into market and success of the products.
  • In Section II, the authors describe the skin-like region segmentation approach proposed in this paper along with the brief description of FDT and specifically, FDT induced for the skin segmentation problem.
  • Computational experiments and results have been discussed in Section III.

A. The Proposed Approach

  • The authors aim is to build an efficient human object presence algorithm and localize at least one face for categorization of consumer images into portraits and non portraits for Auto Album generation.
  • For the induction of rule-based model for skin segmentation the authors have used fuzzy decision trees trained over skin and nonskin samples.
  • This makes their training Db is of the dimension 51444 * 4 where first three columns are B,G,R (x1, x2, and x3 features) values and fourth column is of the class labels (decision variable y).
  • On this Db the authors have developed fuzzy decision tree using fuzzy ID3 induction algorithm.

III. COMPUTATIONAL EXPERIMENTS

  • The authors ten fold cross validation average performance is 94.10 %.
  • The average confusion matrix is given below : .
  • Above results shows that the algorithm is highly efficient in declaring actual skin as skin, where as confusion of almost 7.5 % is involved for nonskin segments.
  • To report the timing performance all the images have been scaled to standard 640 * 480 (i.e., VGA size) resolution.

IV. CONCLUSIONS

  • The authors have proposed B,G,R colour-based skin segmentation approach using fuzzy decision tree.
  • Very compact FDT model using just seven leaf nodes (i.e., fuzzy rules) makes it very efficient for application into embedded devices.
  • Further, each fuzzy rule makes use of at the most two attributes which makes the algorithm application fast enough for the real world applications into products.

Did you find this useful? Give us your feedback

Figures (10)

