Convolutional Attention Networks for Scene Text Recognition

Authors:

Abstract
In this article, we present Convoluitional Attention Networks (CAN) for unconstrained scene text recognition. Recent dominant approaches for scene text recognition are mainly based on Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), where the CNN encodes images and the RNN generates character sequences. Our CAN is different from these methods; our CAN is completely built on CNN and includes an attention mechanism. The distinctive characteristics of our method include (i) CAN follows encoder-decoder architecture, in which the encoder is a deep two-dimensional CNN and the decoder is a one-dimensional CNN; (ii) the attention mechanism is applied in every convolutional layer of the decoder, and we propose a novel spatial attention method using average pooling; and (iii) position embeddings are equipped in both a spatial encoder and a sequence decoder to give our networks a sense of location. We conduct experiments on standard datasets for scene text recognition, including Street View Text , IIIT5K, and ICDAR datasets. The experimental results validate the effectiveness of different components and show that our convolutional-based method achieves state-of-the-art or competitive performance over prior works, even without the use of RNN.
Funding Information
  • National Nature Science Foundation of China (61525206,61771468,61622211,61472392 and 61620106009)
  • Fundamental Research Funds for the Central Universities (WK2100100030)
  • National Key Research and Development Program of China (2017YFC0820600)
  • Youth Innovation Promotion Association Chinese Academy of Sciences (2017209)

This publication has 33 references indexed in Scilit: