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

TL;DR

This comprehensive survey reviews recent advancements in visual text processing, emphasizing the integration of textual features, datasets, and challenges, to guide future research in this evolving field.

Contribution

It provides a hierarchical taxonomy, discusses textual feature integration, benchmarks methods on datasets, and highlights future research directions in visual text processing.

Findings

Effective use of textual features enhances processing tasks.

Benchmarking reveals strengths and gaps in current methods.

Identifies key challenges and future research avenues.

Abstract

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.