Content maybe subject to copyright    Report

Efficient Skin Region Segmentation using Low
Complexity Fuzzy Decision Tree Model
Rajen B. Bhatt
#1
, Abhinav Dhall
#1
, Gaurav Sharma
#1
, Santanu Chaudhury
*2
#
Samsung India Software R&D Centre, Logix Infotech Park,
D-5, Sector-59, Noida-201301, Uttar Pradesh, India,
*
Electrical Engineering Department, IIT Delhi
{Rajen.bhatt, abhinav.d, s.gaurav1}@samsung.com, rajen.bhatt@gmail.com, schaudhury@gmail.com
Abstract— We propose an efficient skin region segmentation
methodology using low complexity fuzzy decision tree
constructed over B, G, R colour space. Skin and nonskin training
dataset has been generated by using various skin textures
obtained from face images of diversity of age, gender, and race
people and nonskin pixels obtained from arbitrary thousands of
random sampling of nonskin textures. Compact fuzzy model with
very few numbers of rules allow to raster scan consumer
photographs and classify each pixel as skin or nonskin for
various face and human detection applications for embedded
platforms.
Keywords
— Fuzzy decision trees, Skin Segmentation
I. INTRODUCTION
Skin-like region segmentation has been utilized as a pre-
processing step for various face and human detection and
tracking applications [1-6]. Colour space-based models act as
efficient approaches for quickly identifying the skin-like
regions before performing complicated steps like face and
body detection and tracking. Various colour space-based
approaches have been proposed by researchers [7-11].
However, skin region segmentation for embedded systems
porting needs separate attention because of processing
limitations of the devices. Further, applications in to consumer
electronics products should work with very good time-
accuracy trade-off for deployment into market and success of
the products. In this paper, we propose the skin-like region
segmentation approach specifically for embedded systems
applications with high accuracy and fast processing time as
the main target. We have used fuzzy decision tree (FDT)
induced over skin and non-skin training patterns. By the
suitable selection of learning parameters, a compact FDT
model has been generated which segments skin-like regions of
consumer images in fraction of seconds.
This paper is organized as follows. In Section II, we
describe the skin-like region segmentation approach proposed
in this paper along with the brief description of FDT and
specifically, FDT induced for the skin segmentation problem.
Computational experiments and results have been discussed in
Section III. Section IV concludes the paper.
II. P
ROPOSED APPROACH FOR SKIN REGION SEGMENTATION
A. The Proposed Approach
Our aim is to build an efficient human object presence
algorithm and localize at least one face for categorization of
consumer images into portraits and non portraits for Auto
Album generation. The target processor is ARM 11 core, 500
MHz clock with 256 MB DDR2 memory and two 32 KB cash
memory. For human object detection, we have added skin
segmentation as a pre-processing step followed by the other
algorithms. For the induction of rule-based model for skin
segmentation we have used fuzzy decision trees trained over
skin and nonskin samples. We have collected skin dataset by
randomly sampling B,G,R values from face images of various
age groups (young, middle, and old), race groups (white,
black, and asian), and genders obtained from FERET database
and PAL database [12,13]. Total learning sample size is
51444; out of which 14654 is the skin samples and 36790 is
nonskin samples. This makes our training Db is of the
dimension 51444 * 4 where first three columns are B,G,R (x
1
,
x
2
, and x
3
features) values and fourth column is of the class
labels (decision variable y). On this Db we have developed
fuzzy decision tree using fuzzy ID3 induction algorithm. A
brief explanation of fuzzy decision trees and fuzzy ID3
algorithm is given below.
B. Fuzzy Decision Trees
Fuzzy decision trees are powerful, top-down, hierarchical
search methodology to extract easily interpretable
classification rules [14, 15]. Fuzzy decision trees are
composed of a set of internal nodes representing variables
used in the solution of a classification problem, a set of
branches representing fuzzy sets of corresponding node
variables, and a set of leaf nodes representing the degree of
certainty with which each class has been approximated. We
have used our own implementation of fuzzy ID3 algorithm
[14,15] for learning a fuzzy classifier on the training data.
Fuzzy ID3 utilizes fuzzy classification entropy of a
possibilistic distribution for decision tree generation.
Before induction of fuzzy decision tree, training patterns
