Abstract
Old movies are often valuable historical records, but most of them progressively deteriorate in visual quality during the years, decreasing their usefulness. To avoid distortions in the unaffected parts of the image, first the locations of the blotches and scratches have to be detected before the restoration algorithm can be applied. This chapter proposes an algorithm based on rank ordered differences (ROD) that are calculated from the data of the current image flame, and the preceding and succeeding motion-compensated frame. The ROD detector presented in the chapter is a modified form of the signal-dependent rank ordered mean filter (SD-ROM) used for restoration of an impulse noise corrupted image. While the SD-ROM filter works exclusively in the spatial area of one image frame and is only able to remove one or two pixel wide distortions, the ROD filter is designed to work on image sequences. It is able to detect both thin scratches and blotches. The chapter also compares the new algorithm to existing detection algorithms in the form of probability plots and images indicating the correct, false, and missing detections.
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 callMore From: Time-Varying Image Processing and Moving Object Recognition, 4
Disclaimer: 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.
