TY - JOUR
T1 - Variational denoising of partly textured images by spatially varying constraints
AU - Gilboa, Guy
AU - Sochen, Nir
AU - Zeevi, Yehoshua Y.
N1 - Funding Information:
Manuscript received September 28, 2004; revised September 5, 2005. G. Gilboa was supported in part by the National Science Foundation under Grants ITR ACI-0321917 and DMS-0312222 and in part by the National Institutes of Health under Contract P20 MH65166. N. Sochen was supported in part by MUSCLE, Multimedia Understanding through Semantics, Computation and Learning, a European Network of Excellence funded by the EC 6th Framework IST Programme; in part by the Israeli Ministry of Science; in part by the Israel Science Foundation; in part by the Tel-Aviv University fund; and in part by the Adams Center. Y. Zeevi was supported in part by the Ollendorf Minerva Center, in part by the Fund for the Promotion of Research at the Technion, and in part by the HASSIP Research Network program HPRN-CT-2002-00285, funded by the European Commission. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Stanley J. Reeves.
PY - 2006/8
Y1 - 2006/8
N2 - Denoising algorithms based on gradient dependent regularizers, such as nonlinear diffusion processes and total variation denoising, modify images towards piecewise constant functions. Although edge sharpness and location is well preserved, important information, encoded in image features like textures or certain details, is often compromised in the process of denoising. We propose a mechanism that better preserves fine scale features in such denoising processes. A basic pyramidal structure-texture decomposition of images is presented and analyzed. A first level of this pyramid is used to isolate the noise and the relevant texture components in order to compute spatially varying constraints based on local variance measures. A variational formulation with a spatially varying fidelity term controls the extent of denoising over image regions. Our results show visual improvement as well as an increase in the signal-to-noise ratio over scalar fidelity term processes. This type of processing can be used for a variety of tasks in partial differential equation-based image processing and computer vision, and is stable and meaningful from a mathematical viewpoint.
AB - Denoising algorithms based on gradient dependent regularizers, such as nonlinear diffusion processes and total variation denoising, modify images towards piecewise constant functions. Although edge sharpness and location is well preserved, important information, encoded in image features like textures or certain details, is often compromised in the process of denoising. We propose a mechanism that better preserves fine scale features in such denoising processes. A basic pyramidal structure-texture decomposition of images is presented and analyzed. A first level of this pyramid is used to isolate the noise and the relevant texture components in order to compute spatially varying constraints based on local variance measures. A variational formulation with a spatially varying fidelity term controls the extent of denoising over image regions. Our results show visual improvement as well as an increase in the signal-to-noise ratio over scalar fidelity term processes. This type of processing can be used for a variety of tasks in partial differential equation-based image processing and computer vision, and is stable and meaningful from a mathematical viewpoint.
KW - Image denoising
KW - Nonlinear diffusion
KW - Spatially varying fidelity term
KW - Texture processing
KW - Variational image processing
UR - http://www.scopus.com/inward/record.url?scp=33746217159&partnerID=8YFLogxK
U2 - 10.1109/TIP.2006.875247
DO - 10.1109/TIP.2006.875247
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:33746217159
SN - 1057-7149
VL - 15
SP - 2281
EP - 2289
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
IS - 8
ER -