NIST logo

Publication Citation: PYRAMID MODEL BASED DOWN-SAMPLING FOR IMAGE INPAINTING

NIST Authors in Bold

Author(s): Hamid Gharavi;
Title: PYRAMID MODEL BASED DOWN-SAMPLING FOR IMAGE INPAINTING
Published: September 02, 2010
Abstract: Image inpainting is a useful and powerful technique for automatically restoring or removing objects in films and damaged pictures. In the last ten years, many excellent inpainting algorithms have been proposed after Bertalmio et al. [1]. However, no paper systematically and theoretically analyzes the factors, which limit the performances of existing algorithms. Based on extensive experiments, we firstly construct a universal framework for image inpainting, which contains three crucial factors Area, Shape, and Perimeter (ASP). Then we propose a Pyramid model based own-sampling Inpainting (PDI) model according to the ASP principles. Experimental results show that the performances of existing methods can be tremendously improved after incorporating the PDI model.
Proceedings: IEEE 2010 International Conference on Image Processing
Pages: pp. 429 - 432
Location: Hong Kong, -1
Dates: September 26-29, 2010
Keywords: Image inpainting; Pyramid model; Downsampling
Research Areas: Information Technology, Information Delivery Systems, Imaging
PDF version: PDF Document Click here to retrieve PDF version of paper (1MB)