| Paper Details: | Downloads: 1130 |
| Serial Number: | P1151502359
|
| Title: | Ontology base to detect Tampering in Online Digital Images
|
| Authors: | Eman K. Elsayed and Asmaa M. Eissa
|
| Abstract: | The power of the image editor and the watermark cracking make a big challenge in determining whether the digital image is original or doctored, determining the forgery's parts and returning to original image
We need to be aware that seeing does not always enough.
So recently, there are many attempts to avoid and detect image forgery. A new proposal method to detect online digital images’ montage was presented in this paper. The proposal based on semantic analysis of digital image.
This proposal starts by manipulating the original image for forgery detection process so we classify our proposal as active forgery detection technique. Although, the proposal has some advantages of passive forgery detection techniques as disappearing of original image.
Our methodology could be called Semantic blind Image Forgery detection technique. That is by converting image to ontology based, where Ontology is widely used in different disciplines as a technique for representing and reasoning about domain knowledge.
Using ontology comparison for detecting image forgery guarantees the efficiency and accuracy because ontology comparison operations based on set theory. Also our proposal is flexible to cover colored, any format and enlarge digital image.
Using OWL ontology engineering to detect the montage in online digital image is not only accurate for comparison based on set theory, but also important for splicing different image online databases.
Also our proposal used steganography technique to hide the universal ontology link inside the image.
|
| Keywords: | Digital images’ montage, Semantic Web, Qualitative image description QID, Steganography, blind forgery detection.
|
| Journal/Conference: | International Journal of Graphics, Vision and Image Processing
|
| Volume: | 15
|
| Issue: | 1
|
| Submission Date: | 1/7/2015 12:00:00 AM
|
| Review Date: | 2/15/2015 12:00:00 AM
|
| Publishing Date: | 3/3/2015 12:00:00 AM
|
| Article Downloads: | 1130
|
| Download: |
|