pertaining to three input attributes have been clustered using
fuzzy c-means clustering algorithm [16] into five fuzzy
clusters. These fuzzy clusters have been approximated as a
Gaussian membership function using the dispersion factor 0.2
[17]. Plot of fuzzy membership functions after Gaussian
membership estimation is shown in Fig. 1 below.
978-1-4244-4859-3/09/$25.00 ©2009
0 50 100 150 200 250
0
0.2
0.4
0.6
0.8
1
1
Degree of m em bership
123 45
0 50 100 150 200 250
0
0.2
0.4
0.6
0.8
1
2
Degree of m em bership
12 345
0 50 100 150 200 250
0
0.2
0.4
0.6
0.8
1
3
Degree of mem bership
12345
Fig. 1 Gaussian membership functions for B,G,R planes
Figure 2 shows fuzzy decision tree using fuzzy ID3
algorithm for the skin-nonskin classification problem. We
have taken leaf selection threshold 0.75. In Fig. 2, root node is
represented by R = x
3
. There are total seven leaf nodes shown
by bold dotes. Children nodes have been terminated as leaf
nodes because their respective certainty thresholds (all
β
) are
greater than 0.75.
mNmS
ββ
and are prediction certainties of m
th
leaf node with respect to class skin and nonskin, respectively.
Fig. 2 Fuzzy decision tree for skin-nonskin classification problem
Certainty coefficients of all the leaf nodes are given as
below :
.
00.100.0
00.100.0
06.094.0
00.100.0
00.100.0
08.092.0
00.100.0
77
66
55
44
33
22
11
»
»
»
»
»
»
»
»
»
¼
º
«
«
«
«
«
«
«
«
«
¬
ª
=
»
»
»
»
»
»
»
»
»
¼
º
«
«
«
«
«
«
«
«
«
¬
ª
NS
NS
NS
NS
NS
NS
NS
ββ
ββ
ββ
ββ
ββ
ββ
ββ
Certainty coefficients can be calculated by standard
subsethood formula [14]. For example,
S2
β
can be calculated
by
()
()
()
()
() ()
,
1
71
1
71
7212
7212
¦
¦
=
=
×
×××
n
i
iFiF
n
i
iiFiiF
xx
yxyx
μμ
μμ
where n is total number of patterns, x
ji
is i
th
pattern of j
th
feature, and
()
jiF
x
jk
μ
is degree of membership of x
ji
to k
th
membership function on
j
th
feature.
Using this FDT, patterns are classified by starting from the
root node and then reaching to one or more than one leaf
nodes by following the path of degree of membership greater
than zero. One can use either
min-max-max or product-
product-sum
[14] reasoning mechanism over extracted rules to
calculate the degree of certainty with which an arbitrary
pattern can be classified to one class. In this paper, we have
used the later one. The
product-product-sum reasoning
mechanism consists of the following three steps:
a. For the operation to aggregate membership values of
fuzzy sets of node genres along the paths, the product is
adopted.
b.
For the operation of the total membership value of the
path of fuzzy evidences and the certainty of the class
attached to leaf-nodes, also the
product is adopted.
c. For the operation to aggregate certainties of the same
class from different paths, the
sum is adopted.
To put these steps in mathematical notations, let us consider
that there are total of
M paths of fuzzy decision tree and total
number of attributes on
m
th
path is P
m
. With this, firing
strength of
m
th
path is given by
()
,,...,1;
1
Mmx
m
P
j
mjmjm
==
∏
=
μμ
(1)
where
x
mj
is j
th
feature on m
th
path. Prediction certainty of
class-1 and class-2 by
m
th
path is given by
.,
21 mmmm
μβμβ
×× (2)
Finally, aggregate the predictions certainties of class-1 and
class-2 from different paths using the following formulas.
.
ˆ
ˆ
1
2
2
1
1
1
¦
¦
=
=
×=
×=
M
m
mm
M
m
mm
d
d
μβ
μβ
(3)
The predicted class y
ˆ
is given by winner-takes-all logic, i.e.,
.
ˆ
max
ˆ
1
q
Qq
dy
≤≤
= (4)
Centre and standard deviation matrix associated with each of
the path of fuzzy decision tree are given below :
.
63.10066.12
63.10075.9
46.958.80
46.993.90
46.902.90
46.958.80
40.1100
;
97.133050.227
97.133017.164
17.18706.1280
17.18765.2200
49.23495.820
49.23497.1700
45.2200
»
»
»
»
»
»
»
»
»
¼
º
«
«
«
«
«
«
«
«
«
¬
ª
=
»
»
»
»
»
»
»
»
»
¼
º
«
«
«
«
«
«
«
«
«
¬
ª
= SC
III. COMPUTATIONAL EXPERIMENTS
We have performed various computational experiments on
PC and on embedded hardware with specifications given in
Section II above. Our ten fold cross validation average
performance is 94.10 %. The average confusion matrix is
given below :
.
51.9248.7Nonskin
90.109.98Skin
NonskinSkin
»
»
»
¼
º
«
«
«
¬
ª
=conf
Above results shows that the algorithm is highly efficient in
declaring actual skin as skin, where as confusion of almost
7.5 % is involved for nonskin segments. We have executed the
proposed algorithm for various consumer images. Some of the
skin segmented and actual images are shown below for
illustration. To report the timing performance all the images
have been scaled to standard 640 * 480 (
i.e., VGA size)
resolution.
100 200 300 400 500
50
100
150
200
250
300
100 200 300 400 500
50
100
150
200
250
300
Fig. 3 Result on Chak De India group photograph. Timing 250 mSec.
