Performance analysis of retargeting pyramid and its applications
Performance analysis of retargeting pyramid and its applications
复制标题
DOI：
10.1109/icip.2015.7351184
复制
发表时间：
2015-12
期刊：
影响因子：
--
通讯作者：
Ryosuke Morita;K. Shirai;Yuichi Tanaka
中科院分区：
文献类型：
--
作者：
Ryosuke Morita;K. Shirai;Yuichi Tanaka
改进的重定向金字塔（iRP）是一种使用内容感知图像金字塔（也称为重定向）的多尺度图像金字塔。据报道，iRP在线性近似和去噪方面优于传统的金字塔。然而，迄今为止，其性能增益的原因还没有得到很好的讨论。在本文中，我们揭示了在iRP中的重定向作为重要区域的局部欠抽取滤波器，同时保持其全局下采样率。此外，我们的iRP被应用到各种图像处理应用程序，以验证其性能。
Improved retargeting pyramid (iRP) is a multiscale image pyramid using content-aware image resizing (also known as retargeting). It has been reported that the iRP outperforms conventional pyramids in linear approximation and denoising. However, the reason of its performance gain was not well discussed so far. In this paper, we reveal that retargeting in the iRP acts as locally underdecimated filters for significant region(s) while keeping its global downsampling ratio. Furthermore, our iRP is applied to various image processing applications to validate its performance.