Abstract
Use of handwriting words for person identification in contrast to biometric features is gaining importance in the field of forensic applications. As a result, forging handwriting is a part of crime applications and hence is challenging for the researchers. This paper presents a new work for detecting forged handwriting words because width and amplitude of spectral distributions have the ability to exhibit unique properties for forged handwriting words compared to blurred, noisy and normal handwriting words. The proposed method studies spectral density and variation of input handwriting images through clustering of high and low frequency coefficients. The extracted features, which are invariant to rotation and scaling, are passed to a neural network classifier for the classification for forged handwriting words from other types of handwriting words (like blurred, noisy and normal handwriting words). Experimental results on our own dataset, which consists of four handwriting word classes, and two benchmark datasets, namely, caption and scene text classification and forged IMEI number dataset, show that the proposed method outperforms the existing methods in terms of classification rate.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shivakumara, P., Basavaraja, V., Gowda, H.S., Guru, D.S., Paland, U., Lu, T.: A new RGB based fusion for forged IMEI number detection in mobile images. In: Proceedings of the ICFHR, pp. 386–391 (2018)
Ferrer, M.A., Morales, A., Vargas, J.F., Lemos, I., Quintero, M.: Is it possible to automatically identify who has forged my signature? Approaching to the identification of static signature forger. In: Proceedings of the DAS, pp. 175–179 (2012)
Fahn, C.S., Lee, C.P., Chen, H.I.: A text independent handwriting forgery detection system based on branchlet features and Gaussian mixture models. In: Proceedings of the PST (2016)
Ghanim, T.M., Nabil, A.M.: Offline signature verification and forgery detection approach. In: Proceedings of the ICCES, pp. 293–298 (2018)
Kumar, R., Pal, N.R., Chanda, B., Sharma, J.D.: Forensic detection of fraudulent alterations in ball point pen strokes. IEEE Trans. IFS 7(2), 809–820 (2012)
Shivakumara, P., Kumar, N.V., Guru, D.S., Tan, C.L.: Separation of graphics (superimposed) and scene text in videos. In: Proceedings of the DAS, pp. 344–348 (2014)
Xu, J., Shivakumara, P., Lu, T., Phan, T.Q., Tan, C.L.: Graphics and scene text classification in video. In: Proceedings of the ICPR, pp. 4714–4719 (2014)
Roy, S., Shivakumara, P., Pal, U., Lu, T., Tan, C.L.: New tampered features for scene and caption text classification in video frame. In: Proceedings of the ICFHR, pp. 36–41 (2016)
Bhardwaj, D., Pankajakshan, V.: Image overlay text detection based on JPEG truncation error analysis. IEEE Signal Process. Lett. 23(8), 1027–1031 (2016)
Roy, S., Shivakumara, P., Pal, U., Lu, T., Wahab, A.W.B.A.: Temporal integration of word-wise caption and scene text identification. In: Proceedings of the ICDAR, pp. 350–355 (2017)
Barbosa, R.D.S., Lins, R.D., Lira, E.D.F.D., Camara, A.C.A.: Later added strokes of text fraud detection in documents written with ballpoint pens. In: Proceedings of the ICFHR, pp. 517–522 (2014)
Elkasrawi, S., Shafait, F.: Printer identification using supervised learning for document forgery detection. In: Proceedings of the DAS, pp. 146–150 (2014)
Ahmed, A., Shafait, F.: Forgery detection based on intrinsic document features. In: Proceedings of the DAS, pp. 252–256 (2014)
Khan, Z., Shafait, F., Mian, A.: Automatic ink mismatch detection for forensic document analysis. Pattern Recogn. 48, 3615–3626 (2015)
Luo, Z., Shafait, F., Mian, A.: Localized forgery detection in hyperspectral document images. In: Proceedings of the ICDAR, pp. 496–500 (2015)
Bertrand, R., Kramer, P.G., Terrades, O.R., Franco, P., Ogier, J.M.: A system based on intrinsic features for fraudulent document detection. In: Proceedings of the ICDAR, pp. 106–110 (2013)
Raghunandan, K.S., et al.: Fourier coefficients for fraud handwritten document classification through age analysis. In: Proceedings of the ICFHR, pp. 25–30 (2016)
Wang, Z., Shivakumara, P., Lu, T., Basavanna, M., Pal, U., Blumenstein, M.: Fourier-residual for printer identification. In: Proceedings of the ICDAR, pp. 1114–1119 (2017)
Cha, S.H., Tappert, C.C.: Automatic detection of handwriting forgery. In: Proceedings of the IWFHR (2012)
Wang, R., Li, W., Li, R., Zhang, L.: Automatic blur type classification via ensemble SVM. Sig. Process. Image Commun. 71, 24–35 (2019)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Man Cybern. 9(1), 62–66 (1979)
Kleber, F., Fiel, S., Diemand, M., Sablatnig, R.: CVL-database: an off-line database for writer retrieval, writer identification and word spotting. In: Proceedings of the ICDAR, pp. 560–564 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kundu, S., Shivakumara, P., Grouver, A., Pal, U., Lu, T., Blumenstein, M. (2020). A New Forged Handwriting Detection Method Based on Fourier Spectral Density and Variation. In: Palaiahnakote, S., Sanniti di Baja, G., Wang, L., Yan, W. (eds) Pattern Recognition. ACPR 2019. Lecture Notes in Computer Science(), vol 12046. Springer, Cham. https://doi.org/10.1007/978-3-030-41404-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-41404-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-41403-0
Online ISBN: 978-3-030-41404-7
eBook Packages: Computer ScienceComputer Science (R0)