200 400 600
100
200
300
400
200 400 600
100
200
300
400
Fig. 4 Result on Asian consumer image. Timing 250 mSec.
IV. CONCLUSIONS
In this paper, we have proposed B,G,R colour-based skin
segmentation approach using fuzzy decision tree. Very
compact FDT model using just seven leaf nodes (
i.e., fuzzy
rules) makes it very efficient for application into embedded
devices. Further, each fuzzy rule makes use of at the most two
attributes which makes the algorithm application fast enough
for the real world applications into products.
100 200 300 400 500 600
100
200
300
400
100 200 300 400 500 600
100
200
300
400
Fig. 5 Result on East Asian consumer image. Timing 216 mSec.
100 200 300 400 500 600
100
200
300
400
100 200 300 400 500 600
100
200
300
400
Fig. 5 Result on party photograph with varying illumination. Timing 216
mSec.
100 200 300 400 500 600
100
200
300
100 200 300 400 500 600
100
200
300
Fig. 6 Result on white race ladies. Timing 237 mSec.
200 400 600
100
200
300
400
500
200 400 600
100
200
300
400
500
Fig. 7 Result on white race ladies portrait photograph. Timing 250 mSec.
200 400 600
100
200
300
400
200 400 600
100
200
300
400
Fig. 8 Results on Black ladies with illumination. Timing 208 mSec.
200 400 600
100
200
300
400
200 400 600
100
200
300
400
Fig. 9 Multiple faces with diversity of age, race, gender. Timing : 250 mSec.
ACKNOWLEDGEMENTS
Authors are thankful to Samsung India Software R&D
Center for excellent research environment and opportunities.
R
EFERENCES
[1] S. Birchfield, “Elliptical head tracking using intensity gradients and
color histograms” in Proc. of CVPR 1998, pp 232-237.
[2] Q. Chen, H. Wu, and M. Yachida, “Face detection by fuzzy pattern
matching” in Proc. of 5
th
Int. Conf. on Computer Vision, 1995, pp.
591-597.
[3] C. Wang and M. Brandstein, “Multisource face tracking with audio and
visual data” in Proc. of IEEE Multimedia and Signal Processing, 1999,
pp. 169-174.
[4] R.-L. Hsu, M. Abdel-Mottaleb, and A.K. Jain, “Face detection in color
images”, IEEE Trans. PAMI, vol. 24, no. 5, pp. 696-706, 2002.
[5] N. Oliver, A. Pentland, and F. Berard, “Lafter : Lips and Face Real
Time Tracker” in Proc. of Computer Vision and Pattern Recognition,
1997, pp. 123-129.
[6] R. Schumeyer and K. Barner, “A color-based classifier for region
identification in video”, in Proc. of Visual Communications and Image
Processing, vol. 3309, 1998, pp. 189-200.
[7] A. Albiol, L. Torres, and E.J. Delp, “Optimal color spaces for skin
detection”, in Proc. of Int. Conf. on Image Processing, vol. 1, 2001, pp.
122-124.
[8] J. Brand and J. Mason, “A comparative assessment of three approaches
to pixel level human skin detection”, in Proc. of Int. Conf. on Pattern
Recognition, vol. 1, 2000, pp. 1056-1059.
[9] D. Chai and A. Bouzerdoum, “A Bayesian approach to skin color
classification in YCbCr color space”, in Proc. IEEE TENCON 2000,
vol. 2, pp. 421-424.
[10] G. Gomez, “On selecting color components for skin detection”, in
Proc. of ICPR, vol. 2, 2000, pp. 961-964.
[11] J.-C. Terrillon, M.N. Shirazi, H. Fukamachi, and S. Akamatsu,
“Comparative performance of different skin chrominance models and
chrominance faces for the automatic detection of human faces in color
images”, in Proc. of Int. Conf. on Face and Gesture Recognition, 2000,
pp. 54-61.
[12] Color FERET Image Database:
http://face.nist.gov/colorferet/request.html
.
[13] PAL Face Database from Productive Aging Laboratory, The University
of Texas at Dallas: https://pal.utdallas.edu/facedb/
.
[14] X.-Z. Wang, D.S. Yeung, and E.C.C. Tsang, “A comparative study on
heuristic algorithms for generating fuzzy decision trees”, IEEE
Transactions on SMC
− B, vol. 21, no. 2, pp. 215-226, 2001.
[15] Rajen B. Bhatt, Fuzzy-rough approach to pattern classification: hybrid
algorithms and optimization, PhD Thesis, Electrical Engineering
Department, IIT Delhi, India. Call number: 621-52 BHA-F, Accession
no: TH-3259, http://indest.iitd.ac.in/scripts/wwwi32.exe/[in=arphd]/
.
[16] N.R. Pal and J.C. Bezdek, “On cluster validity for fuzzy c-means
model”, IEEE Transactions On Fuzzy Systems, vol. 3, no.3, pp.370-
379, 1995.
[17] Rajen B. Bhatt and M.Gopal, “On the structure and initial parameter
identification of Gaussian RBF networks”, International Journal of
Neural Systems, 14 (6), pp. 1-8, 2004.
It is clearly evident from the results and timing information
that at most VGA image takes 250 mSec for the skin
segmentation. As a further research, we plan to include eye-
lips-nose localization algorithm for complete face detection
application and then detection of orientation of portrait images.
Citations
More filters
Journal Article•DOI•
An intelligent quality-based approach to fusing multi-source probabilistic information

