JISA (Jurnal Informatika dan Sains) e-ISSN: 2614-8404

Vol. 05, No. 02, December 2022 p-ISSN: 2776-3234

Analysis Manipulation Copy-Move on Image Digital

using SIFT Method and Histogram
Color RGB
Muhamad Masjun Efendi1*), Salman2, Moh. Subli3
1
Program Studi Sistem Informasi, Fakultas Teknologi Informasi dan Komunikasi, Universitas Teknologi Mataram
2
Program Studi Teknologi Informasi, Fakultas Teknologi Informasi dan Komunikasi, Universitas Teknologi Mataram
3
Program Studi Teknik Komputer, Fakultas Vokasi, Universitas Teknologi Mataram
Email: [email protected], [email protected], [email protected]

Abstract − The application of the SIFT (Scale Invariant feature transform) algorithm and the RGB color histogram in Matlab can detect
the suitability of objects in digital images and perform tests accurately. In this study, we discuss the implementation to obtain object
compatibility on digital images that have been manipulated using the SIFT Algorithm method on the Matlab source, namely by
comparing the original image with the manipulated image. The suitability of objects in digital images is obtained from the large number
of keypoints obtained, other additional parameters, namely comparing the number of pixels in the analyzed image, as well as changes
in the histogram in RGB color in each analyzed image. The purpose of this research is how to apply the SIFT (Scale Invariant feature
transform) Algorithm and RGB color histogram to detect the suitability of objects in digital images and perform tests accurately. This
study discusses the implementation to obtain object compatibility in digital images that have been manipulated using the SIFT
Algorithm method on Matlab sources, namely by comparing the original image with the manipulated image. The application of the
SIFT Algorithm (Scale Invariant Feature Transform) and RGB color histogram in determining the similarity of the keypoint location
and the number of pixels in the image, to obtain object compatibility in digital images in matlab was successfully implemented and
based on the test results obtained accuracy in identifying images in digital images.

Keywords – Image Processingl, Copy-Move, SIFT, Histogram RGB

processing software, it has become easy to create image
I. INTRODUCTION falsifications from one or more images without leaving
Image processing on digital images can be easily clear clues [7]. Digital crime is growing at a very fast rate.
created, edited and manipulated without leaving visual This crime has caused many problems, including legal and
instructions by the user, such as gimp and adobe photoshop ethical problems [8].
applications, for example, which makes it easy for the Image forgery in digital images is mostly done through
original image to be changed / manipulated. This ability can a passive approach. One of the popular passive approaches
of course also be misused to damage the credibility of the is to manipulate by means of the copy-move technique [9].
authenticity of the image in various aspects, so that it can Image falsification in digital images by means of an image
be carried out as a crime, image changes in digital images being copied and then pasted into other parts of the image.
can convey information that is different from the image in Image copy-move forgery is done to hide certain details or
the original digital image [1]. Criminals try to manipulate to duplicate objects in an image. Because the forgery is
the image for their own benefit. The formation of an image done in one image, the damaged area is almost the same,
in a digital image is obtained from several combinations of the nature of the original image will be difficult to identify
pixels [2]. To obtain a modified image, several stages are by humans [10].
needed in carrying out a digital image forensics process. In With the field of digital image forensics, it will help law
it there are several changes from the original at each pixel enforcement, intelligence, private investigations, and the
value [3]. media [11]. The increasingly advanced image technology
Digital technology, especially image, has become the at this time raises new issues and challenges in determining
main technology for creating, processing, transmitting and the authenticity of images in digital images. Digital image
storing information in the form of knowledge and forensics is one of the scientific methods in the field of
intellectual assets. Multidimensional knowledge and research that aims to obtain evidentiary facts in determining
intellectual assets are produced and represented in various the authenticity of images in digital images [12]. This
forms such as audio, video, text, images, if grouped, we can method Algorithm SIFT works by looking for a number of
call it a multimedia form [4]. Finally, all forms are stored the same keypoint points that are suspected of having
as digital form and byte form i.e., digital content. Image on similar objects in the digital image, as well as calculating
Digital images are widely used in our society [5]. From the number of pixels in the digital image.
newspapers to magazines, scientific journals, doctors in the This method can detect changes in scale, rotation and
medical field, the fashion industry, courtrooms and so on reflection, as well as changes in color enhancement
are very dependent on digital images [6]. Information on a digital image. [13].
integrity is fundamental in many fields. Digital technology SIFT (Scale Invariant Feature Transform) algorithm is
is currently starting to erode trust. Although cases of an algorithm in computer vision to detect and describe local
photo\image tampering are not new, over the last few years, features in the image. This algorithm is patented in Canada
tampered images appear with frequency and sophistication, by the University of British Columbia and published by
the development of increasingly sophisticated digital image David Lowe in 1999. This algorithm can perform object

