Image splicing detection based on noise level approach

Authors

  • Mohammed Kassem Alshwely Department of Computer Science, College of Science, Mustansiriyah University.
  • Saad N. AlSaad Department of Computer Science, College of Science, Mustansiriyah University.

DOI:

https://doi.org/10.23851/mjs.v31i4.899

Abstract

The rapid development in technology and the spread of editing image software has led to spread forgery in digital media. It is now not easy by just looking at an image to know whether the image is original or has been tampered. This article describes a new image splicing detection method based on noise level as a major feature to detect the tempered region. Principal Component Analysis (PCA) is exploited to estimate the noise of image and the K-means clustering for authentic and forged region classification. The proposed method adopts Columbia Uncompressed Image Splicing Dataset for evaluation and effectiveness. The experimental results for 360 images demonstrate that the method achieved an 83.33% for detecting tampered region this percentage represent a promising result competed with Stat-of-art splicing detection methods.

Downloads

Download data is not yet available.

References

Wu, Y., Abd-Almageed, W., and Natarajan, P.: 'Deep matching and validation network: An end-to-end solution to constrained image splicing localization and detection', in Editor (Ed.)^(Eds.): 'Book Deep matching and validation network: An end-to-end solution to constrained image splicing localization and detection' (ACM, 2017, edn.), pp. 1480-1502

CrossRef

Cozzolino, D., and Verdoliva, L.: 'Noiseprint: a CNN-based camera model fingerprint', IEEE Transactions on Information Forensics and Security, 2019.

CrossRef

Zhou, P., Han, X., Morariu, V.I., and Davis, L.S.: 'Learning rich features for image manipulation detection', in Editor (Ed.)^(Eds.): 'Book Learning rich features for image manipulation detection' (2018, edn.), pp. 1053-1061K. Elissa, "Title of paper if known," unpublished.

CrossRef

Farid, H.: 'Image forgery detection', IEEE Signal processing magazine, 2009, 26, (2), pp. 16-25.

CrossRef

Sekhar, C., and Sankar, T.: 'Review on Image Splicing Forgery Detection', International Journal of Computer Science and Information Security, 2016, 14, (11), pp. 471.

https://gizmodo.com/that-viral-photo-of-putin-is-totally-fake-1796767457 [Accessed 21/07/2020].

Meena, K.B., and Tyagi, V.: 'Image Forgery Detection: Survey and Future Directions': 'Data, Engineering and Applications' (Springer, 2019), pp. 163-194.

CrossRef

Mushtaq, Saba, and Ajaz Hussain Mir. "Digital image forgeries and passive image authentication techniques: A survey." International Journal of Advanced Science and Technology 73 (2014): 15-32.

CrossRef

Liu, Y., Zhu, X., Zhao, X., and Cao, Y.: 'Adversarial Learning for Constrained Image Splicing Detection and Localization Based on Atrous Convolution', IEEE Transactions on Information Forensics and Security, 2019, 14, (10), pp. 2551-2566.

CrossRef

Zhang, Q., Lu, W., and Weng, J.: 'Joint image splicing detection in DCT and Contourlet transform domain', Journal of Visual Communication and Image Representation, 2016, 40, pp. 449-458.

CrossRef

Kumar, A., Prakash, C.S., Maheshkar, S., and Maheshkar, V.: 'Markov Feature Extraction Using Enhanced Threshold Method for Image Splicing Forgery Detection': 'Smart Innovations in Communication and Computational Sciences' (Springer, 2019), pp. 17-27.

CrossRef

Cozzolino, D., and Verdoliva, L.: 'Single-image splicing localization through autoencoder-based anomaly detection', in Editor (Ed.)^(Eds.): 'Book Single-image splicing localization through autoencoder-based anomaly detection' (IEEE, 2016, edn.), pp. 1-6.

CrossRef | PubMed

Kaur, M., and Gupta, S.: 'A passive blind approach for image splicing detection based on DWT and LBP histograms', in Editor (Ed.)^(Eds.): 'Book A passive blind approach for image splicing detection based on DWT and LBP histograms' (Springer, 2016, edn.), pp. 318-327.

CrossRef

Pomari, T., Ruppert, G., Rezende, E., Rocha, A., and Carvalho, T.: 'Image splicing detection through illumination inconsistencies and deep learning', in Editor (Ed.)^(Eds.): 'Book Image splicing detection through illumination inconsistencies and deep learning' (IEEE, 2018, edn.), pp. 3788-3792.

CrossRef

Moghaddasi, Z., Jalab, H.A., and Noor, R.M.: 'Image splicing forgery detection based on low-dimensional singular value decomposition of discrete cosine transform coefficients', Neural Computing and Applications, 2018, pp. 1-11.

CrossRef

Y?ld?r?m, E.O., and Uluta?, G.: 'Augmented features to detect image splicing on SWT domain', Expert Systems with Applications, 2019, 131, pp. 81-93.

CrossRef

Pyatykh, S., Hesser, J., and Zheng, L.: 'Image noise level estimation by principal component analysis', IEEE transactions on image processing, 2012, 22, (2), pp. 687-699.

CrossRef | PubMed

Zeng, H., Zhan, Y., Kang, X., and Lin, X.: 'Image splicing localization using PCA-based noise level estimation', Multimedia Tools and Applications, 2017, 76, (4), pp. 4783-4799.

CrossRef

Hsu, Y.-F., and Chang, S.-F.: 'Detecting image splicing using geometry invariants and camera characteristics consistency', in Editor (Ed.)^(Eds.): 'Book Detecting image splicing using geometry invariants and camera characteristics consistency' (IEEE, 2006, edn.), pp. 549-552.

CrossRef | PubMed

Downloads

Key Dates

Published

20-12-2020

Issue

Section

Original Article

How to Cite

[1]
M. K. Alshwely and S. N. AlSaad, “Image splicing detection based on noise level approach”, Al-Mustansiriyah J. Sci., vol. 31, no. 4, pp. 55–61, Dec. 2020, doi: 10.23851/mjs.v31i4.899.