Skip to main content
SpringerLink
Log in

An improved detection of blind image forgery using hybrid deep belief network and adaptive fuzzy clustering

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Blind image forgery prediction in the field of image forgery is difficult. Hence, it is the major attention for the investigators recently. This work introduces an innovative methodology for blind image forgery detection. The steps are described as: initially, input images are pre-processed using hybrid homomorphic filtering to enhance the images. After pre-processing images, features such as Hybrid Speeded up Robust features and scale-invariant feature transform (hybrid SURF-SIFT) and hybrid wavelet features are extracted. According to the extracted features hybrid deep belief neural network (HDBN) framework performs the block matching to examine the forgery region in images. Here, modified atom search optimization is utilized for weights optimization in HDBN framework and improving the performance of matching process. The HDBN framework detects non matching regions, and finally, the forgery region is accurately localized with the presented Adaptive fuzzy clustering based improved sun flower optimization (AFCSO) approach. The implementation platform used in work is PYTHON. The presented technique is tested with three datasets: CG-1050, SMIFD, and Coverage. Moreover, the experimental results of the presented approach is examined with the existing techniques in regard to accuracy, precision, recall, F-measure, True positive rate, False positive rate, True negative rate, and False-negative rate. The performance measures of forgery detection with CG-1050 dataset is F-measure (98.98%), Accuracy (99%), recall (98%), precision (99.9%), True positive rate (99.5%), False positive rate (0.4%), True negative rate (99.7%), False negative rate (2%). The performance measures of forgery detection with SMIFD dataset is F-measure (99.15%), True positive rate (99.57%), Accuracy (98.67%), precision (99.57%), false-positive rate (1.56%), True negative rate (98.43%), and false-negative rate (1.25%). The performance measures of forgery detection with COVERAGE dataset is F-measure (98%), True positive rate (98%), False positive rate (2%), Accuracy (98.3%), precision (97.1%), True negative rate (98%), False negative rate (2%). This proved that the presented approach outperforms the compared existing approaches.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

Similar content being viewed by others

Data availability

Data sharing not applicable to this article as no datasets were generated or analysed during the current study.

References

  1. Abidin AB, Majid HB, Samah AB, Hashim HB (2019) Copy-move image forgery detection using deep learning methods: a review. In: 2019 6th international conference on research and innovation in information systems (ICRIIS) IEEE, 1-6

  2. Abrahim AR, Rahim MS, Sulong GB (2019) Splicing image forgery identification based on artificial neural network approach and texture features. Clust Comput 22(1):647–660

    Article  Google Scholar 

  3. Agarwal R, Verma OP (2019) An efficient copy move forgery detection using deep learning feature extraction and matching algorithm. Multimed Tools Appl:1–22

  4. Alkawaz MH, Sulong G, Saba T, Rehman A (2018) Detection of copy-move image forgery based on discrete cosine transform. Neural Comput & Applic 30(1):183–192

    Article  Google Scholar 

  5. Alzahir S, Hammad R (2020) Image forgery detection using image similarity. Multimed Tools Appl 79(39):28643–28659

    Article  Google Scholar 

  6. Bharti CN, Tandel P (2016) A survey of image forgery detection techniques. In: 2016 international conference on wireless communications, signal processing and networking (WiSPNET) IEEE, 877-881

  7. Bilal M, Habib HA, Mehmood Z, Saba T, Rashid M (2019) Single and multiple copy–move forgery detection and localization in digital images based on the sparsely encoded distinctive features and DBSCAN clustering. Arab J Sci Eng 1-8

  8. Bilal M, Habib HA, Mehmood Z, Saba T, Rashid M (2020) Single and multiple copy–move forgery detection and localization in digital images based on the sparsely encoded distinctive features and DBSCAN clustering. Arab J Sci Eng 45(4):2975–2992

    Article  Google Scholar 

  9. Castro M, Ballesteros DM, Renza D (2020) A dataset of 1050-tampered color and grayscale images (CG-1050). Data Brief 28:104864

    Article  Google Scholar 

  10. Christlein V, Riess C, Jordan J, Riess C, Angelopoulou E (2012) An evaluation of popular copy-move forgery detection approaches. IEEE Trans Inf Forensic Secur 7(6):1841–1854

    Article  Google Scholar 

  11. Devi MU, Babu UR (2019) Grey wolf assisted SIFT for improving copy move image forgery detection. Evol Intell 1-2

  12. Dhanya R, KalaiSelvi R (2020) Robust adaptable segmentation-based copy move forgery detection method. In: Advances in Communication Systems and Networks Springer, Singapore, 723–733

  13. Elaskily MA, Elnemr HA, Sedik A, Dessouky MM, El Banby GM, Elshakankiry OA, Fathi E (2020) A novel deep learning framework for copy-moveforgery detection in images. Multimed Tools Appl 79:19167–19192

    Article  Google Scholar 

  14. Elsharkawy ZF, Abdelwahab SA, Abd El-Samie FE, Dessouky M, Elaraby S (2019) New and efficient blind detection algorithm for digital image forgery using homomorphic image processing. Multimed Tools Appl 78(15):21585–21611

