High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Image Retargeting with Visual Attention Video Compression Using Saliency

Author(s):

Jamila Fathima. J. , SAVEETHA SCHOOL OF ENGINEERING; Devaraj. P., SAVEETHA SCHOOL OF ENGINEERING; Pooja. C., SAVEETHA SCHOOL OF ENGINEERING

Keywords:

Image Processing Tools, video compression, Visual saliency.

Abstract

In this paper we propose a method to compress video on image retargeting with visual attension based on using saliency maps. This method allows saliency to increase in high quality parts of the frame, and allows saliency to reduce in non-ROI (Region of Interest) parts. To retargeting the image first extract the saliency maps from the frame, then ROI part of an image assigned as higher pixels count which is salient map image and lower pixels are non-salient image region. We compare our method from existing system H.264/AVC rate distortion optimization (RDO) by introducing a saliency distortion term in the distortion metric to propose method JPEG 2000 and H.264/AVC-10 and verify that, at the cost of visual quality in non-salient image regions, this method achieves a major improvement of the visual quality of salient image regions.

Other Details

Paper ID: IJSRDV2I3615
Published in: Volume : 2, Issue : 3
Publication Date: 01/06/2014
Page(s): 1914-1916

Article Preview

Download Article