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

Abstract

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.

Features Based Spatial and Temporal Blotch Detection for Archive Video Restoration

“…Its interior (inside a blotch area) shows less variance and contrast (i.e., difference of minimal and maximal intensities) than its exterior (outside a blotch area) [11,22]. There also exists a big difference between internal and external mean values [22]. Most of blotches usually have relative sharper edges on their borders.…”

“…On the other hand, techniques without motion-compensation cannot use the blotch temporal intensity discontinuity and also fail when such blotches exceed the filter size. Consequently some people recently developed schemes to combine the different approaches together in order to achieve more accurate blotch detection [21][22][23][24].…”

Detection of dirt impairments from archived film sequences: survey and evaluations

“…In addition, recent progress using combined schemes in archive restoration for scratch detection and concealment can be found in [52,53,54], and reported work on detection of blotches including both dirt and sparkles can be found in [55][56][57]59]. In general, scratch and blotch are significantly different from film dirt.…”

Blotch Detection in Archive Films Based on Visual Saliency Map

“…However, manual restoration of a video sequence having a lot of degradations is difficult. erefore, semiautomatic restoration techniques are generally preferred [8]. e restoration of blotches is carried out in two steps.…”