Abstract

A fuzzy if-then rule-based intra-field deinterlacing method using geometric duality is presented in this paper. The proposed method is a content-based hybrid scheme switching between the well-known edge-based linear average method and the proposed geometric duality-based deinterlacing method. Conventional deinterlacing methods usually employ edge-based interpolation techniques within pixel-based estimations. However, they are somewhat sensitive to noise and intensity variations in the image. Moreover, their performance is visually unacceptable due to their failure to estimate edge direction. To reduce this sensitivity, the proposed algorithm investigates features from low-resolution images, and applies them to high-resolution images to calculate the missing pixels. We analyzed properties of the missing pixels and modeled them using geometric regularity. Depending on the features of the region, the missing pixels were interpolated in different ways. The proposed algorithm is computationally feasible and promises to be a good candidate for a low-cost hardware interpolator.

© 2010 IEEE

Fuzzy-rule-based image reconstruction for positron emission tomography

Partha P. Mondal and K. Rajan
J. Opt. Soc. Am. A 22(9) 1763-1771 (2005)

Optical generation of fuzzy-based rules

Eran Gur, David Mendlovic, and Zeev Zalevsky
Appl. Opt. 41(23) 4753-4761 (2002)

Application of fuzzy-rule-based postprocessing to correlation methods in pattern recognition

T. Wolf, B. Gutmann, H. Weber, J. Ferré-Borrull, S. Bosch, and S. Vallmitjana
Appl. Opt. 35(35) 6955-6963 (1996)

Fuzzy logic-based approach to wavelet denoising of 3D images produced by time-of-flight cameras

Ljubomir Jovanov, Aleksandra Pižurica, and Wilfried Philips
Opt. Express 18(22) 22651-22676 (2010)

Optical fuzzy systems based on efficient implementation of a fuzzy associative memory

Shuqun Zhang and Mohammad A. Karim
Opt. Lett. 23(4) 292-294 (1998)