English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Scene text detection has witnessed rapid development in recent years.However, there still exists two main challenges: 1) many methods suffer fromfalse positives in their text representations; 2) the large scale variance ofscene texts makes it hard for network to learn samples. In this paper, wepropose the ContourNet, which effectively handles these two problems taking afurther step toward accurate arbitrary-shaped text detection. At first, ascale-insensitive Adaptive Region Proposal Network (Adaptive-RPN) is proposedto generate text proposals by only focusing on the Intersection over Union(IoU) values between predicted and ground-truth bounding boxes. Then a novelLocal Orthogonal Texture-aware Module (LOTM) models the local textureinformation of proposal features in two orthogonal directions and representstext region with a set of contour points. Considering that the strongunidirectional or weakly orthogonal activation is usually caused by themonotonous texture characteristic of false-positive patterns (e.g. streaks.),our method effectively suppresses these false positives by only outputtingpredictions with high response value in both orthogonal directions. This givesmore accurate description of text regions. Extensive experiments on threechallenging datasets (Total-Text, CTW1500 and ICDAR2015) verify that our methodachieves the state-of-the-art performance. Code is available athttps://github.com/wangyuxin87/ContourNet.

ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection