6533b873fe1ef96bd12d4a7d

RESEARCH PRODUCT

Vertical scratches detection based on edge detection for old film

Zhang HongyingNie Shi-liangZhang LipingVincent BrostFan Yang

subject

Computer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONInpaintingSobel operatorVertical barEdge detectionImage (mathematics)Operator (computer programming)Canny edge detectorComputer visionArtificial intelligencebusinessImage restorationMathematicsofComputing_DISCRETEMATHEMATICS

description

Automatic detection of image damaged regions is the key to automatic video image inpainting. Vertical scratches are the common damages in the old film. In this paper, a vertical scratches detection algorithm based on edge detection is proposed. The proposed algorithm first uses the operator which has the largest response to the vertical edge in Sobel operator to detect edges, and then uses canny operator to detect edges further. Third, we detect vertical lines in the image through probabilistic Hough transform. Finally, we obtain the true locations of the vertical lines scratches through morphology and width constraints. Many experiments show that our method can detect vertical line scratches effectively in heavily-degraded film sequences.

https://doi.org/10.1109/indusis.2010.5565861