Automatic Line Scratch Detection and Restoration in Films
Archa A. B1, Kumar G. S2

1Archa A. B, M.Tech. Student, SCT College of Engineering, Pappanamcode, Trivandrum (Kerala), India.
2Kumar G. S, Asst. Prof., SCT College of Engineering, Pappanamcode, Trivandrum (Kerala), India.

Manuscript received on 15 June 2015 | Revised Manuscript received on 25 June 2015 | Manuscript Published on 30 June 2015 | PP: 153-156 | Volume-4 Issue-5, June 2015 | Retrieval Number: E4117064515/15©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Line scratches are the most common defects in old films. They are caused by the abrasions of the film material as it passes through the projection mechanism. Once an image is digitized, its defects become part of that image .So scratch detection and removal is important subject for video restoration. This work presents a technique for detecting and removing these line artifacts .Using A Contrario line scratch detection, we detect and locate line scratches accurately, after that a new digital image inpainting algorithm based on directional median filter is used to remove these scratches. In Contrario line scratch detection method along with Spatial detection algorithm, a Temporal filtering algorithm is used for filtering false detections. As a result we can detect and remove original scratches. This work discuss about frame conversion from a digital video of specific length. Pre-process the frame in order to enhance image quality and then perform scratch detection and removal. Final video is once again formed from the processed frames. The overall system is developed in matlab and results are analyzed .Results shows that the proposed method can detect more line artifacts with less false detection and remove the line scratches effectively.
Keywords: Scratch Detection, A Contrario Method, Inpainting, Spatialdetection, Temporal Filtering Algorithm, Directional Median Filter, Video Restoration

Scope of the Article: Algorithm Engineering