Pixel similarity based Betacam dropout detection of degraded archived media in instant QC system

Structural pattern‐based approach for Betacam dropout detection in degraded archived media

“…Ahn et al [13] proposed a spatial frame partitioning‐based Betacam dropout detection approach. The method solely depends on pixel similarity in both the horizontal and vertical directions of a single frame for defect detection.…”

“…In contrast, since our method does not depend on temporal information, it performs the best for consecutive error frames. For the Single video group, where there is no successive error frame [22] and the proposed method perform better compared to [13]. More qualitative results are shown in Fig.…”

“…For the curtain‐like vertical pattern, all frames of Fig. 10 are detected as degraded frames by the Betacam dropout detector in [13] since the method only considers the vertical and horizontal neighbourhood similarity in terms of intensity. However, our proposed method successfully ignores it as a normal frame.…”

“…However, our proposed method successfully ignores it as a normal frame. The method in [13] generates a very large number of false alarms (poor TNR in Fig. 12) since the method only relies on the neighbourhood pixel's similarity.…”

“…Moreover, Kokaram's system often falls short in responding to the errors occurring in consecutive frames at the same position. It also shows shortcomings in detecting some other major errors, such as blotches, digital dropout, Betacam dropout, blockiness etc., as discussed in [8–13].…”