...
首页> 外文期刊>Cognitive Neurodynamics >Visual saliency: A biologically plausible contourlet-like frequency domain approach
【24h】

Visual saliency: A biologically plausible contourlet-like frequency domain approach

机译:视觉显着性:一种生物学上合理的轮廓波状频域方法

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       

摘要

In this paper we propose a fast frequency domain saliency detection method that is also biologically plausible, referred to as frequency domain divisive normalization (FDN). We show that the initial feature extraction stage, common to all spatial domain approaches, can be simplified to a Fourier transform with a contourlet-like grouping of coefficients, and saliency detection can be achieved in frequency domain. Specifically, we show that divisive normalization, a model of cortical surround inhibition, can be conducted in frequency domain. Since Fourier coefficients are global in space, we extend to this model by conducting piecewise FDN (PFDN) using overlapping local patches to provide better biological plausibility. Not only do FDN and PFDN outperform current state-of-the-art methods in eye fixation prediction, they are also faster. Speed and simplicity are advantages of our frequency domain approach, and its biological plausibility is the main contribution of our paper.
机译:在本文中,我们提出了一种快速的频域显着性检测方法,该方法在生物学上也是可行的,称为频域分割归一化(FDN)。我们表明,所有空间域方法共有的初始特征提取阶段可以简化为具有轮廓线状系数分组的傅立叶变换,并且可以在频域中实现显着性检测。具体来说,我们表明除法归一化,皮层周围抑制的模型,可以在频域中进行。由于傅立叶系数在空间上是全局的,因此我们通过使用重叠的局部斑块进行分段FDN(PFDN)来扩展此模型,以提供更好的生物学似真性。在眼球注视预测中,FDN和PFDN不仅超越了当前的最新技术,而且速度更快。速度和简单性是我们频域方法的优势,其生物学上的合理性是本文的主要贡献。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号