Reading Scene Text in Deep Convolutional Sequences

2015/06/14 by Pan He, Weilin Huang, He, Pan +7 · 4 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1506.04395

openalex publication_date 2015/06/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered high-level sequence from a whole word image, avoiding the difficult character segmentation problem. Then a deep recurrent model, building on long short-term memory (LSTM), is developed to robustly recognize the generated CNN sequences, departing from most existing approaches recognising each character independently. Our model has a number of appealing properties in comparison to existing scene text recognition methods: (i) It can recognise highly ambiguous words by leveraging meaningful context information, allowing it to work reliably without either pre- or post-processing; (ii) the deep CNN feature is robust to various image distortions; (iii) it retains the explicit order information in word image, which is essential to discriminate word strings; (iv) the model does not depend on pre-defined dictionary, and it can process unknown words and arbitrary strings. Codes for the DTRN will be available.

Citations

• Synthetic Data and Artificial Neural Networks for Natural Scene Text\n Recognition
• End-to-End Text Recognition with Hybrid HMM Maxout Models
• Long Short-Term Memory
• Gradient-based learning applied to document recognition
• A Novel Connectionist System for Unconstrained Handwriting Recognition

Cited by

• LadderMoE: Ladder-Side Mixture of Experts Adapters for Bronze Inscription Recognition
• Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
• Primitive Representation Learning for Scene Text Recognition
• Fully Convolutional Recurrent Network for Handwritten Chinese Text Recognition

Related

• Sequence to sequence learning for unconstrained scene text recognition
• Memory Matters: Convolutional Recurrent Neural Network for Scene Text Recognition
• Reading Scene Text with Attention Convolutional Sequence Modeling
• Scene Text Recognition with Sliding Convolutional Character Models
• Synthetic Data and Artificial Neural Networks for Natural Scene Text\n Recognition