Boosting saliency in color image features
Boosting saliency in color image features
复制标题
DOI：
10.1109/cvpr.2005.93
复制
发表时间：
2005-06
期刊：
影响因子：
--
通讯作者：
Joost van de Weijer;T. Gevers
中科院分区：
文献类型：
--
作者：
Joost van de Weijer;T. Gevers
显著点检测的目的是发现图像中的显著事件。显著特征通常从图像的局部差分结构确定。他们专注于局部邻域的形状显着性。这些检测器中的大多数是基于亮度的，其缺点是完全忽略了局部颜色信息的独特性。为了充分利用彩色图像显著点检测的可能性，除了形状特征外，还应考虑颜色特征。在本文中，显着性检测的设计中明确纳入颜色的独特性。该算法被称为颜色显着性提升，是基于彩色图像导数的统计分析。在颜色导数空间中，等凸颜色导数可以通过椭球面来近似。基于这一显著的统计发现，通过颜色提升来转换等显着导数，以对显着性具有相同的影响。颜色显著性增强被设计为一种通用方法，易于适应现有的特征检测器。结果表明，通过针对颜色显著特征，信息内容得到了实质性的改善。此外，通过将颜色提升应用于多个现有显著性方法来说明该方法的一般性。
The aim of salient point detection is to find distinctive events in images. Salient features are generally determined from the local differential structure of images. They focus on the shape saliency of the local neighborhood. The majority of these detectors is luminance based which has the disadvantage that the distinctiveness of the local color information is completely ignored. To fully exploit the possibilities of color image salient point detection, color distinctiveness should be taken into account next to shape distinctiveness. In this paper color distinctiveness is explicitly incorporated into the design of saliency detection. The algorithm, called color saliency boosting, is based on an analysis of the statistics of color image derivatives. Isosalient color derivatives can be closely approximated by ellipsoidal surfaces in color derivative space. Based on this remarkable statistical finding, isosalient derivatives are transformed by color boosting to have equal impact on the saliency. Color saliency boosting is designed as a generic method easily adaptable to existing feature detectors. Results show that substantial improvements in information content are acquired by targeting color salient features. Further, the generality of the method is illustrated by applying color boosting to multiple existing saliency methods.