본문 바로가기
  • Home

An ROI Coding Technique of JPEG2000 Image Including Some Arbitrary ROI

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2010, 15(11), pp.31-39
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

홍석원 1 KimSangBok 1 Seo Yeong Geon 1

1경상대학교

Accredited

ABSTRACT

In some image processing system or the users who want to see a specific region of image simply, if a part of the image has higher quality than other regions, it would be a nice service. Specifically in mobile environments, preferential service was needed, as the screen size is small. So, JPEG2000 supplies this function. But this doesn't support the process to extract specific regions or service and does the functions to add some techniques. It is called by ROI(Region-of-Interest). In this paper, we use images including human faces, which are processed most preferentially and compressed with high quality. Before an image is served to the users, it is compressed and saved. Here, the face parts are compressed with higher quality than the background which are relatively with lower quality. This technique can offer better service with preferential transferring of the faces, too. Besides, whole regions of the image are compressed with same quality and after searching the faces, they can be preferentially transferred. In this paper, we use a face extraction approach based on neural network and the preferential processing with EBCOT of JPEG2000. For experimentation, we use images having several human faces and evaluate objectively and subjectively, and proved that this approach is a nice one.

Citation status

* References for papers published after 2023 are currently being built.