Abstract
Multiclass CNN-based window adaptive optimized filter has been proposed in this research work to remove impulse noise from colored images. Instead of applying adaptive filter on the whole images, selective adaptive window has been applied on the test image so that the effective computational complexity of the system is reduced. In this article, multiclass CNN has been used for the choosing the range of selective window. After that, vectored minimum mean value-based detection is being applied on the pixel under operation on a particular kernel of image for detection of noise and defining the appropriate size of the window surrounding the pixel under operation. An adaptive vector median filter incorporated with particle swarm optimization (AVMPSO) is passed over the corrupted pixel if the pixel is determined as corrupted after detection of noisy and noise-free pixels. The performance comparison of the proposed AVMPSO has been carried out along with the available state-of-the-art filters in terms of peak signal-to-noise ratio (PSNR), mean square error (MSE), structural similarity index matrix (SSIM), and feature similarity index matrix (FSIMC). A large set of images has been considered to conclude how AVMPSO outperforms the existing methods at all levels of noise by ~ 1.5 to 3 dB (PSNR) at least.
Similar content being viewed by others
References
Pitas, I., Venetsanopoulos, A.N.: Order statistics in digital image processing. Proc. IEEE 80(12), 1893–1921 (1992)
Tukey, J.W.: Exploratory Data Analysis (1977)
Tukey, J.W.: Nonlinear (Nonsuperposable) Methods for Smoothing Data. In: Congressional Record 1974 EASCON, 673 (1974)
Gonzalez, R.C., Woods, R.E.: Digital Image Processing, Nueva Jersey (2008)
Astola, J., Haavisto, P., Neuvo, Y.: Vector median filters. Proc. IEEE 78(4), 678–689 (1990)
Sun, T., Neuvo, Y.: Detail-preserving median based filters in image processing. Pattern Recogn. Lett. 15(4), 341–347 (1994)
Ko, S.J., Lee, Y.H.: Center weighted median filters and their applications to image enhancement. IEEE Trans. Circuits Syst. 38(9), 984–993 (1991)
Alparone, L., Baronti, S., Carla, R.: Two-dimensional rank-conditioned median filter. IEEE Trans. Circuits Syst. Analog Digital Signal Process, 42(2), 130–132 (1995)
Wang, Z., Zhang, D.: Progressive switching median filter for the removal of impulse noise from highly corrupted images. IEEE Trans. Circuits Syst. II Analog Digital Signal Process. 46(1), 78–80 (1999)
Zhang, S., Karim, M.A.: A new impulse detector for switching median filters. IEEE Signal Process. Lett. 9(11), 360–363 (2002)
Geng, X., Hu, X., Xiao, J.: Quaternion switching filter for impulse noise reduction in color image. Signal Process. 92(1), 150–162 (2012)
Horng, S.J., Hsu, L.Y., Li, T., Qiao, S., Gong, X., Chou, H.H., Khan, M.K.: Using sorted switching median filter to remove high-density impulse noises. J. Vis. Commun. Image Represent. 24(7), 956–967 (2013)
Laskar, R.H., Bhowmick, B., Biswas, R., Kar, S.: Removal of impulse noise from color image. In: TENCON 2009–2009 IEEE Region 10 Conference (pp. 1–5), IEEE (2009)
Eng, H.L., Ma, K.K.: Noise adaptive soft-switching median filter. IEEE Trans. Image Process. 10(2), 242–251 (2001)
Singh, K.M., Bora, P.K.: Adaptive vector median filter for removal impulses from color images. In: Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS'03, vol. 2, IEEE, pp. II-396 (2003)
Roy, A., Laskar, R.H.: Non-casual linear prediction based adaptive filter for removal of high density impulse noise from color images. AEU-Int. J. Electron. C. 72, 114–124 (2017)
Mohapatra, S., Sa, P.K., Majhi, B.: Adaptive threshold selection for impulsive noise detection in images using coefficient of variance. Neural Comput. Appl. 21(2), 281–288 (2012)
Smolka, B., Lukac, R., Chydzinski, A., Plataniotis, K.N., Wojciechowski, W.: Fast adaptive similarity based impulsive noise reduction filter. Real Time Imaging 9(4), 261–276 (2003)
Yuan, S.Q., Tan, Y.H.: Impulse noise removal by a global–local noise detector and adaptive median filter. Signal Process. 86(8), 2123–2128 (2006)
Lin, C.H., Tsai, J.S., Chiu, C.T.: Switching bilateral filter with a texture/noise detector for universal noise removal. IEEE Trans. Image Process. 19(9), 2307–2320 (2010)