[...]

Ronald R. Yager1, Frederick E. Petry2•
Iona College1, United States Naval Research Laboratory2
01 Sep 2016-Information Fusion
TL;DR: The objective here is to obtain quality-fused values from multiple sources of probabilistic distributions, where quality is related to the lack of uncertainty in the fused value and the use of credible sources.

55 citations

Journal Article•DOI•
Curvature-based method for determining the number of clusters

[...]

Yaqian Zhang1, Jacek Mańdziuk1, Jacek Mańdziuk2, Chai Hiok Quek1, Boon Wooi Goh1 •
Nanyang Technological University1, Warsaw University of Technology2
01 Nov 2017-Information Sciences
TL;DR: A simple yet powerful method for determining the number of clusters based on curvature that is computationally efficient and straightforward to implement and compared with 6 other approaches on a wide range of simulated and real-world datasets.

42 citations

Journal Article•
Path-Based Spectral Clustering: Guarantees, Robustness to Outliers, and Fast Algorithms

[...]

Anna Little, Mauro Maggioni, James M. Murphy
01 Jan 2020-Journal of Machine Learning Research
TL;DR: This work provides conditions under which the Laplacian eigengap statistic correctly determines the number of clusters for a large class of data sets, and proves finite-sample guarantees on the performance of clustering with respect to this metric when random samples are drawn from multiple intrinsically low-dimensional clusters in high-dimensional space.
Abstract: We consider the problem of clustering with the longest-leg path distance (LLPD) metric, which is informative for elongated and irregularly shaped clusters. We prove finite-sample guarantees on the performance of clustering with respect to this metric when random samples are drawn from multiple intrinsically low-dimensional clusters in high-dimensional space, in the presence of a large number of high-dimensional outliers. By combining these results with spectral clustering with respect to LLPD, we provide conditions under which the Laplacian eigengap statistic correctly determines the number of clusters for a large class of data sets, and prove guarantees on the labeling accuracy of the proposed algorithm. Our methods are quite general and provide performance guarantees for spectral clustering with any ultrametric. We also introduce an efficient, easy to implement approximation algorithm for the LLPD based on a multiscale analysis of adjacency graphs, which allows for the runtime of LLPD spectral clustering to be quasilinear in the number of data points.

34 citations

Journal Article•DOI•
Fuzzy logic color detection: Blue areas in melanoma dermoscopy images

[...]

Mounika Lingala1, R. Joe Stanley1, Ryan K. Rader, Jason R. Hagerty, Harold S. Rabinovitz, Margaret Oliviero, Iqra Choudhry, William V. Stoecker •
Missouri University of Science and Technology1
01 Jul 2014-Computerized Medical Imaging and Graphics
TL;DR: Fuzzy logic image analysis techniques were used to analyze three shades of blue in dermoscopic images for melanoma detection and can be extended to other image analysis problems involving multiple colors or color shades.

30 citations

Journal Article•DOI•
Integrated artificial intelligence algorithm for skin detection

[...]

Idoko John Bush1, Rahib H. Abiyev1, Mohammad Khaleel Sallam Ma’aitah1, Hamit Altıparmak1•
Near East University1
01 Jan 2018
TL;DR: A colour segmentation algorithm that works directly in RGB colour space without converting the colour space and corresponding output from data mapping of pseudo-polynomial is obtained from input dataset to the adaptive neuro fuzzy inference system (ANFIS).
Abstract: The detection of skin colour has been a useful and renowned technique due to its wide range of application in both analyses based on diagnostic and human computer interactions. Various problems could be solved by simply providing an appropriate method for pixel-like skin parts. Presented in this study is a colour segmentation algorithm that works directly in RGB colour space without converting the colour space. Genfis function as used in this study formed the Sugeno fuzzy network and utilizing Fuzzy C-Mean (FCM) clustering rule, clustered the data and for each cluster/class a rule is generated. Finally, corresponding output from data mapping of pseudo-polynomial is obtained from input dataset to the adaptive neuro fuzzy inference system (ANFIS).

19 citations

References
More filters
Journal Article•DOI•
Face detection in color images

[...]

Rein-Lien Hsu1, Mohamed Abdel-Mottaleb2, Anil K. Jain1•
Michigan State University1, University of Miami2
01 May 2002-IEEE Transactions on Pattern Analysis and Machine Intelligence
TL;DR: A face detection algorithm for color images in the presence of varying lighting conditions as well as complex backgrounds is proposedBased on a novel lighting compensation technique and a nonlinear color transformation, this method detects skin regions over the entire image and generates face candidates based on the spatial arrangement of these skin patches.
Abstract: Human face detection plays an important role in applications such as video surveillance, human computer interface, face recognition, and face image database management. We propose a face detection algorithm for color images in the presence of varying lighting conditions as well as complex backgrounds. Based on a novel lighting compensation technique and a nonlinear color transformation, our method detects skin regions over the entire image and then generates face candidates based on the spatial arrangement of these skin patches. The algorithm constructs eye, mouth, and boundary maps for verifying each face candidate. Experimental results demonstrate successful face detection over a wide range of facial variations in color, position, scale, orientation, 3D pose, and expression in images from several photo collections (both indoors and outdoors).

