Saliency, Scale and Image Description



Abstract  Many computer vision problems can be considered to consist of two main tasks :the extraction of image content description and their subsequent matching.The appropriate choice of type and level of description is of course task dependent, yet it is generally accepted that the low-level or so-called early vision layers in the Human Visual System are context independent.

    This paper concentrates on the use of low-level approaches for solving computer vision problems and discusses three inter-related aspects of this :saliecny; scale selection and content description.In contrast to many previous approaches which separate these tasks, we argue that these three aspects are intrinsically related. Based on this observation, a multiscale algorithm for the selection of salient regions of an image is introduced and its application to matching type problems such as tracking, object recognition and image retrieval is demonstrated.

Keywords : visual saliency, scale selection, image content descriptors , feature extraction, salient features, image database, entropy, scale-space

摘要：许多计算机视觉问题能够被认为由两个主要任务组成：图像内容的提取描述和他们的后续匹配。适当的类型和描述级别的选择当然是任务相关的，尽管普遍承认了人体视觉系统中的低级或所谓的早期视觉层次是上下文无关的。

    这篇论文聚焦于低级方法的使用来解决计算机视觉问题并且讨论了桑内相关的方面：显著性，尺度选择，和内容描述。与之前把这些任务分开相比，我们认为，这三个方面在本质上是关联的。基于这个观察，为了一个图像显著性区域的选择，一个多尺度的算法被提出来了，并且它对于匹配类型的问题诸如跟踪，对象识别和图像检索的应用被证明了。