SCATTER: Selective Context Attentional Scene Text Recognizer

03/25/2020
by   Ron Litman, et al.
0

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.

READ FULL TEXT

page 7

page 12

research
10/10/2019

On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention

Scene text recognition (STR) is the task of recognizing character sequen...
research
08/02/2018

Double Supervised Network with Attention Mechanism for Scene Text Recognition

In this paper, we propose Double Supervised Network with Attention Mecha...
research
07/15/2020

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

The attention-based encoder-decoder framework has recently achieved impr...
research
07/23/2019

2D-CTC for Scene Text Recognition

Scene text recognition has been an important, active research topic in c...
research
06/13/2019

2D Attentional Irregular Scene Text Recognizer

Irregular scene text, which has complex layout in 2D space, is challengi...
research
11/22/2017

Neuron-level Selective Context Aggregation for Scene Segmentation

Contextual information provides important cues for disambiguating visual...
research
05/09/2023

TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition

Text irregularities pose significant challenges to scene text recognizer...

Please sign up or login with your details

Forgot password? Click here to reset