SCATTER: Selective Context Attentional Scene Text Recognizer
arXiv:2003.11288
Abstract
Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still struggle to recognize text written in arbitrary shapes. In this paper, we introduce a novel architecture for STR, named Selective Context ATtentional Text Recognizer (SCATTER). SCATTER utilizes a stacked block architecture with intermediate supervision during training, that paves the way to successfully train a deep BiLSTM encoder, thus improving the encoding of contextual dependencies. Decoding is done using a two-step 1D attention mechanism. The first attention step re-weights visual features from a CNN backbone together with contextual features computed by a BiLSTM layer. The second attention step, similar to previous papers, treats the features as a sequence and attends to the intra-sequence relationships. Experiments show that the proposed approach surpasses SOTA performance on irregular text recognition benchmarks by 3.7\% on average.
In CVPR 2020
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Focusing Attention: Towards Accurate Text Recognition in Natural Images
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- Rosetta: Large scale system for text detection and recognition in images
- MASTER: Multi-Aspect Non-local Network for Scene Text Recognition
- Scene Text Detection and Recognition: The Deep Learning Era
- What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
- Double Supervised Network with Attention Mechanism for Scene Text Recognition
- Adaptive Embedding Gate for Attention-Based Scene Text Recognition