Script Identification in Natural Scene Image and Video Frame using Attention based Convolutional-LSTM Network

TL;DR

This paper introduces an attention-based CNN-LSTM framework for script identification in scene images and videos, effectively handling low quality and complex backgrounds to improve recognition accuracy.

Contribution

The novel approach combines local and global feature extraction with dynamic weighting using attention mechanisms within a CNN-LSTM framework for script identification.

Findings

Achieved superior accuracy on four public datasets.

Effectively handled low-quality images and complex backgrounds.

Demonstrated improvement over conventional methods.

Abstract

Script identification plays a significant role in analysing documents and videos. In this paper, we focus on the problem of script identification in scene text images and video scripts. Because of low image quality, complex background and similar layout of characters shared by some scripts like Greek, Latin, etc., text recognition in those cases become challenging. In this paper, we propose a novel method that involves extraction of local and global features using CNN-LSTM framework and weighting them dynamically for script identification. First, we convert the images into patches and feed them into a CNN-LSTM framework. Attention-based patch weights are calculated applying softmax layer after LSTM. Next, we do patch-wise multiplication of these weights with corresponding CNN to yield local features. Global features are also extracted from last cell state of LSTM. We employ a fusion technique which dynamically weights the local and global features for an individual patch. Experiments have been done in four public script identification datasets: SIW-13, CVSI2015, ICDAR-17 and MLe2e. The proposed framework achieves superior results in comparison to conventional methods.