Abstract
This paper presents a new missing data detection algorithm that is robust to pathological motion (PM). PM causes clean image data to be misdiagnosed as missing data, resulting in damage to the image during restoration. The proposed algorithm uses a probabilistic framework to jointly detect PM and missing data. It builds on an existing technique of using five frames for detection instead of the standard three frames. This allows the temporally impulsive intensity profile of blotches to be distinguished from the quasiperiodic profile of PM. Another diagnostic for PM is defined on the motion fields of the five-frame window. This follows the observation that PM results in motion fields which are not smooth. A ground truth comparison with standard missing data detectors shows that the proposed algorithm dramatically reduces the number of falsely detected missing data regions. It is also shown to reduce image damage during missing data treatment.
Highlights
Missing data treatment is an important process in the digital restoration of archived media
Most blotch detection algorithms are derived from the assumption that if a blotch is present at a particular location in a frame, no blotches are present at the same point in neighbouring frames
Examples of detectors using a three-frame window include the deterministic spike detection index (SDI) [1, 2] and rank order distance (ROD) [3, 4] detectors, which apply deterministic thresholds to the displaced frame difference (DFD) to detect discontinuities, and the probabilistic Morris [2, 5] and blotch Markov random field (MRF) [6] algorithms, which allow for the inclusion of prior knowledge of the result into the decision
Summary
Missing data treatment is an important process in the digital restoration of archived media. The state-of-the art motion estimators can robustly estimate the most common motion patterns, there are complex motion patterns which cannot be estimated accurately This complex motion is referred to as pathological motion (PM) and can lead to true image data being detected as a blotch (see Figure 1). The algorithm is made more robust by preventing PM regions being detected as blotches, thereby preventing damage to image data during restoration of dirty sequences. A five-frame window is used instead of the standard three frames This allows blotches to be distinguished from long term forms of PM, since blotches have a temporally impulsive intensity profile and PM often causes the intensity to vary in a periodic manner (see Figure 2). The paper concludes with a discussion of the algorithm, outlining areas for future development
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
