Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis

Shangbang Long, Siyang Qin, Yasuhisa Fujii, Alessandro Bissacco, Michalis Raptis
10/25/2023
cs.CV

No official code found. Best implementation: google-research-datasets/hiertext (316 stars, CC-BY-SA-4.0, last commit 2024-12-02).

Abstract

We propose Hierarchical Text Spotter (HTS), a novel method for the joint task of word-level text spotting and geometric layout analysis. HTS can recognize text in an image and identify its 4-level hierarchical structure: characters, words, lines, and paragraphs. The proposed HTS is characterized by two novel components: (1) a Unified-Detector-Polygon (UDP) that produces Bezier Curve polygons of text lines and an affinity matrix for paragraph grouping between detected lines; (2) a Line-to-Character-to-Word (L2C2W) recognizer that splits lines into characters and further merges them back into words. HTS achieves state-of-the-art results on multiple word-level text spotting benchmark datasets as well as geometric layout analysis tasks.

View on arXivView PDF

Code Implementations(1)

google-research-datasets/hiertextCommunity100%
CC-BY-SA-4.0

The HierText dataset contains ~12k images from the Open Images dataset v6 with large amount of text entities. We provide word, line and paragraph level annotations.

31629Python, Jupyter NotebookMar 7, 20221 years agoCC-BY-SA-4.0

Similar Papers

Block-level Text Spotting with LLMs

84% match2024

CPN: Complementary Proposal Network for Unconstrained Text Detection

83% match2024

Towards Unified Multi-granularity Text Detection with Interactive Attention

82% match2024

LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting

82% match2 repos482025

ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis

82% match2026

Deformation Robust Text Spotting with Geometric Prior

81% match2023

Cite this paper

@article{long2023hierarchical,
  title  = {Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis},
  author = {Shangbang Long and Siyang Qin and Yasuhisa Fujii and Alessandro Bissacco and Michalis Raptis},
  year   = {2023},
  eprint = {2310.17674},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.17674v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.17674.svg)](https://codeofpaper.com/paper/2310.17674)

Discussion