mathematical model of skin color for face detection
DESCRIPTION
TRANSCRIPT
Mathematical Model of Skin
Color for Face Detection
Setiawan Hadi, Adang Suwandi A,
Iping Supriana S, Farid Wazdi
Universitas Padjadjaran, Bandung, Indonesia
Institut Teknologi Bandung, Indonesia
Introduction
• Face detection is a preprocessing step of facial recognition system (Essential)
Introduction
• Goal: localize face(s) in digital image and/or in real time video
Skin-based Face Detection
• Skin important element in detecting image that contain skin or skin-like region
• Skin is special
– covers most of the face image area
– skin of different people appears to vary over a wide
range, however the differ is much less in colour
(chromaticity) than brightness
– detection of skin area in digital image are more
practical and easy to implement.
Our Research Approach
• Skin colour is represented in 3 colour space (rg, HSB and YCbCr)
• Using mathematical model that is generated from face images
• Implement morphological filters for enhancing face image
• Apply 4-neigbourhood ellipse representation for localizing face
• Using local face databases for experiment
Face in Colour Spaces RGB space
HSB space
YCbCr space
Generating Face Skin Model
• Calculate mean and covariance chromaticity of training images for each colour space
• Training images are prepared semi-manually
M k =
n X
i = 1
1
± i T i
M k = 1
± 1
T 1 + 1
± 2
T 2 + ¢ ¢ ¢ + 1
± n ¡ 1
T n ¡ 1 + 1
± n
T n
Sample of generated skin colour model
Skin distribution in Colour Spaces
Face Detection
Algorithm
w h e r e P s k i n ( i ; j ) i s p r o b a b i l i t y o f
p i x e l P a s s k i n p i x e l i f i n c l u d e d
i n d i s t r i b u t i o n s k i n m o d e l D M k
f o r e v e r y c o l o u r s p a c e s R n .
P s k i n ( i ; j ) = P s k i n ( i ; j ) 2 D M k 8 P ( i ; j ) ^ 8 R n
Visual Result
Experiments
Concluding remarks
• Skin colour is modelled using using mean-covariance characteristics
• Skin colour is represented in 3 colour space
• Skin model is used for face detection, with support morphological filter dan 4-neigborhood ellipse generation
• Experiment has been performed using 7 sets of face database, >>3000 face images
• Accuracy needs to be improved
Next Work
• Multiple image detection
• Symmetry and features detection
• Adding geometric-based detection to increase detection accuracy
• Algorithm improvement for efficient yet faster detection
• Realtime face detection
• Face recognition module
Mathematical Model of Skin
Color for Face Detection
Setiawan Hadi, Adang Suwandi A,
Iping Supriana S, Farid Wazdi
Universitas Padjadjaran, Bandung, Indonesia
Institut Teknologi Bandung, Indonesia