JISA (Jurnal Informatika dan Sains) (e-ISSN: 2614-8404) is published by Program Studi Teknik Informatika, Universitas Trilogi
under Creative Commons Attribution-ShareAlike 4.0 International License.
120
JISA (Jurnal Informatika dan Sains) e-ISSN: 2614-8404
Vol. 05, No. 02, December 2022 p-ISSN: 2776-3234

recognition, robot mapping and navigation, image means that it has 255 color gradations, meaning that each
stitching, 3D modeling, gesture recognition, video tracking, pixel has as many color combinations. True color image
identify wildlife [14]. In another study, the SIFT Algorithm storage in memory is different from grayscale images. Each
(Scale Invariant Feature Transform) was used to match pixel of a grayscale image has 256 color gradations
images based on the main keypoint features (scale invariant represented by 1 byte. Meanwhile, 1 true color image pixel
and rotation) [15]. The SIFT algorithm is one of the most is represented by 3 bytes, each byte representing red, green,
widely used feature extraction methods. The Shift and blue.
algorithm is used to find key points in the image, in this
method it includes a shift description and a SIFT descriptor C. Color image (24 bit)
[16]. With so many crimes against image manipulation, it Each pixel of a 24-bit color image is represented by 24
is hoped that the method that researchers use can analyze bits for a total of 16,777,216 color variations. This variation
images in digital images so that they can detect images that is more than enough to visualize all the colors that human
have been changed from the original digital image [17]. vision can perceive. Human vision is believed to only be
Research on the multiple methods used in digital able to distinguish up to 10 million colors. Each pixel
images has the following objectives: information point (RGB) is stored into 1 byte of data. The
1. Applying the SIFT (Scale Invariant Feature first 8 bits store the blue value, followed by the green value
Transform) Algorithm and RGB color histogram using in the second 8 bits and the last 8 bits are red.
the Matlab application to be able to detect object
matches in digital images. D. File Format Image
2. Perform testing for better accuracy in analyzing An image file format must be able to combine image
images on digital images that have been changed from quality, file size and compatibility with various
the original. applications. There are several types of standard image file
formats used today. These formats are used to store images
in a file. Each format has its own characteristics. These are
II. RESEARCH METHODOLOGY examples of common formats, namely:Bitmap (.bmp),
tagged image format (.tif, .tiff), PortablNetwork Graphics
A. Image Digital (.png), JPEG (.jpg), etc.
Image is a representation (picture), likeness, or
imitation of an object. The image is divided into 2, namely, E. Algorithm SIFT (Scale Invariant feature transform)
there are images that are analog and there are images that Scale-invariant feature transform (SIFT) is an algorithm
are digital. Analog images are continuous images such as in computer vision to detect and describe local features in
images on television monitors, X-ray photos, CT scan images. Applications of these algorithms include object
results, etc. Meanwhile, digital images are images that a recognition, robot mapping and navigation, 3D modeling,
computer can process. gesture recognition, video tracking, wildlife identification
A digital image can be represented by a matrix and similar image transfer.
consisting of M columns and N rows, where the
intersection between the columns and rows is called a pixel III. RESULTS AND DISCUSSION
(pixel = picture element), which is the smallest element of To do this test, the author uses the Matlab application,
an image. Pixels have two parameters, namely coordinates which has prepared the source code to detect the match of
and intensity or color. The value contained in the (x,y) objects in digital images using the SIFT Algorithm. The
coordinate is f(x,y), which is the intensity or color of the following is a sample of the original image data and the
pixel at that point. Therefore, a digital image can be written manipulated image. The files have been processed using
in the following matrix form Photohop CC 2020, which are saved in JPG/JPEG format,
the images include: ds_ori, ds_edit, cover, dika, agus_oci,
three, girl1, girl2, cover, dian_ori, dian_edit, background,
rs_ori, rs_edit, jm_ori, jm_edit, mnrp, ocy, oci_paris, oshi,
sample, sample, rio, dn_edit, ds1, ds2, ar, etc. The SIFT
Algorithm method used is a function that can read two
Based on this description, mathematically a digital images, find their SIFT features, and display a line
image can be written as a function of intensity f (x,y), where connecting the matching keypoints. The equation obtained
x (row) and y (column) are position coordinates and f (x,y) in the first image only if the distance is less than the ratio
is the function value at each point (x, y) which represents times the distance to the nearest equation in the second
the intensity of the image or the gray level or color of the image, then returns the number of matches displayed. The
pixels at that point. In the digitization process (sampling way the algorithm works in this application is, after
and quantity) the number of rows M and columns N is inputting two images, the initial stage is to find the keypoint
obtained so that the image forms matrix M x N and the on each image, the constant value is created at a ratio
number of gray levels of pixels is G. distance of 0.6, this is done with the hope, the way the
analysis of matlab works becomes lighter, the descriptor in
B. Image Resolution the first image, matched with the descriptor in the second
Image resolution is the level of detail of an image. The image, the matrices in each image are recalculated,
higher the resolution, the higher the detail level of the calculate the vector for each corner point, take the inverse
image. Each base color uses 8 bit = 1 byte storage, which cosine value and display the result, in addition to getting

