IIIT Hyderabad Publications |
|||||||||
|
Benchmarking Scene Text Recognition in Devanagari, Telugu and MalayalamAuthors: Minesh Mathew,Mohit Jain, C V Jawahar Conference: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR-2017 2017) Location Kyoto, Japan Date: 2017-11-09 Report no: IIIT/TR/2017/52 AbstractInspired by the success of Deep Learning based approaches to English scene text recognition, we pose and benchmark scene text recognition for three Indic scripts – Devanagari, Telugu and Malayalam. Synthetic word images rendered from Unicode fonts are used for training the recognition system. And the performance is bench-marked on a new - IIIT-ILST dataset comprising of hundreds of real scene images containing text in the above mentioned scripts. We use a segmentation free, hybrid but end-to-end trainable CNN - RNN deep neural network for transcribing the word images to the corresponding texts. The cropped word images need not be segmented into the sub- word units and the error is calculated and backpropagated for the the given word image at once. The network is trained using CTC loss, which is proven quite effective for sequence-to-sequence transcription tasks. The CNN layers in the network learn to extract robust feature representations from word images. The sequence of features learnt by the convolutional block is transcribed to a sequence of labels by the RNN + CTC block. The transcription is not bound by word length or a lexicon and is ideal for Indian languages which are highly inflectional. Full paper: pdf Centre for Visual Information Technology |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |