Combination of DWT And LPQ Features for Document Age Identification

Combination of DWT And LPQ Features for Document Age Identification
  IJETT-book-cover           
  
© 2022 by IJETT Journal
Volume-70 Issue-2
Year of Publication : 2022
Authors : Pushpalata Gonasagi, Shivanand S Rumma, Mallikarjun Hangarge
DOI :  10.14445/22315381/IJETT-V70I2P229

How to Cite?

Pushpalata Gonasagi, Shivanand S Rumma, Mallikarjun Hangarge, "Combination of DWT And LPQ Features for Document Age Identification," International Journal of Engineering Trends and Technology, vol. 70, no. 3, pp. 254-265, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I2P229

Abstract
This paper presents an algorithm based on DWT(Discrete Wavelet Transform) of RT(Radon Transforms) and LPQ(Local Phase Quantization) for document age identification. Features computed by applying fusion of DWT of RT and LPQ techniques on a dataset of 640 handwritten document images written by 640 writers(320 are original and 320 forged). The classification of forged and original documents was performed using an SVM(Support Vector Machine) classifier. The average classification accuracy of original and forgery documents is 93.9% and 92.5%, respectively.

Keywords
RT, DWT, LPQ, Forgery Documents, SVM.

Reference
[1] Chim, J. L. C., Li, C. K., Poon, N. L., & Leung, S. C., Examination of counterfeit banknotes printed by all-in-one colour inkjet printers. Journal of the American Society of Questioned Document Examiners, 7(2) (2004) 69-75.
[2] Makris, J.D., Krezias, S.A. and Athanasopoulou, V.T., Examination of newspapers. Journal of the American Society of Questioned Document Examiners (ASQDE), 9(2) (2006)71-75.
[3] Gebhardt, J., Goldstein, M., Shafait, F. and Dengel, A., , August. Document authentication using printing technique features and unsupervised anomaly detection. In 2013 12th International conference on document analysis and recognition (2013). 479-483. IEEE.
[4] Bertrand, R., Gomez-Krämer, P., Terrades, O.R., Franco, P. and Ogier, J.M., A system based on intrinsic features for fraudulent document detection. In 2013 12th International conference on document analysis and recognition ., (2013) 106-110. IEEE.
[5] Halder, B. and Garain, U., Colour feature-based approach for determining ink age in printed documents. In 2010 20th International conference on pattern recognition., (2010) 3212-3215. IEEE.
[6] Raghunandan, K. S., Shivakumara, P., Navya, B. J., Pooja, G., Prakash, N., Kumar, G. H. & Lu, T., Fourier coefficients for fraud handwritten document classification through age analysis. In 2016 15th International conference on frontiers in handwriting recognition (ICFHR) ., IEEE, (2016) 25-30.
[7] da Silva Barboza, R., Lins, R. D., & de Jesus, D. M., A colour-based model to determine the age of documents for forensic purposes. In 2013 12th International conference on document analysis and recognition (2013) 1350-1354. IEEE.
[8] Elkasrawi, S., & Shafait, F., Printer identification using supervised learning for document forgery detection. In 2014 11th IAPR International Workshop on Document Analysis Systems,. (2014). 146-150. IEEE.
[9] Khan, Z., Shafait, F., & Mian, A., Automatic ink mismatch detection for forensic document analysis. Pattern Recognition, 48(11) (2015) 3615-3626.
[10] Luo, Z., Shafait, F., & Mian, A., Localized forgery detection in hyperspectral document images. In 2015 13th International Conference on Document Analysis and Recognition (ICDAR) (pp. 496-500). IEEE.
[11] Alkawaz, M. H., Sulong, G., Saba, T., & Rehman, A, 2018. Detection of copy-move image forgery based on discrete cosine transform. Neural Computing and Applications, 30(1) (2018)183-192.
[12] Vieira, R., Silva, C., Antunes, M., & Assis, A., Information system for automation of counterfeited documents images correlation. Procedia Computer Science, 100 (2016) 421-428.
[13] Berenguel, A., Terrades, O. R., Lladós, J., & Cañero, C,. e-Counterfeit: a mobile-server platform for counterfeit document detection. In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)., 9 (2017) 15-20. IEEE.
[14] Nawade S.A., Rumma S., Pardeshi R., Hangarge M., Old Handwritten Music Symbol Recognition Using Radon and Discrete Wavelet Transform. In: Chiplunkar N., Fukao T. (eds) Advances in Artificial Intelligence and Data Engineering. Advances in Intelligent Systems and Computing, Springer, Singapore. https://doi.org/10.1007/978-981-15-3514-7_86., 1133 (2021).
[15] Mallat, S. G., A theory for multiresolution signal decomposition: the wavelet representation. In Fundamental Papers in Wavelet Theory., (2009) 494-513. Princeton University Press.
[16] Jiao, J., & Deng, Z., Deep combining of local phase quantization and histogram of oriented gradients for indoor positioning based on a smartphone camera. International Journal of Distributed Sensor Networks, 13(1) (2017) 1550147716686978.
[17] Gonasagi, P., Pardeshi, R., & Hangarge, M., Classification of Documents based on Local Binary Pattern Features through Age Analysis. In Ambient Communications and Computer Systems, 265-271 (2020) Springer, Singapore.
[18] Veershetty, C., & Hangarge, M. Logo retrieval and document classification based on LBP features. In Data Analytics and Learning , Springer, Singapore, (2019) 131-141.
[19] Cortes, C., & Vapnik, V. Support-vector networks. Machine learning, 20(3) (1995) 273-297.