Loading...

A modified patch propagation-based image inpainting using patch sparsity

Hesabi, S ; Sharif University of Technology | 2012

589 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/AISP.2012.6313715
  3. Publisher: 2012
  4. Abstract:
  5. We present a modified examplar-based inpainting method in the framework of patch sparsity. In the examplar-based algorithms, the unknown blocks of target region are inpainted by the most similar blocks extracted from the source region, with the available information. Defining a priority term to decide the filling order of missing pixels ensures the connectivity of object boundaries. In the exemplar-based patch sparsity approaches, a sparse representation of missing pixels was considered to define a new priority term. Here, we modify this representation of the priority term and take measures to compute the similarities between fill-front and candidate patches. Comparative reconstructed test images show the effectiveness of our proposed approach in providing high quality inpainted images
  6. Keywords:
  7. Image inpainting ; High quality ; Inpainting method ; Object boundaries ; patch sparsity ; Source region ; Sparse representation ; Target regions ; Test images ; Texture synthesis ; Artificial intelligence ; Pixels ; Image processing
  8. Source: AISP 2012 - 16th CSI International Symposium on Artificial Intelligence and Signal Processing ; 2012 , Pages 43-48 ; 9781467314794 (ISBN)
  9. URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6313715