computer-vision-11

Curved Text Detection

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in curved-text-detection-11

Trend

Dataset

Best Model

Actions

SCUT-CTW1500

Libraries

i

Use these libraries to find curved-text-detection-11 models and implementations

Datasets

SCUT-CTW1500

UrduDoc

Subtasks

No subtasks available.

Most implemented papers

Shape Robust Text Detection With Progressive Scale Expansion Network

Wenhai Wang, Tong Lu, Xiang Li, Jian Yang, Wenbo Hou, Ruo-Ze Liu•Wed Jun 06 2018

A novel Progressive Scale Expansion Network (PSENet) is proposed, which can precisely detect text instances with arbitrary shapes and is effective to split the close text instances, making it easier to use segmentation-based methods to detect arbitrary-shaped text instances.

695

Content

0

Paper Graph

EAST: An Efficient and Accurate Scene Text Detector

C. Yao, Shuchang Zhou, Xinyu Zhou, He Wen, Yuzhi Wang, Weiran He, Jiajun Liang•Mon Apr 10 2017

This work proposes a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes, and significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency.

1620 0

Paper Graph

Detecting Oriented Text in Natural Images by Linking Segments

Serge J. Belongie, X. Bai, Baoguang Shi•Sat Mar 18 2017

SegLink, an oriented text detection method to decompose text into two locally detectable elements, namely segments and links, achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin.

684 0

Paper Graph

TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes

Shangbang Long, Xin He, C. Yao, Jiaqiang Ruan, W. Zhang•Tue Jul 03 2018

A more flexible representation for scene text is proposed, termed as TextSnake, which is able to effectively represent text instances in horizontal, oriented and curved forms and outperforms the baseline on Total-Text by more than 40% in F-measure.

570 0

Paper Graph

Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition

Chee-Kheng Chng, Chee Seng Chan•Fri Oct 27 2017

To evaluate its robustness against curved text, DeconvNet is fine-tuned and benchmarked on Total-Text to facilitate a new research direction for the scene text community.

519 0

Paper Graph

Detecting Curve Text in the Wild: New Dataset and New Solution

Yuliang Liu, Lianwen Jin, Shuaitao Zhang, Sheng Zhang•Tue Dec 05 2017

A polygon based curve text detector (CTD) which can directly detect curve text without empirical combination and which can be end-to-end trainable to learn the inherent connection among the position offsets by seamlessly integrating the recurrent transverse and longitudinal offset connection (TLOC).

289 0

Paper Graph

Sliding Line Point Regression for Shape Robust Scene Text Detection

Jun Du, Yixing Zhu•Mon Jan 29 2018

This study proposes a novel method named sliding line point regression (SLPR) in order to detect arbitrary-shape text in natural scene and achieved competitive results on traditional ICDAR2015 Incidental Scene Text benchmark and curve text detection dataset CTW1500.

46 0

Paper Graph

MTRNet: A Generic Scene Text Eraser

C. Fookes, Osman Tursun, S. Sridharan, Rui Zeng, Simon Denman, Sabesan Sivipalan•Sun Mar 10 2019

MTRNet is a conditional adversarial generative network (cGAN) with an auxiliary mask that makes the cGAN a generic text eraser, but also enables stable training and early convergence on a challenging large-scale synthetic dataset, initially proposed for text detection in real scenes.

55 0

Paper Graph

Moving Object Detection for Event-based Vision using Graph Spectral Clustering

T. Bouwmans, Anindya Mondal, R. Shashant, Jhony H. Giraldo, A. Chowdhury•Wed Sep 29 2021

An unsupervised Graph Spectral Clustering technique for Moving Object Detection in Event-based data (GSCEventMOD) is presented and it is shown how the optimum number of moving objects can be automatically determined.

56 0

Paper Graph

Adding a benchmark result helps the community track progress.