2,075 citations

Journal Article•DOI•
On cluster validity for the fuzzy c-means model

[...]

Nikhil R. Pal1, James C. Bezdek1•
University of West Florida1
01 Aug 1995-IEEE Transactions on Fuzzy Systems
TL;DR: Limitation analysis indicates, and numerical experiments confirm, that the Fukuyama-Sugeno index is sensitive to both high and low values of m and may be unreliable because of this, and calculations suggest that the best choice for m is probably in the interval [1.5, 2.5], whose mean and midpoint, m=2, have often been the preferred choice for many users of FCM.
Abstract: Many functionals have been proposed for validation of partitions of object data produced by the fuzzy c-means (FCM) clustering algorithm We examine the role a subtle but important parameter-the weighting exponent m of the FCM model-plays in determining the validity of FCM partitions The functionals considered are the partition coefficient and entropy indexes of Bezdek, the Xie-Beni (1991), and extended Xie-Beni indexes, and the Fukuyama-Sugeno index (1989) Limit analysis indicates, and numerical experiments confirm, that the Fukuyama-Sugeno index is sensitive to both high and low values of m and may be unreliable because of this Of the indexes tested, the Xie-Beni index provided the best response over a wide range of choices for the number of clusters, (2-10), and for m from 101-7 Finally, our calculations suggest that the best choice for m is probably in the interval [15, 25], whose mean and midpoint, m=2, have often been the preferred choice for many users of FCM >

1,724 citations

Proceedings Article•DOI•
Elliptical head tracking using intensity gradients and color histograms

[...]

Stan Birchfield1•
Stanford University1
23 Jun 1998
TL;DR: An algorithm that is able to track a person's head with enough accuracy to automatically control the camera's pan, tilt, and zoom in order to keep the person centered in the field of view at a desired size is presented.
Abstract: An algorithm for tracking a person's head is presented. The head's projection onto the image plane is modeled as an ellipse whose position and size are continually updated by a local search combining the output of a module concentrating on the intensity gradient around the ellipse's perimeter with that of another module focusing on the color histogram of the ellipse's interior. Since these two modules have roughly orthogonal failure modes, they serve to complement one another. The result is a robust, real-time system that is able to track a person's head with enough accuracy to automatically control the camera's pan, tilt, and zoom in order to keep the person centered in the field of view at a desired size. Extensive experimentation shows the algorithm's robustness with respect to full 360-degree out-of-plane rotation, up to 90-degree tilting, severe but brief occlusion, arbitrary camera movement, and multiple moving people in the background.

871 citations

Proceedings Article•DOI•
Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images

[...]

J.-C. Terrillon, M.N. Shirazi, H. Fukamachi, S. Akamatsu
26 Mar 2000
TL;DR: An analysis of the performance of two different skin chrominance models and of nine different chrominance spaces for the color segmentation and subsequent detection of human faces in two-dimensional static images shows that, for each chrominance space, the detection efficiency depends on the capacity of each model to estimate the skin Chrominance distribution and, most importantly, on the discriminability between skin and "non-skin" distributions.
Abstract: This paper presents an analysis of the performance of two different skin chrominance models and of nine different chrominance spaces for the color segmentation and subsequent detection of human faces in two-dimensional static images. For each space, we use the single Gaussian model based on the Mahalanobis metric and a Gaussian mixture density model to segment faces from scene backgrounds. In the case of the mixture density model, the skin chrominance distribution is estimated by use of the expectation-maximisation (EM) algorithm. Feature extraction is performed on the segmented images by use of invariant Fourier-Mellin moments. A multilayer perceptron neural network (NN), with the invariant moments as the input vector, is then applied to distinguish faces from distractors. With the single Gaussian model, normalized color spaces are shown to produce the best segmentation results, and subsequently the highest rate of face detection. The results are comparable to those obtained with the more sophisticated mixture density model. However, the mixture density model improves the segmentation and face detection results significantly for most of the un-normalized color spaces. Ultimately, we show that, for each chrominance space, the detection efficiency depends on the capacity of each model to estimate the skin chrominance distribution and, most importantly, on the discriminability between skin and "non-skin" distributions.

