Reading Scene Text with Attention Convolutional Sequence Modeling

Abstract

Reading text in the wild is a challenging task in the field of computer vision. Existing approaches mainly adopted Connectionist Temporal Classification (CTC) or Attention models based on Recurrent Neural Network (RNN), which is computationally expensive and hard to train. In this paper, we present an end-to-end Attention Convolutional Network for scene text recognition. Firstly, instead of RNN, we adopt the stacked convolutional layers to effectively capture the contextual dependencies of the input sequence, which is characterized by lower computational complexity and easier parallel computation. Compared to the chain structure of recurrent networks, the Convolutional Neural Network (CNN) provides a natural way to capture long-term dependencies between elements, which is 9 times faster than Bidirectional Long Short-Term Memory (BLSTM). Furthermore, in order to enhance the representation of foreground text and suppress the background noise, we incorporate the residual attention modules into a small densely connected network to improve the discriminability of CNN features. We validate the performance of our approach on the standard benchmarks, including the Street View Text, IIIT5K and ICDAR datasets. As a result, state-of-the-art or highly-competitive performance and efficiency show the superiority of the proposed approach.

References in corpus (3)

• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
• Addressing the Rare Word Problem in Neural Machine Translation
• Deep Structured Output Learning for Unconstrained Text Recognition

Cited by in corpus (6)

• Rosetta: Large scale system for text detection and recognition in images
• RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition
• Bidirectional Scene Text Recognition with a Single Decoder
• Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
• Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory
• ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition