IterVM: Iterative Vision Modeling Module for Scene Text Recognition

TL;DR

IterVM introduces an iterative vision modeling approach that, combined with iterative language modeling, significantly enhances scene text recognition accuracy, especially on low-quality images, setting new benchmark results.

Contribution

The paper proposes IterVM, a novel iterative vision modeling module that improves feature extraction in scene text recognition, and integrates it with iterative language modeling to form the state-of-the-art IterNet.

Findings

IterVM significantly improves recognition accuracy on low-quality images.

IterNet achieves new state-of-the-art results on multiple benchmarks.

The method effectively fuses multi-level features for better recognition.

Abstract

Scene text recognition (STR) is a challenging problem due to the imperfect imagery conditions in natural images. State-of-the-art methods utilize both visual cues and linguistic knowledge to tackle this challenging problem. Specifically, they propose iterative language modeling module (IterLM) to repeatedly refine the output sequence from the visual modeling module (VM). Though achieving promising results, the vision modeling module has become the performance bottleneck of these methods. In this paper, we newly propose iterative vision modeling module (IterVM) to further improve the STR accuracy. Specifically, the first VM directly extracts multi-level features from the input image, and the following VMs re-extract multi-level features from the input image and fuse them with the high-level (i.e., the most semantic one) feature extracted by the previous VM. By combining the proposed IterVM with iterative language modeling module, we further propose a powerful scene text recognizer called IterNet. Extensive experiments demonstrate that the proposed IterVM can significantly improve the scene text recognition accuracy, especially on low-quality scene text images. Moreover, the proposed scene text recognizer IterNet achieves new state-of-the-art results on several public benchmarks. Codes will be available at https://github.com/VDIGPKU/IterNet.