437 citations

Proceedings Article•DOI•
A comparative assessment of three approaches to pixel-level human skin-detection

[...]

J. Brand1, John Mason•
Swansea University1
03 Sep 2000
TL;DR: This paper assesses the merits of three different approaches to pixel-level human skin detection based on a 3D RGB probability map first implemented by Rehg-Jones (1999), which is a numerically efficient approach made possible to compute only with the availability of a large appropriately labeled database.
Abstract: This paper assesses the merits of three different approaches to pixel-level human skin detection. The basis for the 3 approaches has been reported in the literature. The first two approaches use simple ratios and colour space transforms respectively, whereas the third is a numerically efficient approach based on a 3D RGB probability map, first implemented by Rehg-Jones (1999). The Bayesian probabilities are made possible to compute only with the availability of a large appropriately labeled database. Over 12000 images from the Compaq skin and non-skin databases are used to quantitatively assess the three approaches. Thresholds are determined empirically to detect 95% of all skin-associated pixels and assessment is then made in terms of the percentage of non-skin pixels incorrectly accepted. The lowest of these false acceptance rates is found to be about 20% given by the 3D probability map.

256 citations

Related Papers (5)
A Path-based Fuzzy Approach to Color Image Segmentation

[...]

11 Jul 2021
Jesús Chamorro-Martínez, Miriam Mengibar-Rodriguez, Pedro Manuel Martínez-Jiménez
Adaptive Digital Makeup

[...]

26 Nov 2009
Abhinav Dhall, Gaurav Sharma, Rajen B. Bhatt, Ghulam Mohiuddin Khan 
UCI Machine Learning Repository

[...]

01 Jan 2007
A. Asuncion
Image Segmentation by Searching for Image Feature Density Peaks

[...]

13 Jun 2018-Applied Sciences
Sun Zhe, Qi Meng, Jian Lian, Weikuan Jia, Wei Zou, Yunlong He, Hong Liu, Yuanjie Zheng 
Optimization of Multiresolution Segmentation for Object-Oriented Road Detection from High-Resolution Images

[...]

07 Mar 2016-Canadian Journal of Remote Sensing
Fatemeh Saba, Mohammad Javad Valadan Zoej, Mehdi Mokhtarzade
Frequently Asked Questions (11)
Q1. What have the authors contributed in "Efficient skin region segmentation using low complexity fuzzy decision tree model" ?

The authors propose an efficient skin region segmentation methodology using low complexity fuzzy decision tree constructed over B, G, R colour space. 

Fuzzy decision trees are powerful, top-down, hierarchical search methodology to extract easily interpretable classification rules [14, 15]. 

Their aim is to build an efficient human object presencealgorithm and localize at least one face for categorization of consumer images into portraits and non portraits for Auto Album generation. 

One can use either min-max-max or productproduct-sum [14] reasoning mechanism over extracted rules to calculate the degree of certainty with which an arbitrary pattern can be classified to one class. 

Fuzzy decision trees are composed of a set of internal nodes representing variables used in the solution of a classification problem, a set of branches representing fuzzy sets of corresponding node variables, and a set of leaf nodes representing the degree of certainty with which each class has been approximated. 

Fuzzy decision trees are composed of a set of internal nodes representing variables used in the solution of a classification problem, a set of branches representing fuzzy sets of corresponding node variables, and a set of leaf nodes representing the degree of certainty with which each class has been approximated. 

Verycompact FDT model using just seven leaf nodes (i.e., fuzzy rules) makes it very efficient for application into embedded devices. 

Using this FDT, patterns are classified by starting from the root node and then reaching to one or more than one leaf nodes by following the path of degree of membership greater than zero. 

63.10066.12 63.10075.9 46.958.80 46.993.90 46.902.90 46.958.80 40.1100 ; 97.133050.227 97.133017.164 17.18706.1280 17.18765.2200 49.23495.820 49.23497.1700 45.2200 == SCThe authors have performed various computational experiments on PC and on embedded hardware with specifications given in Section II above. 

This makes their training Db is of the dimension 51444 * 4 where first three columns are B,G,R (x1, x2, and x3 features) values and fourth column is of the class labels (decision variable y). 

This makes their training Db is of the dimension 51444 * 4 where first three columns are B,G,R (x1, x2, and x3 features) values and fourth column is of the class labels (decision variable y).