Content-aware image resizing techniques have become more important with the development of device technology. Although the seam carving method produces high-quality resized images, it requires high computational complexity. In this paper, we propose a novel content-aware image resizing technique that performs the seam carving method in the wavelet transform domain. This approach reduces the computational complexity of image resizing. To avoid breaking the spatial continuity of an image, we reduce the image width by scaling the seam width down instead of carving it out. In addition, the decomposition level is decreased adaptively to avoid distortion. We demonstrate how our method is faster than the seam carving method at producing resized images that retain the important regions.
抄録全体を表示