Revisiting Classification Perspective on Scene Text Recognition

Abstract

The prevalent perspectives of scene text recognition are from sequence to sequence (seq2seq) and segmentation. Nevertheless, the former is composed of many components which makes implementation and deployment complicated, while the latter requires character level annotations that is expensive. In this paper, we revisit classification perspective that models scene text recognition as an image classification problem. Classification perspective has a simple pipeline and only needs word level annotations. We revive classification perspective by devising a scene text recognition model named as CSTR, which performs as well as methods from other perspectives. The CSTR model consists of CPNet (classification perspective network) and SPPN (separated conv with global average pooling prediction network). CSTR is as simple as image classification model like ResNet \cite{he2016deep} which makes it easy to implement and deploy. We demonstrate the effectiveness of the classification perspective on scene text recognition with extensive experiments. Futhermore, CSTR achieves nearly state-of-the-art performance on six public benchmarks including regular text, irregular text. The code will be available at https://github.com/Media-Smart/vedastr.

arXiv comment10 pages, 4 figures

References in corpus (10)

• Language Models are Few-Shot Learners
• Attention-Based Models for Speech Recognition
• A Structured Self-attentive Sentence Embedding
• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
• Focusing Attention: Towards Accurate Text Recognition in Natural Images
• Rosetta: Large scale system for text detection and recognition in images
• MASTER: Multi-Aspect Non-local Network for Scene Text Recognition
• PP-OCR: A Practical Ultra Lightweight OCR System
• Recurrent Calibration Network for Irregular Text Recognition
• KISS: Keeping It Simple for Scene Text Recognition