Designing Takagi-Sugeno fuzzy model-based motion adaptive deinterlacing system

Abstract

This paper proposes a novel interpolation algorithm based on the Takagi-Sugeno (TS) fuzzy model, which uses fuzzy direction-oriented interpolation (FDOI). The proposed algorithm can choose the most suitable deinterlacing methods for interpolation of a missing pixel by using an area classifier that classifies the content of a frame into three different categories. The proposed FDOI utilizes fuzzy theory to find the most accurate edge direction in which to interpolate missing pixels. The shape of the membership functions used in fuzzy logic are designed adaptively according to the parameters. Detection and interpolation results are presented. The results of computer simulations show that the proposed method outperforms a number of methods in the literature.