Benchmarking Scene Text Recognition in Devanagari, Telugu and Malayalam

04/09/2021
by   Minesh Mathew, et al.
1

Inspired 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. IIIT-ILST dataset, synthetic word images dataset and the script used to render synthetic images are available at http://cvit.iiit.ac.in/research/projects/cvit-projects/iiit-ilst

READ FULL TEXT

page 1

page 3

page 4

page 5

research
05/13/2022

An empirical study of CTC based models for OCR of Indian languages

Recognition of text on word or line images, without the need for sub-wor...
research
11/07/2017

Unconstrained Scene Text and Video Text Recognition for Arabic Script

Building robust recognizers for Arabic has always been challenging. We d...
research
08/30/2012

Benchmarking recognition results on word image datasets

We have benchmarked the maximum obtainable recognition accuracy on vario...
research
01/10/2022

Transfer Learning for Scene Text Recognition in Indian Languages

Scene text recognition in low-resource Indian languages is challenging b...
research
01/10/2022

Towards Boosting the Accuracy of Non-Latin Scene Text Recognition

Scene-text recognition is remarkably better in Latin languages than the ...
research
03/16/2020

FragNet: Writer Identification using Deep Fragment Networks

Writer identification based on a small amount of text is a challenging p...
research
03/27/2022

Benchmarking Algorithms for Automatic License Plate Recognition

We evaluated a lightweight Convolutional Neural Network (CNN) called LPR...

Please sign up or login with your details

Forgot password? Click here to reset