Analisis Manipulasi Splicing pada Citra Digital menggunakan Metode Discrete Cosine Transform (DCT) dan Scale Invariant Feature Transform (SIFT)

Muhamad Masjun Efendi; Salman Salman

doi:10.24114/cess.v9i1.53156

Authors

Muhamad Masjun Efendi Universitas Teknologi Mataram
Salman Salman Universitas Teknologi Mataram

DOI:

https://doi.org/10.24114/cess.v9i1.53156

Keywords:

Manipulation, Image, Splicing, DCT, SIFT

Abstract

Pemalsuan dalam citra digital seringkali terjadi di era teknologi saat ini. Bantuan software pengolahan citra memudahkan dan mempercepat proses manipulasi, mendorong orang untuk melakukan perubahan sebelum citra dipublikasikan di internet atau media sosial. Meski kegiatan ini umum dilakukan, seringkali merugikan orang lain dan merupakan bentuk penipuan publik terhadap keaslian citra. Salah satu metode manipulasi yang kerap kali digunakan adalah splicing, splicing adalah menambah objek dalam citra, contohnya meletakkan suatu objek pada citra target yang seolah-olah objek tersebut berada disana. Penelitian ini bertujuan untuk mendeteksi manipulasi jenis splicing dengan menggunakan metode Discrete Cosine Transform (DCT) dan Scale Invariant Feature Transform (SIFT). Metode DCT mentransformasikan blok piksel citra menjadi koefisien, sedangkan SIFT digunakan untuk menemukan frekuensi pada citra grayscale dengan mendeteksi keypoint yang sama. Metode ini mampu mendeteksi objek citra yang dimanipulasi dengan baik dan akurat. Dari hasil pengujian yang dilakukan, nilai akurasi deteksi image splicing pada citra dari internet dan koleksi citra hasil koleksi pribadi mencapai 100%. Harapannya, hasil penelitian ini dapat bermanfaat bagi masyarakat dalam membedakan citra yang asli dengan yang sudah dimanipulasi melalui teknik splicing.

References

J. Charpe and A. Bhattacharya, œRevealing image forgery through image manipulation detection, Glob. Conf. Commun. Technol. GCCT 2015, no. Gcct, pp. 723“727, 2015, doi: 10.1109/GCCT.2015.7342759.

I. T. Ahmed, B. T. Hammad, and N. Jamil, œA comparative analysis of image copy-move forgery detection algorithms based on hand and machine-crafted features, Indones.J. Electr. Eng. Comput. Sci., vol. 22, no. 2, pp. 1177“1190, 2021, doi: 10.11591/IJEECS.V22.I2.PP1177-1190.

M. Hafil, œFenomena Ujaran Kebencian Di Medsos. republika.co.id, Jakarta, p. 2022.

S. S. Narayanan and G. Gopakumar, œRecursive Block Based Keypoint Matching for Copy Move Image Forgery Detection, 2020 11th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2020, 2020, doi: 10.1109/ICCCNT49239.2020.9225658.

M. T. Jijina, L. Koshy, and G. S. Warrier, œDetection of Recoloring and Copy-Move Forgery in Digital Images, Proc. - 2020 5th Int. Conf. Res. Comput. Intell. Commun. Networks, ICRCICN 2020, pp. 49“53, 2020, doi: 10.1109/ICRCICN50933.2020.9296173.

G. Bobashev, N. G. Baldasaro, K. C. Mills, and J. L. Davis, œAn Efficiency-Decay Model for Lumen Maintenance, IEEE Trans. Device Mater. Reliab., vol. 16, no. 3, pp. 277“ 281, 2016, doi: 10.1109/TDMR.2016.2584926.

M. S. Rana, M. M. Hasan, and S. K. S. Shuva, œDigital Watermarking Image Using Discrete Wavelet Transform and Discrete Cosine Transform with Noise Identification, 2022 2nd Int. Conf. Intell. Technol. CONIT 2022, no. August, pp. 1“5, 2022, doi: 10.1109/CONIT55038.2022.9847745.

T. Das, R. Hasan, M. R. Azam, and J. Uddin, œA Robust Method for Detecting Copy- Move Image Forgery Using Stationary Wavelet Transform and Scale Invariant Feature Transform, Int. Conf. Comput. Commun. Chem. Mater. Electron. Eng. IC4ME2 2018, pp. 1“4, 2018, doi: 10.1109/IC4ME2.2018.8465668.

P. Dingbang, C. Hao, S. Xiaochong, and L. Jianxun, œMotion blurred star image centroid optimized extraction based on prior Gaussian distribution, Proc. 29th Chinese Control Decis. Conf. CCDC 2017, pp. 3149“3154, 2017, doi: 10.1109/CCDC.2017.7979049.

Y. Fan and Helbert, œDetection of Image Splicing using Illuminant Color Estimation, 2019.

T. Julliand et al., œAutomated 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, 2017.

J. Zeng, S. Shi, Y. Li, and Q. Lu, œPractical inspection workflow for digital image forensic authentication, pp. 172“172, 2016, doi: 10.1109/isdfs.2016.7473540.

V. Papyan and M. Elad, œMulti-scale patch-based image restoration, IEEE Trans. Image Process., vol. 25, no. 1, pp. 249“261, 2016, doi: 10.1109/TIP.2015.2499698.

C. A. Theran and M. A. Alvarez, œA Pixel Level Scaled Fusion Model to Provide High Spatial-Spectral Resolution for Satellite Images Using Lstm Networks 1. Laboratory for Applied Remote Sensing, Imaging and Photonics 2. Department of Computer science & Engineering 3. Department of Ele, 2019 10th Work. Hyperspectral Imaging Signal Process. Evol. Remote Sens., pp. 2“6.

Y. Zhang, œThe studies and implementation for conversion of image file format, Proc. 2014 Int. Symp. Inf. Technol. ISIT 2014, no. Iccse, pp. 423“426, 2015, doi: 10.1201/b18776-79.

J. Wu, X. Chang, T. Yang, and K. Feng, œBlind Forensic Method Based on Convolutional Neural Networks for Image Splicing Detection, 2019 IEEE 5th Int. Conf. Comput. Commun. ICCC 2019, pp. 2014“2018, 2019, doi: 10.1109/ICCC47050.2019.9064258.

M. A. E. Abdalla, A. A. Abdo, and A. O. Lawgali, œUtilizing Discrete Wavelet Transform and Discrete Cosine Transform for Iris Recognition, Proc. - STA 2020 2020 20th Int. Conf. Sci. Tech. Autom. Control Comput. Eng., pp. 283“296, 2020, doi: 10.1109/STA50679.2020.9329312.

P. Khatua and K. C. Ray, œA basis function for DCT based discrete orthogonal S- transform, Proc. - 2019 IEEE Int. Symp. Smart Electron. Syst. iSES 2019, pp. 7“11, 2019, doi: 10.1109/iSES47678.2019.00015.

B. Fan et al., œA performance evaluation of local features for image-based 3D reconstruction, IEEE Trans. Image Process., vol. 28, no. 10, pp. 4774“4789, 2019, doi: 10.1109/TIP.2019.2909640.