APSIPA Transactions on Signal and Information Processing > Vol 2 > Issue 1

Rate-dependent seam carving and its application to content-aware image coding

Yuichi Tanaka, Graduate School of Engineering, Utsunomiya University, Japan AND Graduate School of BASE, Tokyo University of Agriculture and Technology, Japan, ytnk@cc.tuat.ac.jp , Taichi Yoshida, Keio University, Japan, Madoka Hasegawa, Graduate School of Engineering, Utsunomiya University, Japan, Shigeo Kato, Graduate School of Engineering, Utsunomiya University, Japan, Masaaki Ikehara, Keio University, Japan
 
Suggested Citation
Yuichi Tanaka, Taichi Yoshida, Madoka Hasegawa, Shigeo Kato and Masaaki Ikehara (2013), "Rate-dependent seam carving and its application to content-aware image coding", APSIPA Transactions on Signal and Information Processing: Vol. 2: No. 1, e1. http://dx.doi.org/10.1017/ATSIP.2013.3

Publication Date: 27 Feb 2013
© 2013 Yuichi Tanaka, Taichi Yoshida, Madoka Hasegawa, Shigeo Kato and Masaaki Ikehara
 
Subjects
 
Keywords
Content-aware image codingContent-aware image resizingImage retargetingImage codingWaveletSPIHT
 

Share

Open Access

This is published under the terms of the Creative Commons Attribution licence.

Downloaded: 1063 times

In this article:
I. Introduction 
II Review 
III. RD-SC with Piecewise Approximation 
IV. Wavelet-Based CAIC 
V. Experimental results 
VI. Conclusions 

Abstract

Content-aware image resizing (CAIR) is desired because it preserves prominent regions in a resized image. However, CAIR requires high computational complexity to perform in mobile devices, though it is desired for these displays. Moreover, transmitting the side information for CAIR from the encoder is a problem since it usually requires high bitrates compared with those for image data. In this paper, we present a rate-dependent CAIR method that produce various retargeting results based on the bitrates for side information. Furthermore, we apply the proposed technique to wavelet-based image coding. Our proposed content-aware image coding method provides good performances for both CAIR and image coding.

DOI:10.1017/ATSIP.2013.3