Abstract
Connectionist temporal classification (CTC)-based scene text recognition (STR) methods, e.g., SVTR, are widely employed in OCR applications, mainly due to their simple architecture, which only contains a visual model and a CTC-aligned linear classifier, and therefore fast inference. However, they generally have worse accuracy than encoder-decoder-based methods (EDTRs), particularly in challenging scenarios. In this paper, we propose SVTRv2, a CTC model that beats leading EDTRs in both accuracy and inference speed. SVTRv2 introduces novel upgrades to handle text irregularity and utilize linguistic context, which endows it with the capability to deal with challenging and diverse text instances. First, a multi-size resizing (MSR) strategy is proposed to adaptively resize the text and maintain its readability. Meanwhile, we introduce a feature rearrangement module (FRM) to ensure that visual features accommodate the alignment requirement of CTC well, thus alleviating the alignment puzzle. Second, we propose a semantic guidance module (SGM). It integrates linguistic context into the visual model, allowing it to leverage language information for improved accuracy. Moreover, SGM can be omitted at the inference stage and would not increase the inference cost. We evaluate SVTRv2 in both standard and recent challenging benchmarks, where SVTRv2 is fairly compared with 24 mainstream STR models across multiple scenarios, including different types of text irregularity, languages, and long text. The results indicate that SVTRv2 surpasses all the EDTRs across the scenarios in terms of accuracy and speed. Code is available at this https URL.
Abstract (translated)
基于连接主义时间分类（CTC）的场景文本识别（STR）方法，例如SVTR，在OCR应用中被广泛使用，主要归因于其简单的架构，仅包含一个视觉模型和一个与CTC对齐的线性分类器，因此推理速度较快。然而，它们通常比基于编解码器的方法（EDTRs）具有更低的准确性，尤其是在挑战性场景下表现不佳。本文中，我们提出了SVTRv2，这是一种在准确性和推理速度上都超越领先EDTRs的CTC模型。SVTRv2引入了新颖的功能升级来处理文本不规则性和利用语言上下文，使其具备应对复杂多样的文字实例的能力。首先，提出了一种多尺寸调整（MSR）策略以自适应地调整文本并保持其可读性。同时，我们引入了一个特征重新排列模块（FRM），确保视觉特性能够很好地满足CTC的对齐要求，从而缓解了对齐难题。其次，我们提出了一个语义引导模块（SGM）。它将语言上下文整合到视觉模型中，允许利用语言信息提高准确性。此外，在推理阶段可以省略SGM，不会增加推理成本。我们在标准和近期具有挑战性的基准测试上评估了SVTRv2，与跨多种场景的24种主流STR模型进行了公平比较，包括不同类型的文本不规则性、语言以及长文本。结果表明，SVTRv2在准确性和速度方面超越了所有EDTRs。代码可在以下网址获取：此 https URL。
URL
https://arxiv.org/abs/2411.15858
