STRUCTURAL ADAPTIVE ANISOTROPIC NAS-RIF FOR BIOMEDICAL IMAGE RESTORATION
Abstract
Blind image deconvolution is an ill-posed problem that attempts to restore an acquired image degraded by unknown PSF. A variational BID implementation, called NAS-RIF, is known for being robust but prone to poor convergence under low SNR and unrealistic support. Motivated by simple yet efficient fidelity metric, this paper presents an improved NAS-RIF by reducing adverse effect of inverse high-pass filter and computationally intensive pre-deterministic noise removal, by adaptively incorporating anisotropic structural property within local neighborhood seamlessly in NAS-RIF cost function. With an automatic support region estimation, the entire deconvolution process was fully automatic. The experimental results reported herein indicated that the enhanced structural adaptive anisotropic NAS-RIF had better convergence condition, while maintaining the underlying image fidelity.Blind image deconvolution is an ill-posed problem that attempts to restore an acquired image degraded by unknown PSF. A variational BID implementation, called NAS-RIF, is known for being robust but prone to poor convergence under low SNR and unrealistic support. Motivated by simple yet efficient fidelity metric, this paper presents an improved NAS-RIF by reducing adverse effect of inverse high-pass filter and computationally intensive pre-deterministic noise removal, by adaptively incorporating anisotropic structural property within local neighborhood seamlessly in NAS-RIF cost function. With an automatic support region estimation, the entire deconvolution process was fully automatic. The experimental results reported herein indicated that the enhanced structural adaptive anisotropic NAS-RIF had better convergence condition, while maintaining the underlying image fidelity.
References
Chen, T.J., Chuang, K.S., Chang, J.H., Shiao, Y.H., Chuang, C.C., 2006. A blurring index for medical images. Journal of Digital Imaging. 19(2), 118-125.
van Overveld, I. M. C. J., 1995. Contrast, noise, and blur affect performance and appreciation of digital radiographs. Journal of Digital Imaging. 8(4), 68-179.
Panyavaraporn, J., Horkaew, P., 2018. Classification of Alzheimer's disease in PET scans using MFCC and SVM. International Journal on Advanced Science, Engineering and Information Technology, 8(5), pp. 1829-1835.
Khaminkure, A., Horkaew, P., Panyavaraporn, J., 2017. Building a brain atlas based on gabor texture features, Proc. 14th Intl. Conference on Computer Science and Software Engineering, JCSSE 2017, 8025935, pp. 1-5.
Ipatov, Y., Krevetsky, A., Andrianov, Y., Sokolov, B., 2017. Creation of image models for evolving objects on dynamically changing scenes, Journal of Applied Engineering Sciences, 15(4), pp. 540-545.
Ipatov, Y., Krevetsky, A., Andrianov, Y., Sokolov, B., 2017. Robust classification of texture land forrest inventory based on model of minimally sufficient features, Journal of Applied Engineering Sciences, 15(3), pp. 236-241.
Turner, J.N., Lasek, S., Szarowski, D.H., 2001. Confocal optical microscopy. Encyclopedia of Materials: Science and Technology (Second Edition), pp. 1504-1509.
Jannetta, A., Jackson, J.C., Kotre, C.J., Birch, I.P., Robson, K.J., Padgett, R., 2004. Mammographic image restoration using maximum entropy deconvolution, Physics in Medicine and Biology, 49(4997), 18 pages.
Kundur, D., Hatzinzkos, D., 1996. Blind image deconvolution. IEEE Signal Processing Magazine, 13(8), 43-64.
Ruiz, P., Zhou, X., Mateos, J., Molina, R., Katsaggelos, A., 2015. Variational Bayesian blind image deconvolution: a review. Digital Signal Processing. 47, 116-127.
Molina, R., Mateos, J., Katsaggelos, A., 2006. Blind deconvolution using a variational approach to parameter, image, and blur estimation. IEEE Trans. Image Process, 15(12), 3715–3727.
