A Study Personal 2D Color Feature Image Interpolation

  • Jo, Nam-Chul (Graduate School of Computer Engineering, YeongNam University) ;
  • Ku, Ja-Hyo (Graduate School of Computer Engineering, YeongNam University) ;
  • Kim, Hwi-Won (Dept of Computer Science, KyungBuk College) ;
  • Lee, Ki-Dong (Dept. of Computer Engineering, YeungNam University)
  • Published : 2008.06.20

Abstract

Surveillance Cameras such as CCTV easily found in places requiring security and the prevention of crimes such as public institutions, banks, etc. play an important role as they prevent all sorts of crimes, and provide a decisive clue fix settling a criminal case. But, in case that a far-off person is photographed, an original image should be enlarged to identify the person. And as for the technique of enlarging an image, it is important to enlarge and restore it close to its original image rather than to merely magnify it. For the enlargement and restoration of an image, techniques called interpolation are used; as for interpolation methods known hitherto, however, the higher the magnifying power is, the more deteriorated the quality of an image becomes to the extent that the image cannot be identified. Therefore, in this paper, we are going to propose a new technique whereby the face outline in an image is vectorized and restored by means of FDP(Facial Definition Parameter) standardized by the MPEG-4 SNHC FBA group, and an image is restored to have better quality than images restored with the existing interpolation.

Keywords