Nearest neighbor value interpolation
In mathematics applied to computer graphics, nearest neighbor value interpolation is an advanced method of image interpolation.[1][2][3] This method uses the pixel value corresponding to the smallest absolute difference when a set of four known value pixels has no mode. Proposed by Olivier Rukundo in 2012 in his PhD dissertation,[4] the first work presented at the fourth International Workshop on Advanced Computational Intelligence,[5] was based only on the pixel value corresponding to the smallest absolute difference[6] to achieve high resolution and visually pleasant image. This approach was since upgraded to deal with a wider class of image interpolation artefacts which reduce the quality of image, and as a result, several future developments have emerged, drawing on various aspects of the pixel value corresponding to the smallest absolute difference.
References
- ^ "Getcited". Archived from the original on August 1, 2012. Retrieved May 1, 2012.
{{cite web}}: Unknown parameter|deadurl=ignored (|url-status=suggested) (help) - ^ "Nearest Neighbor Value Interpolation". International Journal of Advanced Computer Science and Applications. 3. 2012. arXiv:1211.1768. doi:10.14569/IJACSA.2012.030405.
- ^ "Copernicus". Archived from the original on December 15, 2013. Retrieved May 1, 2012.
{{cite web}}: Unknown parameter|deadurl=ignored (|url-status=suggested) (help) - ^ "China National Knowledge Infrastructure". Retrieved May 9, 2012.
- ^ "IWACI 2011". Archived from the original on August 3, 2012. Retrieved October 19, 2011.
{{cite web}}: Unknown parameter|deadurl=ignored (|url-status=suggested) (help) - ^ "MENDELEY". Retrieved February 2012.
{{cite web}}: Check date values in:|accessdate=(help)