arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.03082cs.CVcs.LG
收藏

视觉文本遇见低级视觉:视觉文本处理综合综述

Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing

Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)

Yan Shu, Weichao Zeng, Zhenhang Li, Fangmin Zhao, Yu Zhou

AI总结:

本文全面综述视觉文本处理领域,提出层次化分类体系,分析文本特征集成方法,并基准测试现有技术,指出挑战与未来方向。

摘要:

视觉文本作为文档图像和场景图像中的关键元素,承载着丰富的信息,在计算机视觉领域引起了广泛关注。超越视觉文本检测与识别,视觉文本处理领域在基础生成模型的出现推动下,研究激增。然而,由于文本区别于一般物体的独特属性和特征,挑战依然存在。正如我们的研究所观察到的,有效利用这些独特的文本特征在视觉文本处理中至关重要。在本综述中,我们对这一领域的最新进展进行了全面、多视角的分析。首先,我们引入了一个层次化的分类体系,涵盖从文本图像增强与恢复到文本图像操作等领域,随后介绍了不同的学习范式。接着,我们深入讨论了结构、笔画、语义、风格和空间上下文等特定文本特征如何无缝集成到各种任务中。此外,我们探讨了可用的公共数据集,并在几个广泛使用的数据集上对所述方法进行了基准测试。最后,我们指出了主要挑战和未来研究的潜在方向。我们的目标是将本综述确立为基本资源,促进视觉文本处理这一动态领域的持续探索与创新。

英文摘要:

Visual text, a pivotal element in both document and scene images, speaks volumes and attracts significant attention in the computer vision domain. Beyond visual text detection and recognition, the field of visual text processing has experienced a surge in research, driven by the advent of fundamental generative models. However, challenges persist due to the unique properties and features that distinguish text from general objects. Effectively leveraging these unique textual characteristics is crucial in visual text processing, as observed in our study. In this survey, we present a comprehensive, multi-perspective analysis of recent advancements in this field. Initially, we introduce a hierarchical taxonomy encompassing areas ranging from text image enhancement and restoration to text image manipulation, followed by different learning paradigms. Subsequently, we conduct an in-depth discussion of how specific textual features such as structure, stroke, semantics, style, and spatial context are seamlessly integrated into various tasks. Furthermore, we explore available public datasets and benchmark the reviewed methods on several widely-used datasets. Finally, we identify principal challenges and potential avenues for future research. Our aim is to establish this survey as a fundamental resource, fostering continued exploration and innovation in the dynamic area of visual text processing.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