Multi structure morphological inpainting for the recovery of damaged digitised photographs
by D. Jemi Florinabel; S. Ebenezer Juliet; V. Sadasivam
International Journal of Signal and Imaging Systems Engineering (IJSISE), Vol. 7, No. 2, 2014

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.

Online publication date: Mon, 27-Oct-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Signal and Imaging Systems Engineering (IJSISE):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com