Text Growing on Leaf
Chuang. Yang, Mulin. Chen, Yuan. Yuan, and Qi. Wang

TL;DR
This paper introduces LeafText, a novel scene text detection method inspired by leaf vein structures, which effectively captures irregular-shaped texts by simulating leaf growth processes and employing a new vein-based representation.
Contribution
It proposes a leaf vein-based text representation (LVT) and a detection framework that mimics leaf growth, improving detection of highly curved and irregular-shaped texts over existing methods.
Findings
Outperforms state-of-the-art on multiple datasets
Accurately depicts arbitrary-shaped texts
Enhances robustness with Multi-Oriented Smoother
Abstract
Irregular-shaped texts bring challenges to Scene Text Detection (STD). Although existing contour point sequence-based approaches achieve comparable performances, they fail to cover some highly curved ribbon-like text lines. It leads to limited text fitting ability and STD technique application. Considering the above problem, we combine text geometric characteristics and bionics to design a natural leaf vein-based text representation method (LVT). Concretely, it is found that leaf vein is a generally directed graph, which can easily cover various geometries. Inspired by it, we treat text contour as leaf margin and represent it through main, lateral, and thin veins. We further construct a detection framework based on LVT, namely LeafText. In the text reconstruction stage, LeafText simulates the leaf growth process to rebuild text contour. It grows main vein in Cartesian coordinates to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHandwritten Text Recognition Techniques · Vehicle License Plate Recognition · Image Processing and 3D Reconstruction
MethodsSpatial-Channel Token Distillation
