<fmt:message key='jsp.layout.header-default.alt'/>  
 

DSpace@UM >
Faculty of Computer Science and Information Technology >
Masters Dissertations: Computer Science >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1812/993

Title: Enhancement of steganography metrics scheme to assess the quality of image
Authors: Ali Khadair Kadam Al-Frajat
Keywords: Steganography
Messages hiding
Information security
Data hiding
Issue Date: 2011
Publisher: University Malaya
Abstract: Steganography is the art and science of hiding messages within digital multimedia files so as to avoid detection or suspicion from would be hackers. The primary aim of steganography is to hide messages inside harmless multimedia files in a way that does not allow any suspicion that there is an embedded message. In order to achieve this task, one needs to measure the amount of distortion being added to the steganographic image to determine its quality. Currently, there is no acceptable standard metric or measurement that could be used to measure the quality of the steganographic images. Different metrics and software had been developed in the past to ensure the quality of steganography and these include peak signal-to-noise ratio(PSNR), signal-to-noise ratio (SNR), histogram, mean square error (MSE), root mean square error (RMSE) and human vision test. The researcher had found that these metrics are grossly inadequate to be used as a standard measurement. In this research study, the researcher has chosen four of the existing metrics and proposed an enhanced and refined scheme of SNR, PSNR, MSE and RMSE metrics using image segmentation. The enhanced scheme divides an image into small segments and compares each segment from the steganographic image with the mirror segment of the original image and reports the differences in the pixel values between both the images segment. The distortion level in each image segment is evaluated by PSNR, SNR, MSE and RMSE metrics based on the differences in pixel values. In addition to this, a detailed review of related literature had emphasised that images have limited capacity to hide messages. Conversely, video files contain numerous frames where each frame represents an image implying that the capacity to hide messages is greater in video files. The researcher would further wish to propose a video based steganography as test case for the enhanced metrics. Video based steganography would include an encrypted hash code using a neural network. The result of applying PSNR, SNR, MSE and RMSE on smaller image segments is better in term of reliability, accuracy and provides detailed information about the distorted parts. The enhanced scheme is significant as it can be used for image processing measurement such as compression and texture analysis. The new steganographic video had been tested using the enhanced metrics and the output results show both systems are giving the expected result.
Description: Dissertation (M.C.S.) -- Faculty of Computer Science & Information Technology, University of Malaya, 2011.
URI: http://dspace.fsktm.um.edu.my/handle/1812/993
Appears in Collections:Masters Dissertations: Computer Science

Files in This Item:

File Description SizeFormat
Thesis.pdfChapters9.56 MBAdobe PDFView/Open
Preface.pdfPreface527.79 kBAdobe PDFView/Open


This item is protected by original copyright



Their Tags: quality measurement of the steganographic images;

Your Tags:

 

  © Copyright 2008 DSpace Faculty of Computer Science and Information Technology, University of Malaya . All Rights Reserved.
DSpace@UM is powered by MIT - Hawlett-Packard. More information and software credits. Feedback