18-03-2011, 09:19 AM
Skin Tone based Secret Data hiding in Images
Presented by:
B.Rajendraprasad
A.Dhileepan
V.Jayaprakash
[attachment=10449]
abstract
Here secret data is embedded within skin region of image that will provide an excellent secure location for data hiding. For this skin tone detection is performed using HSV (Hue, Saturation and Value) color space. Additionally secret data embedding is performed using frequency domain approach - DWT (Discrete Wavelet Transform), DWT outperforms than DCT (Discrete Cosine Transform). Secret data is hidden in one of the high frequency sub-band of DWT by tracing skin pixels in that sub-band. Different steps of data hiding are applied by cropping an image interactively. Cropping results into an enhanced security than hiding data without cropping i.e. in whole image, so cropped region works as a key at decoding side. This study shows that by adopting an object oriented steganography mechanism, in the sense that, we track skin tone objects in image, we get a higher security. And also satisfactory PSNR (Peak- Signal-to-Noise Ratio) is obtained.
problem statement
Cryptography
Cryptology prior to the modern age was almost synonymous with encryption, the conversion of information from a readable state to apparent nonsense.
The sender retained the ability to decrypt the information and therefore avoid unwanted persons being able to read it.
problem description
The drawbacks of cryptography are frequently overlooked as well.
In medium of cryptography the encrypted form is visually see by every one. so they known the cryptography is done by there.
These unnatural messages usually attract some unintended observers’ attention
introduction
Biometrics comprises methods for uniquely recognizing humans based upon one or more intrinsic physical or behavioral traits.
In computer science, in particular, biometrics is used as a form of identity access management and access control.
basic theory
Steganography is the art and science of writing hidden messages in such a way that no one, apart from the sender and intended recipient, suspects the existence of the message, a form of security through obscurity.
The advantage of steganography, over cryptography alone, is that messages do not attract attention to themselves.
research issue
Steganographic techniques
Multimedia Security
Usage in modern printers
Alleged use by intelligence services
objective
Implementing a Steganography based Biometric feature (Skin Tone)
Embedding the data in frequency domain of image
Improving the security of hiding data
Embedding Block Diagram
Extraction Block Diagram
content
Skin Color Tone Detection
Discrete Wavelet Transform (DWT)
Embedding Process
Extraction Process
Performance of the proposed method
Skin Color Tone Detection
The simplest way to decide whether a pixel is skin color or not is to explicitly define a boundary.
RGB matrix of the given color image can be converted into different color spaces to yield distinguishable regions of skin or near skin tone.
Mainly two kinds of color spaces are exploited in the literature of biometrics which are
HSV (Hue, Saturation and Value)
YCbCr (Yellow, Chromatic Blue, Chromatic red)
Color space used for skin detection in this work is HSV.
Any color image of RGB color space can be easily converted into HSV color space.
We found that human flesh can be an approximation from a sector out of a hexagon with the constraints:
Smin= 0.23, Smax =0.68, Hmin =0 and Hmax=50
HSV COLOR SPACE
Instinctive color characteristics such as tint, shade and tone (or family, purity and intensity) form the basis of HSV model.
The colors are defined within a hexcone, with the coordinate system being cylindrical.
The value of hue H varies from 0 to 360º.
The process for the transformation from RGB to HSV can be briefed as follows.
[file,path] = uigetfile('*.jpg','*.png','Pick an Image File');
a = imread(file);
a=imresize(a,[256 256]);
subplot(2,2,1);imshow(a,[]);
[r c p] = size(a);
HSV=rgb2hsv(a);
subplot(2,2,2);imshow(HSV);
HSV(:,:,1) = HSV(:,:,1)*360;
h = HSV(:,:,1);
s = HSV(:,:,2);
v = HSV(:,:,3);
[r c p]=size(a);
d=zeros(r,c);
for i=1:r;
for j=1:c;
if ((h(i,j)<.25)&((s(i,j)<0.68)& (s(i,j)>0.10)))
d(i,j)=1;
end
end
end
d = medfilt2(d,[3 3]);
subplot(2,2,3);
imshow(d);
title('Mask image');
helpdlg('Skin detection is done');
OUTPUT