Improvement of Modified Edge-Based Line Average Algorithm via Fuzzy Logic System
Gwanggil Jeon, Hyun‐Woo Lee, Jun-Ho Won, Youngsub Jo, Jechang Jeong · ICEIC : International Conference on Electronics, Informations and Communications · 2008
This article presents a new algorithm for spatial deinterlacing that could easily be integrated in a more complete deinterlacing system. We review modified edgebased line average algorithm, and improve it by utilizing fuzzy theory. The employed fuzzy concepts are utilized to design a weight-measuring technique. We propose the measuring criteria of significance of edge direction field. To calculate accurate weight we employ fuzzy concepts. The weights are considered to be multiplied by the candidate deinterlaced pixels. The proposed algorithm yields good visual results in various kinds of horizontal, narrow, and weak edges. Experimental results on various data sets demonstrate that the proposed fuzzy rule based modified ELA method works well the diverse kinds of sequences and reconstructs flicker-free details in the motion region.