Retargeting framework based on monte-carlo sampling
- Autori: Gallea, R.; Ardizzone, E.; Pirrone, R.
- Anno di pubblicazione: 2015
- Tipologia: Capitolo o Saggio (Capitolo o saggio)
- Parole Chiave: Image resizing; Monte-carlo; Retargeting; Saliency; Computer Science (all)
Advance in image technology and proliferation of acquisition devices like smartphones, digital cameras, etc., made the display of digital images ubiquitous. Many displays exist in the market, spanning within a large variety of resolutions and shapes. Thus, displaying content optimizing the available number of pixels has become a very important issue in the multimedia community, and the image retargeting problem is being widely faced. In this work, we propose an image retargeting framework based on monte-carlo sampling. We operate the non-homogeneous resizing as the composition of several simple atomic resizing functions. The shape of such atomic operator can be chosen within a set of tested functions or the user could design additional ones. Using independent atomic operators allows parallelizing the retargeting procedure. Additionally, since the algorithm does not require any optimization, it could be executed in real-time, which is a key aspect for on-line visualization of multimedia content.