Wang Ling Goh — accepted AI-conference papers

2019

Towards Robust Curve Text Detection With Conditional Spatial Expansion

Zichuan Liu, Guosheng Lin, Sheng Yang, Fayao Liu, Weisi Lin, Wang Ling Goh

CVPR 2019poster

It is challenging to detect curve texts due to their irregular shapes and varying sizes. In this paper, we first investigate the deficiency of the existing curve detection methods and then propose a novel Conditional Spatial Expansion (CSE) mechanism to improve the performance of curve detection. In…

Cited by 105 PDF ↗Scholar ↗

2018

Learning Markov Clustering Networks for Scene Text Detection

Zichuan Liu, Guosheng Lin, Sheng Yang, Jiashi Feng, Weisi Lin, Wang Ling Goh

CVPR 2018poster

A novel framework named Markov Clustering Network (MCN) is proposed for fast and robust scene text detection. MCN predicts instance-level bounding boxes by firstly converting an image into a Stochastic Flow Graph (SFG) and then performing Markov Clustering on this graph. Our method can detect text o…

Cited by 139 Source ↗PDF ↗Scholar ↗