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

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.

arXiv commentThe first and second authors contributed equally. Accepted in Pattern Recognition Journal

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Neural Machine Translation by Jointly Learning to Align and Translate
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Image Captioning with Semantic Attention
• Understanding Deep Neural Networks with Rectified Linear Units
• Automatic Script Identification in the Wild

Cited by in corpus (5)

• A Survey of the Recent Architectures of Deep Convolutional Neural Networks
• A Deep One-Shot Network for Query-based Logo Retrieval
• Patch Aggregator for Scene Text Script Identification
• Sequential Random Network for Fine-grained Image Classification
• Exploring Knowledge Distillation of a Deep Neural Network for Multi-Script identification