Proceedings of the 2008 IEEE
International Conference on Robotics and Biomimetics
Bangkok, Thailand, February 21 - 26, 2009
Prefessor : 謝銘原
Student : 謝琮閔
ID : M9820113
PPT 100％原創
Abstract (1/4)
 In human face detection applications, face region
usually form an inconsequential part of images.
 Preliminary segmentation of images into regions that
contain "non-face" objects and regions that may
contain "face" candidates .
Abstract (2/4)
 Color information based methods take a great
attention, because colors have obviously character and
robust visual cue for detection.
 This paper proposed a new method based on RGB
color centroids segmentation (CCS) for face detection.
Abstract (3/4)
 Include two parts, first part is color image
thresholding based on CCS.
 Second part is face detection based on region growing
and facial features structure character combined
method.
Abstract (4/4)
 The experimental results show the ideal thresholding
result and better than the result of other color space
analysis based thresholding methods.
 Proposed method can conquer the influence of
different background conditions, position, scale
instance and orientation in images from several photo
collections and database; the effect is also better than
existing skin color segmentation based methods.
INTRODUCTION
 Nowadays, many application technologies are
developed to secure access control based on
biometrics recognition such as fingerprints, iris
pattern and face recognition.
 Many applications such as financial transactions,
monitoring system, credit card verification, ATM
access, personal PC access, video surveillance etc.
Recent surveys on face detection
(1/3)
 Principal component analysis (PCA),
 Neural networks (NN),
 Support vector machines (SVM),
 Hough transform (HT),
 Geometrical template matching (GTM),
 Color analysis
 etc.
Recent surveys on face detection
(2/3)
 PCA need create Eigen face by many dimension data and
training sample data.
 The NN require a large number "face" and "non-face"
images to train respectively for getting the network model .
 SVM are a linear classifier and can classify goal region in
hyper-plane.
 HT and GTM were incorporated to detect gray faces in
real time applications.
Recent surveys on face detection
(3/3)
 A combination of holistic and feature-based
approaches is a promising approach to face detection
as well as face recognition.
 This paper proposed a color image thresholding
algorithm based on color centroids segmentation (CCS)
for detection and tracking is able to handle a wide
range of variations in color images sequence, various
backgrounds can detect face region effetely.
COLOR IMAGE THRESHOLDING
BASED ON CCS
 This section introduce how to thresholding the color
image by transform RGB components of RGB 3-D color
space to 2-D polar coordinate system.
 Use multi-threshold to segment the centroids region.
 By analyzing and processing, it can cluster the color of
image to 2~7 colors by 2~7 thresholds for require and
the effect better than traditional methods.
A. Color Triangle (1/3)
 To create the color triangle, a standard 2-D Cartesian
coordinate system is used to describe R, G and B values
and then transform it to polar coordinate system as (1)
show:
A. Color Triangle (2/3)
 By the following steps can create the color triangle:
Step 1: create a standard 2-D polar coordinate system;
Step 2: create three color vectors to reflect R, G and B
colors; every vector’s value range is ሾ0, 255ሿ and
alternation 120° reciprocally.
Step 3: connect the three apexes.
A. Color Triangle (3/3)
 After above processes, the color triangle can be created
as Fig. 1. For different R, G and B values, the shape of
triangle is changeable. No matter the R, G and B
value change the main structure are fixed.
B. Color Centroids Hexagon
Region Distributing (1/3)
 R, G, B vectors direction is fixed and the value is
change from 0 to 255, so different combination of R,
G, B value will create different color, and the shape of
color triangle is changed too.
 The different shape triangle has different centroid, and
the centroids distributing region of color triangle is
show hexagon as Fig. 2.
B. Color Centroids Hexagon
Region Distributing (2/3)
 In this hexagon region, it divided to 7 regions: R (Red),
G (Green), B (Blue), C (Cyan), M (Magenta), Y (Yellow)
and L (Luminance, achromatic) regions. In Fig. 2 we
use seven threshold curves as the dividing line for
thresholding.
B. Color Centroids Hexagon
Region Distributing (3/3)
 The R, G and B values are closely, no matter small or
large it only reflect the luminance information (weak
color information).
 The centroids of corresponding color triangles will in a
circular region (L region). And other six color regions
reflect the color character of R, G and B combination.
C. Color Centroids Segmentation
Thresholds Acquisition (1/7)
 Considering the L region usually is not the goal region
and existing method cannot effective to divide white
and black region usually. This region is noise region, so
clustering the value of this kind to one region wills
effective to ignore the influence of white, black and
other achromatic region.
 Here let
as the threshold of L region,
angle, the function of threshold curve is:
as the
C. Color Centroids Segmentation
Thresholds Acquisition (2/7)
 The other six regions which around the L region as
follows formulas show:
C. Color Centroids Segmentation
Thresholds Acquisition (3/7)
 In formula (2) and (3),
and
are the thresholds, and the initial value of them is 5,
60°, 120°, 180°, 240°, 300° and 360°.
