针对图像自适应显示的视觉注意力模型

A Visual Attention Model for Image Adaptation

图像在移动设备上的使用越来越广泛,但是各种不同的显示环境需要对图像进行自适应的显示,针对这个问题作者提出了基于视觉注意力的图像自适应显示的方法,而其基础是针对图像视觉注意力的建模。该文提出了一种有效地描述视觉注意力的模型,区别于把图像作为一个整体进行考虑的方法,把图像分解成一系列的注意力对象,并通过对视觉注意力对象的尺寸估计、区域约束分割、基于区域的显著度计算等步骤确定注意力对象的属性。实验结果证明了该模型的有效性。

Images have become more and more common in mobile communications. However, a crucial challenge is to provide adaptive displays on limited and heterogeneous screen sizes of mobile devices. To hurdle this problem, we proposed the solution of attention - based image adaptation, which is based on the visual attention modeling. In this paper, an effective attention model is proposed. Instead of treating an image as a whole, we decompose it into a series of Attention Objects ( AOs) and determine the attributions of each AO by the approaches of size estimation, constraint segmentation and region - based saliency extraction. The experiment results demonstrate its effectiveness.