PERFORMANCE COMPARISON OF DENOISING METHODS FOR HISTORICAL DOCUMENTS
DOI:
https://doi.org/10.11113/jt.v77.6676Keywords:
DCT-based image denoising, mean filtering, median filtering, Gaussian filteringAbstract
Image denoising plays an important role in image processing. It is also part of the pre-processing technique in a binarization complete procedure that consists of pre-processing, thresholding, and post-processing. Our previous research has confirmed that the Discrete Cosine Transform (DCT)-based filtering as the new pre-processing process improved the performance of binarization output in terms of recall and precision. This research compares three classical denoising methods; Gaussian, mean, and median filtering with the DCT-based filtering. The noisy ancient document images are filtered using those classical filtering methods. The outputs of this process are used as the input for Otsu, Niblack, Sauvola and NICK binarization methods. Then the resulted binary images of the three classical methods are compared with those of DCT-based filtering. The performance of all denoising algorithms is evaluated by calculating recall and precision of the resulted binary images. The result of this research is that the DCT based filtering resulted in the highest recall and precision as compared to the other methods.Â
References
Maleki, Arian, Manjari Narayan, and Richard G. Baraniuk. Anisotropic nonlocal means denoising. Applied and Computational Harmonic Analysis. 35.3 (2013): 452-482.
B. Gatos, I. Pratikakis, S. J. Perantonis. 2006. Adaptive degraded document image binarization, Pattern Recognition. 39(3): 317-327,
R. F. Moghaddam and M. Cheriet, AdOtsu. 2012. An adaptive and parameterless generalization of Otsus method for document image binarization. Pattern Recognition. 45: 2419-2431.
B. Su, S. Lu, and C. L. Tan. 2013. Robust Document Image Binarization Technique for Degraded Document Image, IEEE Trans. Image Processing. 22(4): 1408-1417,
Arnia, Fitri; Munadi, Khairul; Fardian; Muchallil, Sayed. Improvement of binarization performance by applying DCT as pre-processing procedure, Communications, Control and Signal Processing (ISCCSP), 2014 6th International Symposium on.1 28(132): 21-23 May 2014
Buades, Antoni, Bartomeu Coll, and Jean-Michel Morel. June 2005. A review of image denoising algorithms, with a new one. Multiscale Modeling & Simulation 4(2): 490-530. 2005 Buades, A; Coll, B.; Morel, J. -M, "A non-local algorithm for image denoising, Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on , 2: 60,65. 2: 20-25
Maria Petrou and Panagiota Bosdogianni. 1999. Image Processing : The Fundamentals. Wiley
Lin Yin; Ruikang Yang; Gabbouj, M.; Neuvo, Y. 1996. "Weighted median filters: a tutorial," Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on .43(3):157&192
F. Arnia, I. Iizuka, M. Fujiyoshi and H. Kiya, 2007. “DCT signbased similarity measure for JPEG image retrieval,†IEICE Trans. Fund. of Elect., Comm. and Comp. Sci., Vol. E90-A.9: 1976-1985
F. Arnia, K. Munadi, M. Fujiyoshi and H. Kiya. 2009. “Efï¬cient Content-Based Copy Detection Using Signs of DCT Coefï¬cient, “in Proc. IEEE Symp. on Industrial Electronics and Applications (ISIEA) . 493-498
Qureshi, M. I., Khan, N. U., Rasli, A. M., and Zaman, K. 2015. The battle of health with environmental evils of Asian countries: promises to keep. Environmental Science and Pollution Research. 1-8.
Qureshi, M. I., Rasli, A. M., Awan, U., Ma, J., Ali, G., Alam, A., and Zaman, K. 2014. Environment and air pollution: health services bequeath to grotesque menace. Environmental Science and Pollution Research. 22(5): 3467-3476.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
