A novel saliency measure using combined spatial redundancy and local appearance
A novel saliency measure using combined spatial redundancy and local appearance
复制标题
DOI：
--
复制
发表时间：
2013-03
期刊：
影响因子：
--
通讯作者：
A. Boudissa;J. Tan;Hyoungseop Kim;S. Ishikawa;Takashi Shinomiya
中科院分区：
文献类型：
--
作者：
A. Boudissa;J. Tan;Hyoungseop Kim;S. Ishikawa;Takashi Shinomiya
在本文中，我们提出了一种新的显著性检测方法。我们在这里提出的方法旨在综合图像中显着性的共同知识。我们用以下两个参数定义一个视觉显著区域；空间冗余及其局部外观。前者是它在图像中出现的概率，是对相关区域“稀有性”的量化，而后者定义了该区域包含多少信息，可以用熵来量化。通过将全局空间冗余度量和局部熵相结合，我们可以得到一种简单而鲁棒的度量方法。我们将其与Itti方法和谱残差方法进行了评价和比较，结果表明该方法的性能有了明显的提高。
In this paper, we present a novel approach to saliency detection. The method we propose here aims at synthesizing common knowledge of saliency in an image. We define a visually salient region with following two parameters; the spatial redundancy and its local appearance. The former is its probability of occurrence within the image, which is a quantification of the “rarity” of the concerned region, whereas the latter defines how much information is contained within the region, and it can be quantified using the entropy. By combining the global spatial redundancy measure and local entropy, we can achieve a simple, yet robust measure. We evaluated and compared it to Itti’s and the spectral residual methods, and it has shown a significant improvement of performance.