逆向检测图像中是否被删除文字，防范文本移除技术滥用
Inverse Scene Text Removal
- 通过分析处理后图像，判断是否经过文本移除
- 二分类准确率高，能定位被删除的文字区域
- 可恢复部分删除文本，适合安全与版权检测场景
场景文本移除（STR）旨在消除图像中的文字元素，最初用于去除自然场景中敏感或不必要文字，现也应用于排版图像。传统STR通过检测文本区域并进行修复填充。尽管借助神经网络和合成数据取得进展，其滥用风险也随之增加。本文研究逆向文本移除（ISTR），分析经STR处理的图像，聚焦于二分类任务（判断图像是否经过STR）和被删除文本区域的定位。实验表明，这些任务可实现高精度，有助于检测潜在滥用行为并改进STR。此外，通过训练文本识别模型评估恢复难度，尝试重建被删除的文字内容。
原文摘要 · Abstract (English)
Scene text removal (STR) aims to erase textual elements from images. It was originally intended for removing privacy-sensitiveor undesired texts from natural scene images, but is now also appliedto typographic images. STR typically detects text regions and theninpaints them. Although STR has advanced through neural networksand synthetic data, misuse risks have increased. This paper investi-gates Inverse STR (ISTR), which analyzes STR-processed images andfocuses on binary classification (detecting whether an image has un-dergone STR) and localizing removed text regions. We demonstrate inexperiments that these tasks are achievable with high accuracies, en-abling detection of potential misuse and improving STR. We also at-tempt to recover the removed text content by training a text recognizerto understand its difficulty.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。