Jafar, I.F., AlNa’mneh, R.A., Darabkh, K.A.: Efficient improvements on the BDND filtering algorithm for the removal of high-density impulse noise. IEEE Trans. Image Process. 22(3), 1223–1232 (2013)
Dawood, H., Dawood, H., Guo, P.: Removal of random-valued impulse noise by local statistics. Multimedia Tools Appl. 74(24), 11485–11498 (2015)
Esakkirajan, S., Veerakumar, T., Subramanyam, A.N., PremChand, C.H.: Removal of high density salt and pepper noise through modified decision based unsymmetric trimmed median filter. IEEE Signal Process. Lett. 18(5), 287–290 (2011)
Ahmed, F., Das, S.: Removal of high-density salt-and-pepper noise in images with an iterative adaptive fuzzy filter using alpha-trimmed mean. IEEE Trans. Fuzzy Syst. 22(5), 1352–1358 (2014)
Bhadouria, V.S., Ghoshal, D., Siddiqi, A.H.: A new approach for high density saturated impulse noise removal using decision-based coupled window median filter. SIViP 8(1), 71–84 (2014)
Schulte, S., De Witte, V., Nachtegael, M., Van der Weken, D., Kerre, E.E.: Histogram-based fuzzy colour filter for image restoration. Image Vis. Comput. 25(9), 1377–1390 (2007)
Masood, S., Hussain, A., Jaffar, M.A., Choi, T.S.: Color differences based fuzzy filter for extremely corrupted color images. Appl. Soft Comput. 21, 107–118 (2014)
Verma, O.P., Hanmandlu, M., Sultania, A.K., Parihar, A.S.: A novel fuzzy system for edge detection in noisy image using bacterial foraging. Multidimens. Syst. Signal Process. 24(1), 1–18 (2012)
Budak, C., Türk, M., Toprak, A.: Reduction in impulse noise in digital images through a new adaptive artificial neural network model. Neural Comput. Appl. 26(4), 835–843 (2015)
Roy, A., Laskar, R.H.: Impulse noise removal based on SVM classification. In: TENCON 2015–2015 IEEE Region 10 Conference, IEEE, pp. 1–5 (2015)
Roy, A., Singha, J., Devi, S.S., Laskar, R.H.: Impulse noise removal using SVM classification based fuzzy filter from gray scale images. Signal Process. 128, 262–273 (2016)
Roy, A., Laskar, R.H.: Multiclass SVM based adaptive filter for removal of high density impulse noise from color images. Appl. Soft Comput. 46, 816–826 (2015)
Roy, A., Devi, S.S., Laskar, R.H.: Impulse noise removal from gray scale images based on ANN classification based Fuzzy filter. In: CINE 2016 conference, IEEE, pp. 1–5 (2016)
Mursal, A.S.N., Ibrahim, H.: Median filtering using first-order and second-order neighborhood pixels to reduce fixed value impulse noise from grayscale digital images. Electronics 9(12), 2034 (2020)
Veerakumar, T., Subudhi, B.N., Esakkirajan, S.: Empirical mode decomposition and adaptive bilateral filter approach for impulse noise removal. Expert Syst. Appl. 121, 18–27 (2019)
Chan, R.H., Ho, C.W., Nikolova, M.: Salt-and-pepper noise removal by median-type noise detectors and detail-preserving regularization. IEEE Trans. Image Process. 14(10), 1479–1485 (2005)
Singh, K.M.: Vector median filter based on non-causal linear prediction for detection of impulse noise from images. Int. J. Comput. Sci. Eng. 7(4), 345–355 (2012)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Zhang, L., Zhang, L., Mou, X., Zhang, D.: FSIM: a feature similarity index for image quality assessment. IEEE Trans. Image Process. 20(8), 2378–2386 (2011)
Abdelmounaime, S., Dong-Chen, H.: New Brodatz-based image databases for grayscale color and multiband texture analysis. Int. Sch. Res. Not. 2013, 14 (2013)
Liu, S., Fan, J., Ai, D., Song, H., Fu, T., Wang, Y., Yang, J.: Feature matching for texture-less endoscopy images via superpixel vector field consistency. Biomed. Opt. Express 13(4), 2247–2265 (2022)
Funding
This study was funded by no funding agency.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Dr. Amarjit Roy has no conflict of interest. Dr. Lakhan Dev Sharma has no conflict of interest. Dr. Alok Kumar Shukla has 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
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Roy, A., Sharma, L.D. & Shukla, A.K. Multiclass CNN-based adaptive optimized filter for removal of impulse noise from digital images. Vis Comput 39, 5809–5822 (2023). https://doi.org/10.1007/s00371-022-02697-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-022-02697-7