What does scene text tell us?

Seiichi Uchida, Yuto Shinahara

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

抄録

Scene text is one of the most important information sources for our daily life because it has particular functions such as disambiguation and navigation. In contrast, ordinary document text has no such function. Consequently, it is natural to have a hypothesis that scene text and document text have different characteristics. This paper tries to prove this hypothesis by semantic analysis of texts by word2vec, which is a neural network model to give a vector representation of each word. By the vector representation, we can have the semantic distributions of scene text and document text in Euclidean space and then determine their semantic categories by simple clustering. Experimental study reveals several differences between scene text and document text. For example, it is found that scene text is a semantic subset of document text and several semantic categories are very specific to scene text.

本文言語英語
ホスト出版物のタイトル2016 23rd International Conference on Pattern Recognition, ICPR 2016
出版社Institute of Electrical and Electronics Engineers Inc.
ページ4047-4052
ページ数6
ISBN(電子版)9781509048472
DOI
出版ステータス出版済み - 1 1 2016
イベント23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, メキシコ
継続期間: 12 4 201612 8 2016

出版物シリーズ

名前Proceedings - International Conference on Pattern Recognition
0
ISSN(印刷版)1051-4651

その他

その他23rd International Conference on Pattern Recognition, ICPR 2016
Countryメキシコ
CityCancun
Period12/4/1612/8/16

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

フィンガープリント 「What does scene text tell us?」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル