Title: Multi structure morphological inpainting for the recovery of damaged digitised photographs

Authors: D. Jemi Florinabel; S. Ebenezer Juliet; V. Sadasivam

Addresses: Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Tirunelveli 627 012, Tamilnadu, India ' Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Tirunelveli 627 012, Tamilnadu, India ' Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Tirunelveli 627 012, Tamilnadu, India

Abstract: Multi structure morphological inpainting for the recovery of damaged digitised photographs is proposed. The motivation behind this paper is to address this interesting application area in terms of morphological image processing literature and evaluate the interpolation capabilities of the same in the context of inpainting. As the inpainting order plays an important factor for human visualisation it is guided by the orientation of edges at the surrounding known regions of the missing domain. The damaged picture is edge detected by morphological gradient algorithm based on multi-structure element morphology of eight different directions. The edge detected image is represented as eight different edge planes based on the orientation of the edges. This edge plane information is used for reconstructing the regions within the missing part in a particular orientation, as well as for guiding the integration that follows. Edge planes having edges at the boundary of the missing domain are known as positive response edge planes. The damaged regions are morphologically eroded using the structuring elements of corresponding orientations given by the positive response edge planes. The resultant image is obtained using texture synthesis incorporated isotope driven integration of the eroded images. The novelty of our approach is to explicitly specify the direction of filling herby ensuring ease in convergence in different orientations and then streamlining the integration process to guarantee complete and natural look.

Keywords: inpainting order; morphological gradient; multi-structure elements; morphological erosion; texture synthesis; morphological inpainting; photograph recovery; damaged photographs; digitised photographs; edge detection; eroded images; filling direction; reconstruction.

DOI: 10.1504/IJSISE.2014.060059

International Journal of Signal and Imaging Systems Engineering, 2014 Vol.7 No.2, pp.92 - 103

Received: 16 Apr 2011
Accepted: 23 Apr 2012
Published online: 27 Oct 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article