Bishop, T.E., Babacan, S.D., Amizic, B., Katsaggelos, A.K., Chan, T., Molina, R., 2007. Blind image deconvolution: problem formulation and existing approaches, CRC Press, 49 pages.
Ayers, G. R., Dainty, J. C., 1988. Iterative blind deconvolution method and its applications, Optics Letters, 13(7), 547–549.
Kundur, D., Hatzinakos, D., 1995. A novel recursive filtering method for blind image restoration, Proc. IASTED International Conference on Signal and Image Processing (SIP), 428-431.
Kundur, D., Hatzinzkos D., 1996A. On the global asymptotic stability of the NAS-RIF algorithm, Proc. International Conference on Image Processing, 73-76.
Kundur, D., Hatzinzkos D., 1998. A novel blind deconvolution scheme for image restoration using recursive filtering, IEEE Signal Processing Magazine, 26(2), 375-390.
Ong, C.A., Chambers J.A., 1999. An enhanced NAS-RIF algorithm for blind image deconvolution, IEEE Transactions on Image Processing, 8(7), 988-992.
Kundur, D., Hatzinakos, D., Leung, H., 2000. Robust classification of blurred imagery, IEEE Transactions on Image Processing, 9, 243-255.
Maysuyama, M., Tanji, Y., Tanaka, M., 2000. Enhancing the ability of NAS_RIF algorithm for blind image deconvolution, Proc. IEEE International Symposium on Circuits and Systems (ISCAS). 553-556.
Yang, Y., Yang, Z., Shen, T., Chen, B., 2012. ENAS-RIF algorithm for image restoration, SPIE, Photonics Asia, 1, 85581Z-85581Z-8.
Siddhichai, S., Chambers, J.A., 2000. Wavelet transform-based noise reduction schemes to improve the noise sensitivity of the NAS-RIF algorithm for blind image deconvolution, Proc. Signal Processing Conference, 4 pages.
Wang, H., Qi, S., Liu, Y., 2009. An improved NAS-RIF algorithm based on the lifting scheme for blind image restoration, IEEE Circuits, Communications and Systems, 423-426.
Chow, T.W.S., Li, X.D., Cho, S.Y, 2000. Improved blind image restoration scheme using recurrent filtering, Proc. IEE Vision Image and Signal Processing, 147(1), 23-28.
Kundur, D., Hatzinakos, D., 1996B. Blind image deconvolution. IEEE Signal Processing Magazine, 13(3), 43-64.
Chany, T.F., Yipy, A.M., Parky, F.E., 2005. Simultaneous total variation image inpainting and blind deconvolution. International Journal of Imaging System and Technology, 15(1), 92-102.
Zhulina, Y.V., 2006. Multiframe blind deconvolution of heavily blurred astronomical images. Applied Optics, 45(28) 7342-7352.
Zhang, J., Zhang, Q., He, G., 2009. Blind deconvolution of a noisy degraded image, Applied Optics, 48(12), 2350-5.
Hanocka, R., Kiryati, N., 2015. Progressive blind deconvolution. LCNS Computer Analysis of Images and Patterns, 9257, 313-325.
Yang, G.Z., Burger, P., Firmin, D.N., Underwood, S.R. 1996. Structure adaptive anisotropic image filtering, Image and Vision Computing, 14, 135-145.
Wu, J., Feng, Z., Ren, Z., 2014. Improved structure-adaptive anisotropic filter based on a nonlinear structure tensor. Cybernetic and Information Technology, 14(1), 112-127.
Otsu, N., 1979. A threshold selection method from gray-level histograms. IEEE Trans. Sys., Man., Cyber. 9(1), 62–66.
Sezgin, M., Sankur, B., 2004. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging. 13(1), 146–165.
Shi, S., 2013. Emgu CV essentials, Packt Publishing, 118 pages.
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P., 2004. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing. 13(4), pp. 600–612.
Garcia-Nieto, J., Alba, E., Jourdan, L., Talbi E., 2009. Sensitivity and specificity based multiobjective approach for feature selection: Application to cancer diagnosis, Information Processing Letters, 109(16), 887-896.