    Article  Google Scholar 

  15. Gull S, Loan NA, Parah SA, Sheikh JA, Bhat GM (2020) An efficient watermarking technique for tamper detection and localization of medical images. J Ambient Intell Humaniz Comput 11(5):1799–1808

    Article  Google Scholar 

  16. Hayat K, Qazi T (2017) Forgery detection in digital images via discrete wavelet and discrete cosine transforms. Comput Electr Eng 62:448–458

    Article  Google Scholar 

  17. Hegazi A, Taha A, Selim MM (2019) An improved copy-move forgery detection based on density-based clustering and guaranteed outlier removal. J King Saud Univ-Comput Inf Sci

  18. Hilal A, Hamzeh T, Chantaf S (2017) Copy-move forgery detection using principal component analysis and discrete cosine transform. In2017 sensors networks smart and emerging technologies (SENSET) IEEE, 1-4

  19. Jabeen S, Khan UG, Iqbal R, Mukherjee M, Lloret J (2021) A deep multimodal system for provenance filtering with universal forgery detection and localization. Multimed Tools Appl 80(11):17025–17044

    Article  Google Scholar 

  20. Jaiprakash SP, Desai MB, Prakash CS, Mistry VH, Radadiya KL (2020) Low dimensional DCT and DWT feature based model for detection of image splicing and copy-move forgery. Multimed Tools Appl 79(39):29977–30005

    Article  Google Scholar 

  21. Kaur N, Jindal N, Singh K (2020) A passive approach for the detection of splicing forgery in digital images. Multimed Tools Appl 79(43):32037–32063

    Article  Google Scholar 

  22. Lin C, Lu W, Huang X, Liu K, Sun W, Lin H, Tan Z (2019) Copy-move forgery detection using combined features and transitive matching. Multimed Tools Appl 78(21):30081–30096

    Article  Google Scholar 

  23. Liu B, Pun CM (2020) Exposing splicing forgery in realistic scenes using deep fusion network. Inf Sci 526:133–150

    Article  MathSciNet  Google Scholar 

  24. Marra F, Gragnaniello D, Cozzolino D, Verdoliva L (2018) Detection of Gan-generated fake images over social networks. In2018 IEEE conference on multimedia information processing and retrieval (MIPR) 384-389

  25. Nath S, Naskar R (2021) Automated image splicing detection using deep CNN-learned features and ANN-based classifier. Signal Image and Video Processing 1–8

  26. Rahman MM, Tajrin J, Hasnat A, Uzzaman N, Rahaman GA (2019) SMIFD: novel social media image forgery detection database. In2019 22nd international conference on computer and information technology (ICCIT), IEEE 1-6

  27. Rao Y, Ni J, Xie H (2021) Multi-semantic CRF-based attention model for image forgery detection and localization. Signal Process 183:108051

    Article  Google Scholar 

  28. Roy A, Dixit R, Naskar R, Chakraborty RS (2020) Digital image forensics. Springer, Singapore

    Book  Google Scholar 

  29. Roy A, Dixit R, Naskar R, Chakraborty RS (2020) Copy-move forgery detection exploiting statistical image features. In: Digital Image Forensics, Springer, Singapore, 57–64

  30. Roy A, Dixit R, Naskar R, Chakraborty RS (2020) Copy-move forgery detection with similar but genuine objects. In: Digital Image Forensics, Springer, Singapore, 65–77

  31. Soni B, Das PK, Thounaojam DM (2019) Geometric transformation invariant block based copy-move forgery detection using fast and efficient hybrid local features. J Inf Secur Appl 45:44–51

    Google Scholar 

  32. Thakur R, Rohilla R (2020) Recent advances in digital image manipulation detection techniques: a brief review. Forensic Sci Int 312:110311

    Article  Google Scholar 

  33. Yang F, Li J, Lu W, Weng J (2017) Copy-move forgery detection based on hybrid features. Eng Appl Artif Intell 59:73–83

    Article  Google Scholar 

  34. Yang B, Sun X, Guo H, Xia Z, Chen X (2018) A copy-move forgery detection method based on CMFD-SIFT. Multimed Tools Appl 77(1):837–855

    Article  Google Scholar 

  35. Zhu Y, Chen C, Yan G, Guo Y, Dong Y (2020) AR-net: adaptive attention and residual refinement network for copy-move forgery detection. IEEE Trans Ind Inform 16(10):6714–6723

    Article  Google Scholar 

Download references

Funding

No funding is provided for the preparation of manuscript.

Author information

Authors and Affiliations

  1. Electronics and Telecommunication Department, P. R. Pote College of Engineering and Management, Amravati, Maharashtra, 444602, India

    Rupesh D. Sushir

  2. P. R. Patil College of Engineering & Technology, Kathora Road, Amravati, India

    Dinkar Govindrao Wakde

Authors
  1. Rupesh D. Sushir
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dinkar Govindrao Wakde
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rupesh D. Sushir.

Ethics declarations

Conflict of interest

Authors declared that they have no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sushir, R.D., Wakde, D.G. An improved detection of blind image forgery using hybrid deep belief network and adaptive fuzzy clustering. Multimed Tools Appl 81, 29177–29205 (2022). https://doi.org/10.1007/s11042-022-12923-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12923-y

Keywords

Search

Navigation