Title :
Scalable image representation using improved retargeting pyramid
Author :
Tanaka, Yuichi ; Shirai, Keigo
Author_Institution :
Grad. Sch. of BASE, Tokyo Univ. of Agric. & Technol., Koganei, Japan
Abstract :
The retargeting pyramid (RP) method is a good alternative to the well-known Laplacian pyramid (LP) approach for multiscale image decomposition. RP can be obtained by replacing the low-pass filtering and downsampling processes in LP with content-aware image resizing (a.k.a. retargeting), which is a technique being developed in computer vision research. In this paper, we improve RP so that it obtains good scalable image representation. The improved RP is then integrated with a well-known multiscale-multidirection (MSMD) transform, contourlet transform, to construct a saliency-oriented MSMD image representation. In the experiment, our decomposition outperforms the conventional pyramid structures.
Keywords :
Laplace transforms; computer vision; image representation; LP approach; Laplacian pyramid approach; MSMD transform; computer vision; content-aware image resizing; contourlet transform; multiscale image decomposition; multiscale-multidirection transform; retargeting pyramid method; saliency-oriented MSMD image representation; scalable image representation; Cost function; Discrete wavelet transforms; Image processing; Interpolation; Laplace equations; Redundancy; Laplacian pyramid; Retargeting; content-aware image resizing; interpolation; retargeting pyramid;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
Conference_Location :
Vancouver, BC
DOI :
10.1109/ICASSP.2013.6638051
