Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/317571
Title: | Generalised image quality preserving algorithm for stego destruction |
Researcher: | Amritha PP |
Guide(s): | Sethumadhavan M |
Keywords: | Engineering and Technology, Radiometric and geometric operations, steganalysis, steganography; Computation theory, Image processing, Intelligent computing, Markov feature,PSNR, SSIM-Structured Similarity Index Measure |
University: | Amrita Vishwa Vidyapeetham (University) |
Completed Date: | 2019 |
Abstract: | Covert transmission of information hidden in different media to either a general newlineor targeted audience constitutes steganography. However, this technique can be newlinemisused to transmit undesirable information. Traditionally the removal of such newlinecontent necessitated the knowledge of the steganographic algorithm used. However, newlinewe address the scenario where such stego is removed using generic image newlineprocessing operations which involves convolution and smoothening of image depending newlineon the type of filter and the window size used. The degradation caused newlineby these operations are partially restored using variational deconvolution. This removal newlineprocess can be done without assuming any knowledge of the steganographic newlinealgorithm used. Our procedure has been tested on a variety of steganographic newlinealgorithms including Random LSB, _ LSB, PVD, OutGuess, HUGO-BD, WOW, newlineSynch and J-UNIWARD. By applying universal steganalysis we found that all images newlinewhich have been subjected to our procedure have become stego free. However, newlinea direct evaluation of the stego content assuming knowledge of the stego content newlineand its location showed that 80 percentage of the stego is removed without significantly impacting the visual image quality. Video stream containing isolated newlinestatic images have been addressed in this thesis. The peak signal-to-noise ratio newlineand structural similarity metric values of cleaned images and videos are found to newlinebe in the range 30 dB - 40 dB and 0.81 - 0.99 respectively newline newline |
Pagination: | x,142 |
URI: | http://hdl.handle.net/10603/317571 |
Appears in Departments: | Center for Cyber Security Systems and Networks |
Files in This Item:
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: