UPRE method for total variation parameter selection

Journal Article · Tue Jan 01 04:00:00 EST 2008 · IEEE Signal Processing Letter

OSTI ID:957756

Wohlberg, Brendt ^[1]; Lin, Youzuo ^[1]

---

1. Los Alamos National Laboratory

Total Variation (TV) Regularization is an important method for solving a wide variety of inverse problems in image processing. In order to optimize the reconstructed image, it is important to choose the optimal regularization parameter. The Unbiased Predictive Risk Estimator (UPRE) has been shown to give a very good estimate of this parameter for Tikhonov Regularization. In this paper we propose an approach to extend UPRE method to the TV problem. However, applying the extended UPRE is impractical in the case of inverse problems such as de blurring, due to the large scale of the associated linear problem. We also propose an approach to reducing the large scale problem to a small problem, significantly reducing computational requirements while providing a good approximation to the original problem.

• Research Organization: Los Alamos National Laboratory (LANL)
• Sponsoring Organization: DOE
• DOE Contract Number: AC52-06NA25396
• OSTI ID: 957756
• Report Number(s): LA-UR-08-04485; LA-UR-08-4485
• Journal Information: IEEE Signal Processing Letter, Journal Name: IEEE Signal Processing Letter
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
APPROXIMATIONS
IMAGE PROCESSING
LANL