arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.15381cs.CV
收藏

标签还是信息:文本与客体共现的大规模实验研究

Label or Message: A Large-Scale Experimental Survey of Texts and Objects Co-Occurrence

Kyushu University(九州大学)

Koki Takeshita, Juntaro Shioyama, Seiichi Uchida

摘要:

我们的日常生活被文本信息所包围。随着场景文本检测器和识别器技术的飞速发展,文本信息的自动采集成为可能。本文的目的是进行一个大规模的调查,视觉对象(如书籍和汽车)和场景文本之间的共现与大型图像数据集和国家的最先进的场景文本检测器和识别器。特别是,我们专注于“标签”文本的功能,这是附加到对象的细节对象。通过分析对象和场景文本之间的共现,可以观察标签文本的统计数据,并了解场景文本如何有助于识别对象,反之亦然。

英文摘要:

Our daily life is surrounded by textual information. Nowadays, the automatic collection of textual information becomes possible owing to the drastic improvement of scene text detectors and recognizer. The purpose of this paper is to conduct a large-scale survey of co-occurrence between visual objects (such as book and car) and scene texts with a large image dataset and a state-of-the-art scene text detector and recognizer. Especially, we focus on the function of "label" texts, which are attached to objects for detailing the objects. By analyzing co-occurrence between objects and scene texts, it is possible to observe the statistics about the label texts and understand how the scene texts will be useful for recognizing the objects and vice versa.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