Deep neural networks for recognizing online handwritten mathematical symbols
Hai Nguyen, Anh Duc Le, Masaki Nakagawa · 2015
This paper presents application of deep learning to recognize online handwritten mathematical symbols. Recently various deep learning architectures such as Convolution neural network (CNN), Deep neural network (DNN) and Long short term memory (LSTM) RNN have been applied to fields such as computer vision, speech recognition and natural language processing where they have been shown to produce state-of-the-art results on various tasks. In this paper, we apply max-out-based CNN and BLSTM to image patterns created from online patterns and to the original online patterns, respectively and combine them. We also compare them with traditional recognition methods which are MRF and MQDF by carrying out some experiments on CROHME database.