講演抄録/キーワード |
講演名 |
2014-11-18 15:00
[ポスター講演]Combination of LSTM and CNN on recognizing mathematical symbols ○Hai Nguyen Dai・Anh Le Duc・Masaki Nakagawa(TUAT) IBISML2014-73 |
抄録 |
(和) |
(事前公開アブストラクト) combining classifiers is an approach that has been shown to be useful on numerous occasions when striving for further improvement over the performance of individual classifiers. In this paper we present a system that is a combination of CNN and LSTM which are good classifiers for offline and online handwriting mathematical character recognition respectively. The best combination ensemble has a recognition rate which is significantly higher than the rate achieved by the best individual classifier on database CROHME 2013. |
(英) |
Combining classifiers is an approach that has been shown to be useful on numerous occasions when striving for further improvement over the performance of individual classifiers. In this paper we present a combination of CNN and LSTM, which are both sophisticated neural networks and good classifiers for offline and online handwriting mathematical character recognition respectively. In addition, we employ the dropout technique and gradient based local features to improve accuracy of CNN and LSTM, respectively. The best combination ensemble has a recognition rate which is significantly higher than the rate achieved by the best individual classifier on database MathBrush |
キーワード |
(和) |
/ / / / / / / |
(英) |
Convolutional Neural Network / LSTM / DropOut / Shape Context Feature / Directional Feature / / / |
文献情報 |
信学技報, vol. 114, no. 306, IBISML2014-73, pp. 287-292, 2014年11月. |
資料番号 |
IBISML2014-73 |
発行日 |
2014-11-10 (IBISML) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
IBISML2014-73 |