 Considering the advantages and disadvantages, here
proposed an automatic thresholds selection method to
get the thresholding for different scene.
C. Color Centroids Segmentation
Thresholds Acquisition (4/7)
 By analyzing largely face region distributing, we can
see that the color of face usually included in R region
and lean to Y region.
 To display distributing character more clearly, we
transform the Polar coordinate system to Cartesian
coordinate system as Fig. 3(d) to reflect the
distributing of centroids.
C. Color Centroids Segmentation
Thresholds Acquisition (5/7)
 In the Fig. 3(d) horizontal axis is
vertical axis is
and other six vertical
color-line are color threshold curves
 The face region is belonging to Red and Yellow region
C. Color Centroids Segmentation
Thresholds Acquisition (6/7)
 By observing many face included image in different
condition, we let the threshold curve
can move to left or right 20° for find best value.
 Then find the left and right valley bottom respectively
as
method.
in the fix rang by histogram analysis
C. Color Centroids Segmentation
Thresholds Acquisition (7/7)
 In Fig. 3, (a) is original image and (b) showing the
distributing of color centroids. By transforming Fig.
3(b) to (d) and calculate the
we can get
the pre-face region, and the binary image show in Fig.
3(c):
FACE DETECTION AND TRACKING
A. Thresholding
 1. Thresholding Based on CCS
The binary image can be got as Fig. 4(b). From the
result we can see that the white background region
(wall), pale color clothing region ①, ④ and ⑤ and
dark color clothing region ⑦ are clustering to black
and only the goal region clustering to white.
 2. Correction Using Nonlinear Thresholding
For denoise the incorrect region, this paper adopt
the nonlinear thresholding method to correct the
binary image which thresholdinged by CCS.
 The hair region ② and ⑧, so use (5) processed image
to correct the CCS based method processed the image
with and operation can get idea result as follows:
 Fig. 4(d) is the corrected binary image, it correct the
region ②, ⑥ and ⑧ effetely.
B. Pre-face Region Decision
 After get the idea binary image, the white region is the
wait-decision region. Here all wait-decision regions
are analysed in a selection process and some of them
accepted by aspect ratio and size.
 Accepted by aspect ratio:
here C is aspect ratio,L is the length of boundary. S is
the area of wait-decision region.
If
, it will be accepted.
 Accepted by size:
After accepted by aspect ratio, then calculate the
average area
of all wait-decision regions without
the largest and smallest regions.
If
it will be accepted.
C. Face Region Tracking
 After face region fixed, use a circle to draw it by follows:
Step1: divide the face region to 9 blocks and
thresholding respectively as Fig. 6.
Step2: wipe off noise region by median filter.
Step3: fix eyes and mouth region and then calculate the
area centroids of eyes and mouth respectively.
Step4: draw a circumcircle (blue circle of Fig. 6) of
triangle which created by the three centroids.
Then use its 1.5 times’ concentric circle (green
circle of Fig. 6) to mark face.
EXPERIMENTAL RESULTS ANALYZE AND COMPARISON
A. The Result of Proposed Method
 1. Thresholding result and compare with other
methods:
 2. Face detection result
Fig. 8(a) is a white background image with multi-face;
usually the white clothing region will influence the
thresholding result which method based on luminance
or histogram analysis and the pink clothing region will
influence the thresholding result which method based
on color analysis.
 Fig. 9 shows a multi-person image under indoor
situation and everyone ware different color clothing.
From Fig. 9(b) we can see that proposed method can
conquer the influence of the light, ground region and
different color of clothing effectively.
 Fig. 10 is one frame of video under outdoor situation.
In this image, some region of background can
influence thresholding result, because the color is
near face color.
B. Compare with reference[22]
 Fig. 11(a) is [22] used image, Passing analysis the method based
on skin information of [22] and experiment result, it only adopt
to propose simple background and little color influence images.

[22] Y. Wu, and X. Ai, "Face Detection in Color Images Using AdaBoost Algorithm Based on Skin Color
Information," 2008 Int’l Workshop on Knowledge Discovery and Data Mining, pp. 33-342, Jan.
2008.
C. Compare with reference [23]
 Fig. 12 shows the sample image of reference [23], and Fig. 12(b)
and Fig. 12(d)~(f) is from experiment result of [23].
[23] L. Sabeti, and Q. M. J. Wu, "High-speed Skin Color Segmentation for Real-time Human Tracking," 2007
IEEE Int’l Conf. on Systems, Man and Cybernetics, pp. 2378-2382, Oct. 2007
CONCLUSIONS
 All the experiment results show that the proposed
method can get ideal detection and tracking result
under complex background, multi-face and color
influence.
 The future works are how to make the CCS method
more quickly and have better thredholded effect for
detecting and tracking .