JISA (Jurnal Informatika dan Sains) (e-ISSN: 2614-8404) is published by Program Studi Teknik Informatika, Universitas Trilogi
under Creative Commons Attribution-ShareAlike 4.0 International License.
121
JISA (Jurnal Informatika dan Sains) e-ISSN: 2614-8404
Vol. 05, No. 02, December 2022 p-ISSN: 2776-3234

the keypoint, another additional parameter is getting the graph (Red, Green, Blue) were also added. Where the level
pixel value to strengthen analysis of the studied image, the of difference in the image can be obtained from changes in
results of the process are presented in Table 1 below. the number of pixels and RGB colors displayed based on
the histogram graph.
Table 1. Results of Matching Dian Sastro's Pair of
Objects with the SIFT Algorithm and RGB Color IV. CONCLUSION
Histogram The application of the SIFT (Scale Invariant Feature
transform) algorithm and RGB color histogram in
determining the similarity of keypoint locations and the
number of pixels in the image, to obtain object
compatibility in digital images in Matlab has been
successfully implemented. Based on the test results
obtained accuracy in identifying images in digital images
using the SIFT Algorithm (Scale Invariant Feature
Transform), that the research has been going well and
smoothly.

REFERENCES

[1] Koeshardianto, M. (2014). Pencocokan Obyek Wajah

Menggunakan Metode Sift ( Scale Invariant Feature
Transform ). Nero, 1(1), 53–59.
[2] Setiyawan, A., & Basuki, R. S. (2014). Pencocokan
Citra Berbasis Scale Invariant Feature Transform
(SIFT) menggunakan Arc Cosinus. Jurnal Teknik
Informatika, 1–4.
[3] Amtullah, S., & Koul, D. A. (2014). Passive Image
Forensic Method to detect Copy Move Forgery in
Digital Images. IOSR Journal of Computer
Engineering, 16(2), 96–104.
https://doi.org/10.9790/0661-1621296104
[4] Anh, N. T., Hang, H. T. T., & Chen, G. (2019). One
approach in the time domain in detecting copy-move
of speech recordings with the similar magnitude.
International Journal of Engineering and Applied
In comparison, the three images compared produce Sciences (IJEAS), 6(4), 9–11.
histogram values with different numbers of pixels, meaning https://doi.org/10.31873/ijeas/6.4.2019.05
that the histogram values can be used as a reference as an [5] Mahalakshmi, D., & Science, C. (2017). Copy - Move
additional parameter to match objects, then when viewed Image Forgery Detection System Using Hybrid
from the number of keypoints, there are matches on objects Method. International Journal of Engineering
marked with lines. Science Invention Research & Development, III(XI),
He use of the SIFT algorithm was chosen as the feature 692–698.
extraction method because this method is invariant to [6] Inoue, K., Hara, K., & Urahama, K. (2017). RGB color
changes in scale, rotation, translation, and illumination. cube-based histogram specification for hue-
SIFT is used to obtain the characteristics of the obtained preserving color image enhancement. Journal of
keypoint pattern. The hope is that by applying this method, Imaging, 3(3).
from the keypoints obtained on each of these images, we https://doi.org/10.3390/jimaging3030024
get an accurate object match. The first step in determining [7] Korman, S., Reichman, D., Tsur, G., & Avidan, S.
the keypoint that is invariant to changes in the scale of the (2013). FasT-match: Fast affine template matching.
image is to find the extreme values in the scale space. To Proceedings of the IEEE Computer Society
get the keypoint location in a scale space efficiently, the Conference on Computer Vision and Pattern
Difference-of-Gaussian (DoG) function is used, the value Recognition, 2331–2338.
for the DoG function is obtained from the difference https://doi.org/10.1109/CVPR.2013.302
between Gaussian images with different scales. [8] Salahat, E., & Qasaimeh, M. (2017). Recent advances
Given orientation so that it will not be affected by the in features extraction and description algorithms: A
rotation of the image. In this study, the features in the form comprehensive survey. Proceedings of the IEEE
of keypoint locations and also the feature vectors of these International Conference on Industrial Technology,
keypoints have been obtained. Then the classification has 1059–1063.
been carried out, so it can be concluded that this system is https://doi.org/10.1109/ICIT.2017.7915508
able to detect the match of objects in digital images [9] Dakhode, G., & Chourey, A. P. P. K. (2017). Forensic
accurately. To strengthen the results of the analysis in the Technique for Detection of Image Forgery.
above test, additional tests using an RGB color histogram International Journal of Advanced Engineering

