LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition

TL;DR

LISTER introduces a neighbor decoding approach with feature enhancement to achieve robust scene text recognition across varying lengths, especially excelling in recognizing longer texts and extrapolating length without prior length information.

Contribution

The paper presents the first effective method for length-insensitive scene text recognition, combining neighbor decoding and feature enhancement for improved long text recognition.

Findings

Superior performance on long text recognition

Effective length extrapolation capability

Outperforms previous state-of-the-art methods on benchmarks

Abstract

The diversity in length constitutes a significant characteristic of text. Due to the long-tail distribution of text lengths, most existing methods for scene text recognition (STR) only work well on short or seen-length text, lacking the capability of recognizing longer text or performing length extrapolation. This is a crucial issue, since the lengths of the text to be recognized are usually not given in advance in real-world applications, but it has not been adequately investigated in previous works. Therefore, we propose in this paper a method called Length-Insensitive Scene TExt Recognizer (LISTER), which remedies the limitation regarding the robustness to various text lengths. Specifically, a Neighbor Decoder is proposed to obtain accurate character attention maps with the assistance of a novel neighbor matrix regardless of the text lengths. Besides, a Feature Enhancement Module is devised to model the long-range dependency with low computation cost, which is able to perform iterations with the neighbor decoder to enhance the feature map progressively. To the best of our knowledge, we are the first to achieve effective length-insensitive scene text recognition. Extensive experiments demonstrate that the proposed LISTER algorithm exhibits obvious superiority on long text recognition and the ability for length extrapolation, while comparing favourably with the previous state-of-the-art methods on standard benchmarks for STR (mainly short text).