Temporal series recognition using a new neural network structure T-CombNET

Author

Lamar, Marcus V. ; Bhuiyan, Md Shoaib ; Iwata, Akira

Author_Institution

Dept. of Electr. & Comput. Eng., Nagoya Inst. of Technol., Japan

Volume

3

fYear

1999

fDate

1999

Firstpage

1112

Abstract

We present a new neural network structure dedicated to the temporal data series recognition, called T-CombNET (Temporal CombNET). The T-CombNET is a modified and improved version of the CombNET-II structure, which was designed to deal with very large vocabulary character recognition. We incorporated a time normalization stage and used recurrent neural networks to enable CombNET-II to do the temporal analysis. Then we applied this new model T-CombNET to the hand gesture recognition task. The preliminary results show that the proposed structure is very efficient, obtaining a recognition rate of 99.41% in visual based kana hand alphabet recognition experiments

Keywords

gesture recognition; neural net architecture; recurrent neural nets; temporal reasoning; T-CombNET; Temporal CombNET; experiments; hand gesture recognition; kana hand alphabet recognition; large vocabulary character recognition; neural network structure; recurrent neural networks; temporal data series recognition; time normalization; Automata; Character recognition; Computer networks; Data mining; Hidden Markov models; Information processing; Neural networks; Pattern recognition; Recurrent neural networks; Weather forecasting;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on

Conference_Location

Perth, WA

Print_ISBN

0-7803-5871-6

Type

conf

DOI

10.1109/ICONIP.1999.844691

Filename

844691