Effective neural LUM smoother for image smoothing applications

• Autorzy: Lukac R.
• Języki publikacji: EN

Abstrakty

EN

In this paper, an effective image filtering approach for the impulsive noise suppression with the simultaneous signal-detail preservation is presented. The novelty of the proposed method lies in the combination of the LUM (lower-upper-middle) smoothing characteristics and the neural network. The included LUM-based impulse detector improves the signal-detail preservation capability of the proposed method, whereas the neural network along with the input LUM smoothers guarantee its noise attenuation capability. Since the LUM operation can be very efficiently implemented, the proposed method is computationally attractive and useful for practical image filtering applications.

Słowa kluczowe

EN

LUM smoothers; impulsive noise; adaptive filtering; neural network; backpropagation; noise removal; image processing

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2003
• Tom: Vol. 12, No. 3
• Strony: 377--391
• Opis fizyczny: Bibliogr. 34 poz., rys., wykr.

Twórcy

autor

Lukac R.

• Slovak Image Processing Center, Jarkova 343, 049 25 Dobsina, Slovak Republic,

Bibliografia

• [1] Berstain R.: Adaptive nonlinear filters for simultaneous removal of different kinds of noise in images. IEEE Trans. on Circuits and Systems, CAS-34(11), 1275-1291. 1987.
• [2] Pitas I., Venetsanopoulos A.N.: Nonlinear Digital Filters: Principles and Applications. Kluwer Academic Publishers. 1990.
• [3] Arce G.R.: Multistage order statistic filters for image sequence processing. IEEE Trans. on SP, 39(5), 1146-1163. 1991.
• [4] Pitas I., Venetsanopoulos A.N.: Order statistics in digital image processing. Proc. of the IEEE, 80(12), 1892-1919. 1992.
• [5] Wright M.J.: Training and Testing of Neural Net Window Operators on Spatiotemporal Image Sequences. In Neural Networks for Vision, Speech and Natura! Language (Linggard R., Myers D.J. Nightingale C.), Chapman and Hall International. 1992.
• [6] Glasa J.: Bit-level systolic arrays for digital contour smoothing by Abel-Poisson kernel. Parallel Processing Letters, 3, 43-51. 1993.
• [7] Hardie R .C., Boncelet C.G.: LUM Filters: A class of rank-order-based filters for smoothing and sharpening. IEEE Trans. on SP, 41(3), 1061-1076. 1993.
• [8] Yin L., Astola J., Neuvo Y.: A New Class of Nonlinear Filters - Neural Filters. IEEE Trans. on SP, 41(3), 1201-1222. 1993.
• [9] Klima M., Dvorak P., Zahradnk P., Kolar J., and Kott P.: Motion detection and target tracking in a TV image for security purposes. Proc. of the IEEE Carnahan Conf. on Security Technology, Albuquerque, USA, 43-44. 1994.
• [10] Bishop C .M.: Neural Networks for Pattern Recognition, Clarendon Press, Oxford. 1995.
• [11] Kleihorst R .P., Lagendijk R.L., Biemond J.: Noise reduction of image sequences using motion compensation and signal decomposition. IEEE Trans. on IP, 4, 274-284. 1995.
• [12] Zahradnik P., Klima M., Cuda J.: Real time video motion detection based on the TMS 320C50 Signal Processor, Proc. of The Texas Instruments Educators Conf., 51-53. 1995.
• [13] Kong H., Guan L.: A neural network adaptive filter for the removal of impulse noise in digital images. NN, 9(3), 373-378. 1996.
• [14] Astola J., Akopian D., Vainio O., Agaian S.: New digit-serial implementations of stack filters. SP, 61, 181-197.1997.
• [15] Astola J., Kuosmanen K.: Fundamentals of Nonlinear Digital Filtering, CRC Press LLC, New York. 1997.
• [16] Beghdadi A., Khellaf A.A.: Noise-filtering method using a local information measure. IEEE Trans. on IP, 6(6), 879-882. 1997.
• [17] Kokaram A.: Motion Picture Restoration. S-V, London. 1998.
• [18] Leondes C.T.: Image Processing and Pattern Recognition: Neural Networks Systems, Techniques and Applications, AP, London. 1998.
• [19] Chen T., Ma K.K., Chen L.H.: Tri-state median filter for image denoising. IEEE Trans. on IP, 8(12), 1834-1838. 1999.
• [20] Wang Z., Zhang D.: Progressive switching median filter for the removal of impulse noise from highly corrupted images. IEEE Trans. Circuits and Systems II, 46(1), 78-80. 1999.
• [21] Boncelet C.: Image Noise Models. Bovik A. (Ed.): Handbook of Image and Video Processing. AP. 2000.
• [22] Glasa J.: On derivatives estimation of smoothed digital curves. C&AI, 19, 335-349. 2000.
• [23] Lagendijk R.L., Roosmalen P.M., Biemond J.: Video Enhancement and Restoration. Bovik A. (Ed.): Handbook of Image and Video Processing, AP. 2000.
• [24] Mitra S., Sicuranza J.: Nonlinear Image Processing, AP. 2000.
• [25] Nikolaidis N., Pitas I.: 3-D Image Processing Algorithms, Wiley. 2000.
• [26] Chen T., Wu H.R.: Adaptive impulse detection using center-weighted median filters. IEEE SPL, 8(1), 1-3. 2001.
• [27] Eng H.L., Ma K.K.: Noise adaptive soft-switching median filter. IEEE Trans. on IP, 10(2), 242-251. 2001.
• [28] Lukac R., Marchevsky S.: LUM smoother with smooth control for noisy image sequences. EURASIP J. on Applied Signal Processing, 2001(2), 110-120. 2001.
• [29] Lukac R., Marchevsky, S.: Boolean expression of LUM smoothers. IEEE SPL, 8(11), 292-294. 2001.
• [30] Fischer V., Drutarovsky M., Lukac R.: Implementation of 3-D adaptive LUM smoother in reconfigurable hardware. Proc. of the 12th Int. Conf. on Field Programmable Logic and Applications FPL 2002, Montpellier, France, LNCS, 2438, 720-729. 2002.
• [31] Hashimoto Y., Kajikawa Y., Nomura Y.: Directional difference-based switching median filters. Electronics and Communications in Japan, 3, 85(3), 22-32. 2002.
• [32] Lukac R.: Simplified boolean LUM smoothers. Proc. of the 4th EURASIP-IEEE Reg. 8 Int. Symp. on Video/Image Processing and Multimedia Communications VIPromCom-2002, Zadar, Croatia, 159-162. 2002.
• [33] Lukac R.: Binary LUM smoothing. IEEE SPL 9(12), 400-403. 2002.
• [34] Zhang S., Karim M.A.: A new impulse detectorfor swithing median filters. IEEE SPL, 9(11), 360-363. 2002.