Inpainting with Refinement of Vicinity Patches using alpha trim filter for Heritage Sites
Pages : 226-233, DOI: https://doi.org/10.14741/ijcet/v.9.2.5
Download PDF
Abstract
Image processing and computer vision have been active areas of research and used in different applications. Few researchers have attempted the use of image processing techniques in the digital preservation of heritage sites. Heritage sites across the world are important sources of knowledge which introduce us to our cultural history, depicting the evolution of humankind. Digital reconstruction of ruined historic monuments and heritage sites can help in visualizing how these may have existed in the past. Also, such a process requires no physical alteration to the existing monuments. Inpainting is the process of restoring image contents imperceptibly. The contribution of this paper is patch based inpainting technique with standard deviation used as a parameter to find the pixel of highest priority. In the search strategy v vicinity patches in the neighborhood of the destination patch with center pixel of v belonging to the boundary of destination patch is used. The vicinity patches are searched merely by looking at the known and unknown pixels of the destination patch. Experimental results carried on a set of 90 images in comparison with standard techniques show improved performance.
Keywords: Inpainting, Image Reconstruction, Heritage Sites, Exemplar Based Inpainting, PSNR, SSIM, Quality Factor, Vicinity Patches.
Article published in International Journal of Current Engineering and Technology, Vol.9, No.2 (March/April 2019)