/ プログラム/ 発表一覧/ 著者一覧/ 企業展示一覧/ jsai2013ホーム /

2H1-2 Text Localization in Scene Images by Using Character Energy and Maximally Stable Extremal Regions

*セッションの無断動画配信はご遠慮下さい。

Tweet #jsai2013 このエントリーをはてなブックマークに追加

06月05日(Wed) 09:00〜10:40 H会場(-市民プラザ3F AVスタジオ)
2H1 画像・音声「画像・音声」

演題番号2H1-2
題目Text Localization in Scene Images by Using Character Energy and Maximally Stable Extremal Regions
著者馬場 惇(京都大学大学院情報学研究科 知能情報学専攻)
山本 章博(京都大学 大学院情報学研究科)
時間06月05日(Wed) 09:20〜09:40
概要Text localization in scene images is a challenging problem, and a lot of methods have been proposed for ICDAR dataset. Character Energy is a naive feature developed by observing images of characters in previous researches. However, the accuracy obtained when Character Energy is used depends on the accuracy of closed boundary detection.
In this paper, we propose to combine using Character Energy and detecting MSERs. That is, we detect virtually unchanged regions with MSERs and compute Character Energy with the boundaries of detected regions. By using our proposal, we would properly extract text locations in scene images of ICDAR dataset.
論文PDFファイル