Proceedings of the AAAI Conference on Artificial Intelligence · 2020 · 159 citations · 14 references
ComputingComputer ScienceComputer VisionNatural Language ProcessingVisual AttentionDeep LearningPattern RecognitionScene UnderstandingSemantic SegmentationText SegmentationAttentionBenchmark DatasetsContext ModelingPositionScene Text RecognitionSemantic Text SegmentationText DetectionThresholding
Driven by deep learning and a large volume of data, scene text recognition has evolved rapidly in recent years. Formerly, RNN-attention-based methods have dominated this field, but suffer from the problem of attention drift in certain situations. Lately, semantic segmentation based algorithms have proven effective at recognizing text of different forms (horizontal, oriented and curved). However, these methods may produce spurious characters or miss genuine characters, as they rely heavily on a thresholding procedure operated on segmentation maps. To tackle these challenges, we propose in this paper an alternative approach, called TextScanner, for scene text recognition. TextScanner bears three characteristics: (1) Basically, it belongs to the semantic segmentation family, as it generates pixel-wise, multi-channel segmentation maps for character class, position and order; (2) Meanwhile, akin to RNN-attention-based methods, it also adopts RNN for context modeling; (3) Moreover, it performs paralleled prediction for character position and class, and ensures that characters are transcripted in the correct order. The experiments on standard benchmark datasets demonstrate that TextScanner outperforms the state-of-the-art methods. Moreover, TextScanner shows its superiority in recognizing more difficult text such as Chinese transcripts and aligning with target characters.
14
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
ICDAR 2015 competition on Robust Reading
Dìmosthenis Karatzas, Lluís Gómez, Anguelos Nicolaou et al. · 2015 · 1.6K citations
Synthetic Data for Text Localisation in Natural Images
Ankush Gupta, Andrea Vedaldi, Andrew Zisserman · 2016 · 1.5K citations
ICDAR 2013 Robust Reading Competition
Dìmosthenis Karatzas, Faisal Shafait, Seiichi Uchida et al. · 2013 · 1.4K citations