Focus on the Whole Character: Discriminative Character Modeling for Scene Text Recognition

TL;DR

This paper introduces a novel character modeling approach for scene text recognition that enhances discriminability by explicitly guiding attention and enforcing intra- and inter-class feature consistency, achieving state-of-the-art results.

Contribution

The paper proposes the Character-Aware Constraint Encoder (CACE) with a decay matrix and the Intra-Inter Consistency Loss (I^2CL) to improve character feature discriminability in scene text recognition.

Findings

Achieves 94.1% accuracy on common benchmarks.

Attains 61.6% accuracy on Union14M-Benchmark.

Outperforms existing models in recognizing challenging texts.

Abstract

Recently, scene text recognition (STR) models have shown significant performance improvements. However, existing models still encounter difficulties in recognizing challenging texts that involve factors such as severely distorted and perspective characters. These challenging texts mainly cause two problems: (1) Large Intra-Class Variance. (2) Small Inter-Class Variance. An extremely distorted character may prominently differ visually from other characters within the same category, while the variance between characters from different classes is relatively small. To address the above issues, we propose a novel method that enriches the character features to enhance the discriminability of characters. Firstly, we propose the Character-Aware Constraint Encoder (CACE) with multiple blocks stacked. CACE introduces a decay matrix in each block to explicitly guide the attention region for each token. By continuously employing the decay matrix, CACE enables tokens to perceive morphological information at the character level. Secondly, an Intra-Inter Consistency Loss (I^2CL) is introduced to consider intra-class compactness and inter-class separability at feature space. I^2CL improves the discriminative capability of features by learning a long-term memory unit for each character category. Trained with synthetic data, our model achieves state-of-the-art performance on common benchmarks (94.1% accuracy) and Union14M-Benchmark (61.6% accuracy). Code is available at https://github.com/bang123-box/CFE.