An adaptive texture-preserved image denoising model
Tóm tắt
Suppressing noise
while preserving textures is one of the most important and challenging problems in natural image denoising. Various priors of natural image, such as gradient based prior, nonlocal self-similarity based prior etc., have been widely studied for noise removal. The methods based on these priors may smooth the fine scale image textures and degrade visual quality of the image. To improve image visual quality, an improved texture-preserved total variation (TPTV) image denoising model with an adaptive fidelity item is proposed in this paper. Firstly, we construct an image structure control function (SCF) based on structure tensor to describe the image structure information. Secondly, we combine SCF into a total variation framework for noise removal such that the model can adaptively balance its regular and fidelity item to keep fine scale features while denoising. Finally, extensive experimental evaluations demonstrate that our TPTV model can well preserve the texture appearance in the denoised image and make them more natural. Besides, it overcomes staircase and over-smoothing effects compared with some competing algorithms.
Tài liệu tham khảo
Abdelkader K, Broeckhove J (2009) Pricing computational resources in a dynamic grid. Int J Grid Util Comput 1:205–215
Alvarez L, Morel JM (1994) Formalization and computational aspects of image analysis. Acta Numer 3:1–59
Alvarez L, Guichard F, Lions PL, Morel M (1993) Axioms and fundamental equations of image processing. Arch Rational Mech Anal 123(3):199–257
Ballester C, Bertalmio M, Caselles V, Sapiro G, Verdera J (2001) Filling-in by joint interpolation of vector fields and gray levels. IEEE Trans Image Process 10(8):1200–1211
Benavente-Peces C, Ahrens A, Filipe J (2014) Advances in technologies and techniques for ambient intelligence. J Ambient Intell HumComput 5(5):621–622
Bertalmio M, Bertozzi AL, Sapiro G (2001) Navier–Stokes, fluid dynamics, image and video inpainting. In: IEEE conference on computer vision and pattern recognition, vol 1. IEEE, New York, pp I-355–I-362. doi:10.1109/CVPR.2001.990497
Blomgren P, Chan TF (1998) Color tv: total variation method for restoration of vectorvalued images. IEEE Trans Image Process 7:304–309
Brox T, Weickert J, Burgeth B, Mrazeket P (2006) Nolinear structure tensors. Image Vis Comput 24:41–55
Carullo G, Castiglione A, Santis AD, Palmieri F (2015) A triadic closure and homophily-based recommendation system for online social networks. World Wide Web. doi:10.1007/s11280-015-0333-5
Catte F, Lions PL, Morel JM, Coll T (1992) Image selective smoothing and edge detection by nonlinear diffusion. SIAM J Numer Anal 29:182–193
Cremers D, Tischhäuser F, Weickert J, Schnörr C (2002) Diffusion snakes: introducing statistical shape knowledge into the Mumford–Shah functional. Int J Comput Vis 50(3):295–313
Gilboa G, Sochen N, Zeevi YY (2003) Texture preserving variational denoising using an adaptive fidelity term. In: Proceedings of the VLSM 2003, Nice
Gilboa G, Sochen N, Zeevi YY (2004) Estimation of optimal PDE-based denoising in the SNR sense. In: CCIT report 499, Technion, Haifa
Ho TB, Bellot P, Cao T (2012) Advances in information and knowledge systems. J Ambient Intell Hum Comput 3(4):249–249
Kim S (2006) PDE-based image restoration: a hybrid model and color image denoising. IEEE Trans Image Process 15(5):1163–1170
Klthe U (2003) Edge and junction detection with an improved structure tensor. In: Lecture notes in computer science, pp 25–32
Li J, Wang Q, Wang C, Cao N, Ren K, Lou W (2010) Fuzzy keyword search over encrypted data in cloud computing. In: Proceedings of the IEEE on INFOCOM. IEEE, New York, pp 1–5
Li J, Huang X, Li J, Chen X, Xiang Y (2014) Securely outsourcing attribute-based encryption with checkability. IEEE Trans Parallel Distrib Syst 25(8):2201–2210
Lin Z, Cho S, Metaxas D, Paris S, Wang J (2013) Handling noise in single image deblurring using directional filters. In: IEEE conference on computer vision and pattern recognition (CVPR). IEEE, New York, pp 612–619
Marquina A, Osher S (2000) Explicit algorithms for a new time dependent model based on level set motion for nonlinear deblurring and noise removal. SIAM J Sci Comput 22:387–405
Palmieri F, Fiore U, Ricciardi S, Castiglione A (2015) Grasp-based resource re-optimization for effective big data access in federated clouds. Future Gener Comput Syst
Pandey M, Pathak VK, Chaudhary BD (2012) A framework for interest-based community evolution and sharing of latent knowledge. Int J Grid Util Comput 3:200–213
Papenberg N, Bruhn A, Brox T, Didas S, Weickert J (2006) Highly accurate optic flow computation with theoretically justified warping. Int J Comput Vis 67(2):141–158
Perona P, Malik J (1990) Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12:629–639
Rudin L, Osher S, Fatemi E (1992) Total variation based noise removal algorithms. Physica D 60:259–268
Song B (2003) Topics in variational PDE image segmentation, inpainting and denoising. University of California, Los Angeles
Weickert J (1999) Coherence-enhancing diffusion filtering. Int J Comput Vis 31:111–127
Weickert J (2001) Application of nonlinear diffusion in image processing and computer vision. Acta Math Univ Comenianae LXX:33–50
Zhang H, Peng Q (2006) Adaptive image denoising model based on total variation. Opto Electron Eng 33:50–53
Zontak M, Mosseri I, Irani M (2012) Separating signal from noise using patch recurrence arcoss scales. In: IEEE conference on computer vision and pattern recognition (CVPR)
Zuo W, Zhang L, Song C, Zhang D (2013) Texture enhanced image denoising via gradient histogram preservation. In: IEEE conference on computer vision and pattern recognition (CVPR). IEEE, New York, pp 1203–1210