Text recognition using deep BLSTM networks
Citations
230 citations
Cites methods from "Text recognition using deep BLSTM n..."
...However [18] demonstrated that a Deep Bidirectional Long Short Term Memory based RNN (BLSTM-RNN) can be used which provides promising results for text recognition....
[...]
222 citations
Cites methods from "Text recognition using deep BLSTM n..."
...[26,27], etc, that have achieved higher accuracies than the presently proposed method....
[...]
117 citations
Cites methods from "Text recognition using deep BLSTM n..."
...This model consists of a forward and backward LSTM to extract temporal features in two directions; hence, it can effectively capture the periodicity and regularity of ridership data [33]....
[...]
99 citations
88 citations
References
241 citations
"Text recognition using deep BLSTM n..." refers methods in this paper
...[15] used 95,338 lines for training and 1,020 for test in case of printed English text to obtain an error of 0....
[...]
...LSTM has been used for the recognition of printed Urdu Nastaleeq script [14] and printed English and Fraktur scripts [15]....
[...]
204 citations
"Text recognition using deep BLSTM n..." refers background in this paper
...Long Short Term Memory based Recurrent Neural network architecture has been widely used for speech recognition [7], [8], text recognition [9], social signal prediction [10], emotion recognition [11] and time series prediction problems since it has the ability of sequence learning....
[...]
183 citations
"Text recognition using deep BLSTM n..." refers background in this paper
...Long Short Term Memory based Recurrent Neural network architecture has been widely used for speech recognition [7], [8], text recognition [9], social signal prediction [10], emotion recognition [11] and time series prediction problems since it has the ability of sequence learning....
[...]
112 citations
"Text recognition using deep BLSTM n..." refers methods in this paper
...LSTM has been used for the recognition of printed Urdu Nastaleeq script [14] and printed English and Fraktur scripts [15]....
[...]
108 citations
"Text recognition using deep BLSTM n..." refers methods in this paper
...Some work has also been done in the last few years on online handwritten recognition of Telugu script using HMM [23] and online handwritten Tamil word recognition [24] have used segmentation based approaches....
[...]
...Traditionally, different handcrafted features have been used for text recognition of Oriya [20], Bangla[21] and classifiers like HMM [22], SVM and CRF has been widely used....
[...]
...LSTM based approaches have outperformed HMM based ones for handwriting recognition proving that learnt features are better than handcrafted features [17]....
[...]
...In segmentation free approaches sequential classifiers like Hidden Markov Model(HMM) and graphical models like Conditional Random Fields(CRF) have been used....
[...]