Journal Article

Scene text recognition: an Indic perspective

Doermann, David, Chanda, Sukalpa, Vijayan, Vasanthan P., Krishnan, Narayanan C.

2025

Overview

Exploring Scene Text Recognition (STR) in Indian languages is an important research domain due to its wide applications. This paper proposes a spatial attention-based model (LaSA-Net) that combines visual features and language knowledge for word recognition from scene image word segments. We augment the classical cross-entropy loss with a novel language-attunement loss that enables the model to learn valid and prevalent character sequences in the word. This enhances the model’s ability to perform zero-shot word recognition. Further, to compensate for the lack of rotational invariance in CNN based feature extraction backbone, we propose a training data augmentation strategy involving the creation of glyphs: images of individual characters of different orientations. This improves LaSA-Net’s ability to recognize words in images with curved/vertically aligned text, alleviating the need for computationally expensive preprocessing modules. Our experiments with Tamil, Malayalam, and Telugu scripts on the IIIT-ILST datasets have achieved new benchmark results and outperformed other state-of-the-art STR models.

• Publisher: Springer Berlin Heidelberg,Springer Nature B.V
• Subject: Accuracy / Classification / Computer Science / Data augmentation / Dictionaries / Image Processing and Computer Vision / Language / Morphology / Original Paper / Pattern Recognition / Words (language)