著作: [松本 和幸]/Fujisawa Akira/[吉田 稔]/[北 研二]/ASCII Art Classification based on Deep Neural Networks Using Image Feature of Characters/[Journal of Software]
ヘルプを読む
「著作」(著作(著書,論文,レター,国際会議など))は,研究業績にかかる著作(著書,論文,レター,国際会議など)を登録するテーブルです. (この情報が属するテーブルの詳細な定義を見る)
- 項目名の部分にマウスカーソルを置いて少し待つと,項目の簡単な説明がツールチップ表示されます.
種別 | 必須 | 学術論文(審査論文) | |||
---|---|---|---|---|---|
言語 | 必須 | 英語 | |||
招待 | 推奨 | ||||
審査 | 推奨 | Peer Review | |||
カテゴリ | 推奨 | 研究 | |||
共著種別 | 推奨 | 国内共著(徳島大学内研究者と国内(学外)研究者との共同研究 (国外研究者を含まない)) | |||
学究種別 | 推奨 | ||||
組織 | 推奨 | ||||
著者 | 必須 | ||||
題名 | 必須 |
(英) ASCII Art Classification based on Deep Neural Networks Using Image Feature of Characters |
|||
副題 | 任意 | ||||
要約 | 任意 |
(英) In recent years, a lot of non-verbal expressions have been used on social media. Ascii art (AA) is an expression using characters with visual technique. In this paper, we set up an experiment to classify AA pictures by using character features and image features. We try to clarify which feature is more effective for a method to classify AA pictures. We proposed four methods: 1) a method based on character frequency, 2) a method based on character importance value and 3) a method based on image features and 4) a method based on image features of characters. We trained neural networks by using these four features. In the experimental result, the best classification accuracy was obtained in the feed forward neural networks that used image features of characters. |
|||
キーワード | 推奨 |
|
|||
発行所 | 推奨 | ||||
誌名 | 必須 |
Journal of Software(Academy Publisher)
(pISSN: 1796-217X)
|
|||
巻 | 必須 | 13 | |||
号 | 必須 | 10 | |||
頁 | 必須 | 559 572 | |||
都市 | 任意 | ||||
年月日 | 必須 | 2018年 10月 初日 | |||
URL | 任意 | http://www.jsoftware.us/index.php?m=content&c=index&a=show&catid=199&id=2901 | |||
DOI | 任意 | 10.17706/jsw.13.10.559-572 (→Scopusで検索) | |||
PMID | 任意 | ||||
CRID | 任意 | ||||
WOS | 任意 | ||||
Scopus | 任意 | ||||
評価値 | 任意 | ||||
被引用数 | 任意 | ||||
指導教員 | 推奨 | ||||
備考 | 任意 |