I. Introduction
Deinterlacing converts each field into a frame, so the number of pictures per second remains constant, while the number of lines per picture is doubled [1]. However, an interlaced TV signal in the vertical direction does not satisfy the demands of Nyquist sampling theory. Effective linear sampling rate conversion theory cannot be employed for interpolation. This causes different visual artifacts, such as twitter artifacts, flicker artifacts, and unwanted staircase effects, which decrease the picture quality of the interlaced video sequence [2]. In order to resolve these issues, deinterlacing methods have been investigated by many authors and various methods have been proposed with different degrees of complexity and qualities of reconstruction [3]–[7].