Image steganography based on discrete wavelet transform and enhancing resilient backpropogation neural network
العناوين الأخرى
إخفاء صورة اعتماد على التحويل الموجي المتقطع و الشبكة العصبية المرنة المحسنة ذات الانتشار الخلفي
مقدم أطروحة جامعية
مشرف أطروحة جامعية
Naum, Riyad Shakir
al-Hammuz, Sadiq O.
أعضاء اللجنة
الجامعة
جامعة الشرق الأوسط
الكلية
كلية تكنولوجيا المعلومات
القسم الأكاديمي
قسم علم الحاسوب
دولة الجامعة
الأردن
الدرجة العلمية
ماجستير
تاريخ الدرجة العلمية
2015
الملخص الإنجليزي
Steganography is the science and art of covert communication.
it allows the undercover information transmission and conceal the existence of message itself in content such as video, audio, or image to protect the transmitted information from intruders and unwanted recipients.
in past decade, a variety of researches have been conducted on various steganographic schemes in both spatial and transform domain.
In this research, a novel image steganography system that hides both encrypted color image and secret key inside another color cover image was proposed using a combination of Discrete Wavelet Transform Technique (DWT) and Enhanced Resilient Backpropagation Neural Network (ERPROP).
In this research, we apply the DWT for all color layers (Red, Green, and Blue) separately for both cover and secret image with different levels; 1-level for the secret image and 4-level for cover image where encrypted coefficients of sub bands of the secret image are embedded in the corresponding sub bands of the cover image.
The enhanced resilient backpropagation neural network is applied in two stages.
The first stage is to choose the best cover image that will be used to conceal the secret image, while the second stage is to choose the best embedding threshold that will be used to determine the embedding locations in both embedding and extraction phases.
This research, takes advantage of combination between cryptography and steganography to enhance the security and robustness of the system where the sub bands of the secret image converted to bit streams and then encrypted before the embedding phase.
This system was implemented using MATLAB 7.14, R2012a, and it is proven to be pre-eminence, in comparison with other existing steganographic systems in terms of Peak Signal-to- Noise Ratio (PSNR) and capacity.
The PSNR of embedding phase reaching up to (112.4780) dB and the secret image is recovered with PSNR reaching up to (93.1047) dB.
These satisfactory results are fulfilled in combination with multilayer security.
Therefore, our proposed system achieved the steganographic goals that was built for.
التخصصات الرئيسية
تكنولوجيا المعلومات وعلم الحاسوب
عدد الصفحات
96
قائمة المحتويات
Table of contents.
Abstract.
Abstract in Arabic.
Chapter One : Introduction.
Chapter Two : Literature review.
Chapter Three : Principles and fidelity criteria of steganography.
Chapter Four : Artificial neural networks.
Chapter Five : Proposed artificial neural network-steganography system.
Chapter Six : Experimental results, conclusion and future work.
References.
نمط استشهاد جمعية علماء النفس الأمريكية (APA)
al-Nuaymi, Ahmad Shihab Ahmad. (2015). Image steganography based on discrete wavelet transform and enhancing resilient backpropogation neural network. (Master's theses Theses and Dissertations Master). Middle East University, Jordan
https://search.emarefa.net/detail/BIM-699386
نمط استشهاد الجمعية الأمريكية للغات الحديثة (MLA)
al-Nuaymi, Ahmad Shihab Ahmad. Image steganography based on discrete wavelet transform and enhancing resilient backpropogation neural network. (Master's theses Theses and Dissertations Master). Middle East University. (2015).
https://search.emarefa.net/detail/BIM-699386
نمط استشهاد الجمعية الطبية الأمريكية (AMA)
al-Nuaymi, Ahmad Shihab Ahmad. (2015). Image steganography based on discrete wavelet transform and enhancing resilient backpropogation neural network. (Master's theses Theses and Dissertations Master). Middle East University, Jordan
https://search.emarefa.net/detail/BIM-699386
لغة النص
الإنجليزية
نوع البيانات
رسائل جامعية
رقم السجل
BIM-699386
قاعدة معامل التأثير والاستشهادات المرجعية العربي "ارسيف Arcif"
أضخم قاعدة بيانات عربية للاستشهادات المرجعية للمجلات العلمية المحكمة الصادرة في العالم العربي
تقوم هذه الخدمة بالتحقق من التشابه أو الانتحال في الأبحاث والمقالات العلمية والأطروحات الجامعية والكتب والأبحاث باللغة العربية، وتحديد درجة التشابه أو أصالة الأعمال البحثية وحماية ملكيتها الفكرية. تعرف اكثر