论文标题

用户研究旨在调查www图像的语义相关上下文信息

A User Study to Investigate Semantically Relevant Contextual Information of WWW Images

论文作者

Fauzi, Fariza, Belkhatir, Mohammed

论文摘要

研究了Web图像的上下文信息,以解决用语义描述符丰富其索引特征的问题,因此弥合语义差距(即基于低级内容的图像描述及其语义解释之间的差距)。尽管我们受到网络上丰富知识的可用性以及商业搜索引擎在网页中使用周围基于文本的信息索引图像所取得的相对成功的激励,但我们知道周围文本的不可预测质量是主要限制因素。为了提高其质量,我们重点介绍了与Web图像的语义表征相关的上下文信息,并根据其位置和性质研究其统计属性,并考虑将分类分为五个语义概念类别:信号,对象,场景,抽象和关系。进行用户研究以验证结果。结果表明,有几个位置始终包含与图像有关的相关文本信息。每个位置的重要性都受网页类型的影响,因为结果显示了不同网页类型的相关上下文信息的不同分布。经常发现的语义概念类是对象和抽象。用户研究的另一个重要结果表明,网页不是原子单元,可以进一步分为较小的细分市场。包含图像的片段很有趣,并称为图像段。我们观察到,用户通常会从图像段中界定的文本信息中挑出与图像相关的文本信息。

The contextual information of Web images is investigated to address the issue of enriching their index characterizations with semantic descriptors and therefore bridge the semantic gap (i.e. the gap between the low-level content-based description of images and their semantic interpretation). Although we are highly motivated by the availability of rich knowledge on the Web and the relative success achieved by commercial search engines in indexing images using surrounding text-based information in webpages, we are aware that the unpredictable quality of the surrounding text is a major limiting factor. In order to improve its quality, we highlight contextual information which is relevant for the semantic characterization of Web images and study its statistical properties in terms of its location and nature considering a classification into five semantic concept classes: signal, object, scene, abstract and relational. A user study is conducted to validate the results. The results suggest that there are several locations that consistently contain relevant textual information with respect to the image. The importance of each location is influenced by the type of webpage as the results show the different distribution of relevant contextual information across the locations for different webpage types. The frequently found semantic concept classes are object and abstract. Another important outcome of the user study shows that a webpage is not an atomic unit and can be further partitioned into smaller segments. Segments containing images are of interest and termed as image segments. We observe that users typically single out textual information which they consider relevant to the image from the textual information bounded within the image segment.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源