NASTER: Non-local Attentional Scene Text Recognizer

Abstract

Scene text recognition has been widely investigated in computer vision. In the literature, the encoder-decoder based framework, which first encodes image into feature map and then decodes them into corresponding text sequences, have achieved great success. However, this solution fails in low-quality images, as the local visual features extracted from curved or blurred images are difficult to decode into corresponding text. To address this issue, we propose a new framework for Scene Text Recognition (STR), named Non-Local Attentional Scene Text Recognizer (NASTER). We use ResNet with Global Context Block (GC block) to extract global visual features. The global context information is then captured in parallel using the self-attention module and finally decoded by a multi-layer attention decoder with an intermediate supervision module. The proposed method achieves the state-of-the-art performances on seven benchmark datasets, demonstrating the effectiveness of our approach.

Pure Transformer with Integrated Experts for Scene Text Recognition

“…A transformer decoder is then used to decode the image features into sequences of characters. A similar model was also proposed by Wu et al [42], utilizing a transformer decoder which is preceded by a global context ResNet (GCNet). Zhang et al [50] employed a combination of CNN and RNN as the encoder and a transformer inspired cross-network attention as a part of the decoder in their cascade attention network.…”