Smart Traveller with Visual
What is Smart Traveller?
• Mobile Device which is convenience for a
traveller to carry
• E.g. Pocket PC, Mobile Phone
What is Visual Translator?
• Recognize the foreign text and translate it
into native language
• Detect the face and recognize it into name
• Simple (Computational low power)
• Lightweight (Low Storage)
• User Friendly
Core Pattern Recognition Model
Find Each Quantify the Assign Label
Object from object by some for each object
the Image characteristics
Image Feature Classification
Input Image Object Image Feature Vector Object Type
• Language: Korean
• Target: Sign, Guidepost
– Contrast in Color
– Printed Character
– Using Color Histogram to binarize the image for the
background and the character
• Text Region Segmentation
– User Define Method
– Edge Detection with horizontal and vertical
• Stroke Extraction
– Labeling of connected component Algorithm
• Stroke Features
– Number of Junctions, Corners
– Any Hole
• Gabor Features
• Minimum Euclid Distance
• Learn the Decision Tree by training
•Find Face Region
•Find the potential eye region
•Locate the iris and eyelids
Find Face Region - Color-based
• We used this method because of its
simplicity and robustness.
• Usually RGB color model will be
transformed to other color modes such as
YUV (luminance-chrominance) and HSB
(hue, saturation and brightness)
• We use YUV or YCbCr color model.
• Y component is used to represent the
intensity of the image
• Cb and Cr are used to represent the blue
and red component respectively.
• Y, Cb ,Cr component image
Y Cb Cr
Representation of skin color
• We just use a
equation to model
Representation of skin color
• The white regions represent the
skin color pixels
• We distribute some agent in the image uniformly.
• Then each agent will check whether the pixel is
a skin-like pixel and not visited by the other
• If yes, it will produce 4 more agents at its four
• If no, it will move to one of four neighboring
points randomly and decrease its lifespan by 1.
When its lifespan becomes zero, it will be
removed from the image.
• This agent produce 4
• The advantage of this algorithm is that we
need not to search the whole image.
• Therefore, it is fast.
• 19270 of 102900
pixels is searched
• There are 37 regions
• Each color regions
regions searched by a
• After the segmentation of face region, we
have some parts which are not regarded
as skin color.
• They are probably the region of eye and
• We only consider the red component of
these regions because it usually includes
the most information about faces.
• We extraction such
• The red region
represent the region
which is not skin color.
We do the following on the regions of
potential eye region
1. Histogram equalization
3. Template matching
Threshold with < 49
Locating the iris and eyelids
We plan to use the following methods to
improve the face detection
We can use these methods to locate the iris
and eyelid precisely.
– Correlation variance filter
– Deformable template