Trainable blotch detection on high resolution archive films minimizing the human interaction

Film archives are continuously in need of automatic restoration tools to accelerate the correction of film artifacts and to decrease the costs. Blotches are a common type of film degradation and their correction needs a lot of manual interaction in traditional systems due to high false detection rates and the huge amount of data of high resolution images. Blotch detectors need reliable motion estimation to avoid the false detection of uncorrupted regions. In case of erroneous detection, usually an operator has to remove the false alarms manually, which significantly decreases the efficiency of the restoration process. To reduce manual intervention, we developed a two-step false alarm reduction technique including pixel- and object-based methods as post-processing. The proposed pixel-based algorithm compensates motion, decreasing false alarms at low computational cost, while the following object based method further reduces the residual false alarms by machine learning techniques. We introduced a new quality metric for detection methods by measuring the required amount of manual work after the automatic detection. In our novel evaluation technique, the ground truth is collected from digitized archive sequences where defective pixel positions are detected in an interactive process.