Text recognition using deep BLSTM networks

Abstract

This paper presents a Deep Bidirectional Long Short Term Memory (LSTM) based Recurrent Neural Network architecture for text recognition. This architecture uses Connectionist Temporal Classification (CTC) for training to learn the labels of an unsegmented sequence with unknown alignment. This work is motivated by the results of Deep Neural Networks for isolated numeral recognition and improved speech recognition using Deep BLSTM based approaches. Deep BLSTM architecture is chosen due to its ability to access long range context, learn sequence alignment and work without the need of segmented data. Due to the use of CTC and forward backward algorithms for alignment of output labels, there are no unicode re-ordering issues, thus no need of lexicon or postprocessing schemes. This is a script independent and segmentation free approach. This system has been implemented for the recognition of unsegmented words of printed Oriya text. This system achieves 4.18% character level error and 12.11% word error rate on printed Oriya text.

Threat Detection and Analysis in the Internet of Things using Deep Packet Inspection

“…Artificial Neural Network(ANN) and more complex versions of Recurrent Neural Networks(RNN) such as Long Short Term Memory (LSTM) only work with numerical values. However (Ray, Rajeswar, & Chaud, 2015) demonstrated that a Deep Bidirectional Long Short Term Memory based RNN (BLSTM-RNN) can be used which provides promising results for text recognition. (Wang, Qian, Soong, He, & Zhao, 2015) further demonstrated this potential when a BLSTM-RNN was used in conjunction with Word Embedding, in such a way phrases and vocabulary were mapped to vectors or real numbers and proved to be an effective method for modelling and predicting sequential text.…”

A hypothesize-and-verify framework for text recognition using deep recurrent neural networks

“…A deep recurrent neural network is trained on perfectly segmented data and tests each of the candidate segments, generating unicode sequences. This work is an extension of the work on printed text recognition using Deep BLSTM wherein Deep BLSTM architecture for text recognition was proposed [1]. In the verification stage these unicode sequences are validated using a sub-string match with the language model and best first search is used to find the best possible combination of alternative hypothesis from the tree structure.…”

Segmentation-free optical character recognition for printed Urdu text

“…However, segmenting (Urdu and alike) cursive scripts into characters is a challenging task in itself. Recently, implicit segmentation using deep learning has been successfully investigated for recognition of Urdu text [23][24][25][26]. These techniques, however, require large training data and employ characters as units of recognition rather than ligatures or words.…”

“…While the initial endeavors primarily focused on recognition of isolated characters [6][7][8], a number of deep learning-based robust solutions [17,[23][24][25][26] have been proposed in the recent years. These methods mainly rely on implicit segmentation of characters and report high recognition rates.…”