One of the fundamental challenges in the field of image processing and computer vision is image denoising, where the underlying goal is to estimate the original image by suppressing noise from a noise-contaminated version of the image. Image noise may be caused by different intrinsic (i.e., sensor) and extrinsic (i.e., environment) conditions which are often not possible to avoid in practical situations. Therefore, image denoising plays an important role in a wide range of applications such as image restoration, visual tracking, image registration, image segmentation, and image classification, where obtaining the original image content is crucial for strong performance. While many algorithms have been proposed for the purpose of image denoising, the problem of image noise suppression remains an open challenge, especially in situations where the images are acquired under poor conditions where the noise level is very high.
In the VIP lab, we investigate an alternative approach to the problem of image denoising based on data-adaptive stochastic optimization via Markov-Chain Monte Carlo sampling. By formulating the problem as a Bayesian optimization problem and taking a nonparametric stochastic strategy to solving this problem, such a Markov-Chain Monte Carlo denoising (MCMCD) strategy dynamically adapts to the underlying image and noise statistics in a flexible manner to provide high denoising performance while maintaining relatively low computational complexity.
Examples of the results produced using the MCMCD strategy are shown below:
Related people
Directors
Students
Alumni
Related research areas
Image Segmentation/Classification
Related publications
Xu L., Shafiee M.J., Wong A., and Clausi D.A, "Fully Connected Continuous Conditional Random Field with Stochastic Cliques for Dark-Spot Detection in SAR Imagery", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 9, pp. 2882-2890, 2016. Get it here. Xu L., Wong A., Li F., and Clausi D.A, "Intrinsic Representation of Hyperspectral Imagery for Unsupervised Feature Extraction", IEEE Transactions on Geoscience and Remote Sensing, vol. 54, pp. 1118-1130, 2016. Get it here. Li F., Xu L., Wong A., and Clausi D.A, "QMCTLS: Quasi Monte Carlo Texture Likelihood Sampling for Despeckling of Complex Polarimetric SAR Images", IEEE Geoscience and Remote Sensing Letters, vol. 12, pp. 1566-1570, 2015. Get it here. Xu L., Li F., Wong A., and Clausi D.A, "Hyperspectral Image Denoising Using a Spatial-Spectral Monte Carlo Sampling Approach", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 8, pp. 3025-3038, 2015. Get it here. Cameron A., Lui D., Boroomand A., Glaister J., Wong A., and Bizheva K, "Stochastic speckle noise compensation in optical coherence tomography using non-stationary spline-based speckle noise modelling", Biomedical Optics Express, vol. 4, pp. 1769-1785, 2013. Get it here. Lui D., Cameron A., Modhafar A., Cho D.S., and Wong A, "Low-dose computed tomography via spatially adaptive Monte-Carlo reconstruction", Computerized Medical Imaging and Graphics, vol. 37, pp. 438-449, 2013. Get it here. Wong A., and Scharcanski J, "Monte Carlo despeckling of transrectal ultrasound images of the prostate", Digital Signal Processing: A Review Journal, vol. 22, pp. 768-775, 2012. Get it here. Wong A., Mishra A., Zhang W., Fieguth P., and Clausi D.A, "Stochastic image denoising based on Markov-chain Monte Carlo sampling", Signal Processing, vol. 91, pp. 2112-2120, 2011. Get it here. Wong A., Mishra A., Bizheva K., and Clausi D.A, "General Bayesian estimation for speckle noise reduction in optical coherence tomography retinal imagery", Optics Express, vol. 18, pp. 8338-8352, 2010. Get it here.
Conference PapersLeigh A., Wong A., Clausi D.A., and Fieguth P, "Comprehensive analysis on the effects of noise estimation strategies on image noise artifact suppression performance", Proceedings - 2011 IEEE InternationalSymposium on Multimedia, ISM 2011, 2011. Get it here.