Abstract
A detection and tracking approach is proposed for line scratch removal in a digital film restoration process. Unlike random im- pulsive distortions such as dirt spots, line scratch artifacts persist across several frames. Hence, motion compensated methods will fail, as well as single-frame methods if scratches are unsteady or fragmented. The proposed method uses as input pro jections of each image of the in- put sequence. First, a 1D-extrema detector provides candidates. Next, a MHT (Multiple Hypothesis Tracker) uses these candidates to create and keep multiple hypothesis. As the tracking goes further through the sequence, each hypothesis gains or looses evidence. To avoid a combina- torial explosion, the hypothesis tree is sequentially pruned, preserving a list of the best ones. An energy function (quality of the candidates, comparison to a model) is used for the path hypothesis sorting. As hy- pothesis are set up at each iteration, even if no information is available, a tracked path might cross gaps (missed detection or speckled scratches). At last, the tracking stage feeds the correction process. Since this con- tribution focus on the detection stage, only tracking results are given.