Nugroho, Yusuf (2016) Forensik Citra Untuk Analisis Copy-Move Menggunakan Exhaustive Search Dan Autocorrelation. Undergraduate thesis, Institut Teknologi Sepuluh Nopember Surabaya.
Preview |
Text
5112100147-Undergraduate_Thesis.pdf - Published Version Download (3MB) | Preview |
Abstract
Copy-move adalah suatu bentuk pemalsuan citra, dimana
pengguna menyalin suatu bagian citra lalu menempelkannya di
bagian lain pada citra yang sama. Teknik ini biasanya digunakan
untuk menutupi objek dari suatu citra dengan cara menempelkan
objek yang serupa di sekitarnya. Oleh karena itu diperlukan
metode untuk mendeteksi serangan copy move, terlebih citra sering
digunakan sebagai bukti dalam persidangan, dalam bidang
kedokteran, dan bagian dari suatu berita.
Data citra seringkali terganggu dengan adanya noise,
sehingga diperlukan metode filtering yang digunakan untuk
meminimalisasi noise pada citra. Metode filtering dapat membantu
proses pendeteksian serangan copy move pada citra. Oleh karena
itu Tugas Akhir ini mengimplementasikan metode Gaussian dan
Laplacian Filter sebagai penghilang noise pada citra yang akan
dideteksi menggunakan metode exhaustive search dan
autocorrelation.
Pada tugas akhir ini hasil yang didapat untuk
menghilangkan noise menggunakan metode Gaussian Filter
dianggap lebih efektif dibandingkan Laplacian Filter. Penggunaan
kernel pada metode autocorrelation dianggap efektf dalam
meningkatkan akurasi hasil deteksi serangan copy move pada
citra. Sedangkan pada exhaustive search penggunaan kernel tidak
diperlukan
===============================================================================================part of image is copied and pasted in another part of the same
image. This technique is usually used to cover up an objek in the
image by attaching similar objek around it. Therefore developing
method to verify and detect manipulated image became very
important, especially because the image can be used as evidence
in court, as a picture of headline news, and as a part of medical
record.
The image data is often disturbed by a noise, therefore we
need a filtering method that is used to minimize the noise. This
filtering methods are useful to improve the copy move detection
method. This study implements the method of Gaussian and
Laplacian Filter to minimize the noise of image that will be
detected using exhaustive and autocorrelation method.
In this undergraduate thesis, the results obtained using
Gaussian Filter method to minimize noise was the effective way
compared to Laplacian Filter. The use of kernel on autocorrelation
method is considered effective for improving the accuracy of copy
move image detection. Whereas on exhaustive Method, the use of
kernel is not required
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Additional Information: | RSIf 006.312 Nug f |
| Uncontrolled Keywords: | Copy Move, Gaussian Filter, Laplacian Filter, Metode exhaustive search, autocorrelation, kernel morphology. |
| Subjects: | Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) |
| Divisions: | Faculty of Information Technology > Informatics Engineering > 55201-(S1) Undergraduate Thesis |
| Depositing User: | EKO BUDI RAHARJO |
| Date Deposited: | 21 Feb 2020 02:43 |
| Last Modified: | 21 Feb 2020 02:43 |
| URI: | http://repository.its.ac.id/id/eprint/75091 |
Actions (login required)
 |
View Item |