Digital signature generation for image copyright using neural network global data association

Other Title(s)

استحداث توقيع الكتروني لحماية الصور الالكترونية اعتمادا على الخلايا العصبية في عملية ربط البيانات

Dissertant

al-Barham, Iqab Muhammad Ahmad

Thesis advisor

al-Rababiah, Mamun S.
Rashid, Walid A. Jabbar M. Ali

Comitee Members

al-Nihoud, Jihad Quball Awdah
Ababinah, Ismail M.
Ubayd, Nadim Ali Miri

University

Al albayt University

Faculty

Prince Hussein Bin Abdullah Faculty for Information Technology

Department

Department of Computer Science

University Country

Jordan

Degree

Master

Degree Date

2011

English Abstract

This work aims to achieve the security for digital images when some persons claim they own or use these images without their owner's permission.

This work contradicts several techniques which belong to watermarking.

The work tries to protect the digital images without influencing on the original image.

The design of this system contains two processes : Signature association and signature extraction.

This work explains watermarking is changed to serve another aim.

So, system design tries to create a new technique or develop an exist one.

This work depends on traditional posting way which it done by putting the necessary papers in envelop, then it closed by putting red melting wax by a stamp, which it has a signature or a unique mark to take a shape of the stamp.

Therefore, it's left to be cool.

This process is imitated by using Neural Network tools.

By several Programs that have been written in MatLab by investigating Neural Network tool which is used in training processes between input and output to produce a structure form.

For this point, this structural form is investigated as a key which taken to prove who has the right to own copyright.

In addition, another key is added to support the first key that users can define input for broker process after minimizing input size to cope with output size which is small normally.

During the practice of this work, many justifications are adopted to prove who can own copyright instead of one evidence as in watermarking.

Many helping factors are added to support the security.

For example, we move criminal to criminal investigations depending on the personal information with the image and other information about time, history and type of machine which the image is taken by.

Many procedures are taken for system design such as applying the system.

After that it is practiced by changing the number of neurons during training process between input and output.

Hence the system is examined to notice if the system can sense any change in the digital picture size.

This study proves that this system achieves the aims.

Main Subjects

Information Technology and Computer Science

Topics

• Encryption
• Digital electronics
• Neural networks(Computer science)
• Data

No. of Pages

53

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-321600