A new edge dependent deinterlacing algorithm based on edge patterns
Min‐Gyu Park, Moon Gi Kang · 2005
In this paper, a new deinterlacing algorithm based on an edge dependent interpolation (EDI) considering horizontal and vertical edge patterns is proposed. Generally, EDI algorithms perform better visually than any other deinterlacing algorithm using one field. However, they produce unpleasant results due to their failure in estimating edge direction. In order to detect edge direction exactly, edge patterns are modeled as weight functions. Weight functions help the proposed algorithm to estimate the edge direction exactly. Experimental results indicate that the proposed algorithm outperforms conventional approaches.