JISA (Jurnal Informatika dan Sains) (e-ISSN: 2614-8404) is published by Program Studi Teknik Informatika, Universitas Trilogi
under Creative Commons Attribution-ShareAlike 4.0 International License.
122
JISA (Jurnal Informatika dan Sains) e-ISSN: 2614-8404
Vol. 05, No. 02, December 2022 p-ISSN: 2776-3234

Research and Science, 4(1), 189–193.

https://doi.org/10.22161/ijaers.4.1.31
[10] Kashyap, A., Agarwal, M., & Gupta, H. (2018).
Detection of copy-move image forgery using SVD
and cuckoo search algorithm. International Journal
of Engineering and Technology(UAE), 7(2), 79–87.
https://doi.org/10.14419/ijet.v7i2.13.11604
[11] Kresnha, P. E., Susilowati, E., & Adharani, Y. (2016).
Pendeteksian Manipulasi Citra Berbasis Copy-move
Forgery Menggunakan Euclidean DIstance dengan
Single Value Decomposition. Seminar Nasional
Teknologi Informasi Dan Multimedia 2016, 6–7.
[12] Wang, X. (2013). The research of digital recognition
technology based on bp neural network.
BioTechnology: An Indian Journal, 8(2), 180–185.
[13] Ahmed, I. T., Hammad, B. T., & Jamil, N. (2021). A
comparative analysis of image copy-move forgery
detection algorithms based on hand and machine-
crafted features. Indonesian Journal of Electrical
Engineering and Computer Science, 22(2), 1177–
1190.
https://doi.org/10.11591/IJEECS.V22.I2.PP1177-
1190
[14] Li, B., Ng, T. T., Li, X., Tan, S., & Huang, J. (2015).
Revealing the trace of high-quality JPEG
compression through quantization noise analysis.
IEEE Transactions on Information Forensics and
Security, 10(3), 558–573.
https://doi.org/10.1109/TIFS.2015.2389148
[15] Xiang, Z., Bestagini, P., Tubaro, S., & Delp, E. J.
(2022). Forensic Analysis and Localization of
Multiply Compressed MP3 Audio Using
Transformers. 2929–2933.
https://doi.org/10.1109/icassp43922.2022.9747639
[16] Julliand, T., Nozick, V., Talbot, H., Julliand, T.,
Nozick, V., Talbot, H., Image, A., Detection, S.,
Julliand, T., Nozick, V., & Talbot, H. (2017).
Automated Image Splicing Detection from Noise
Estimation in Raw Images To cite this version : HAL
Id : hal-01510075 Automated Image Splicing
Detection from Noise Estimation in Raw Images.
[17] Qiang, B., Chen, R., Zhou, M., Pang, Y., Zhai, Y., &
Yang, M. (2020). Convolutional neural networks-
based object detection algorithm by jointing semantic
segmentation for images. Sensors (Switzerland),
20(18), 1–14. https://doi.org/10.3390/s20185080

JISA (Jurnal Informatika dan Sains) (e-ISSN: 2614-8404) is published by Program Studi Teknik Informatika, Universitas Trilogi
under Creative Commons Attribution-ShareAlike 4.0 International License.
123