Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 41064 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Jamzad, Mansour
- Abstract:
- Nowadays, digital images are easy to manipulate and edit due to availability of powerful image processing and editing software. It is possible to add or remove important features to the image without leaving any obvious traces of tampering. Therefore, proving the authenticity and integrity of digital media becomes increasingly important. In this study, we focus on detection of a special type of digital forgery, the copy-move attack, in which a part of the image is copied and pasted somewhere else in the image with the intent to cover an important image features or to add some fake feature. In this way we propose some novel methods that work in spatial domain, Discrete Cosine domain and Wavelet domain. At first, the algorithm is applied on image pixels directly then it is applied on blocks of pixels in order to improve the performance. The forged regions can be detected using by a shift vector based on similarity between pixels or blocks. This method can successfully detect the forged part. In the second algorithm we investigate the problem of detecting the copy-move forgery and describe an efficient and reliable detection method. The idea of this study is coefficient histogram analysis to find the copy region. The Last method is based on special kinds of wavelet transforms which do not change the size of coefficient against the common wavelet transform. The forged regions can be detected using by a shift vector in transform domain based on similarity between coefficients blocks. This method can successfully detect the forged part
- Keywords:
- Discrete Cosine Transform ; Wavelet Transform ; Tamper Detection ; Image Forgery ; Image Forensics
Digital Object List
-
محتواي پايان نامه
- view
Bookmark