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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Detecting scene text of arbitrary shapes has been a challenging task over thepast years. In this paper, we propose a novel segmentation-based text detector,namely SAST, which employs a context attended multi-task learning frameworkbased on a Fully Convolutional Network (FCN) to learn various geometricproperties for the reconstruction of polygonal representation of text regions.Taking sequential characteristics of text into consideration, a ContextAttention Block is introduced to capture long-range dependencies of pixelinformation to obtain a more reliable segmentation. In post-processing, aPoint-to-Quad assignment method is proposed to cluster pixels into textinstances by integrating both high-level object knowledge and low-level pixelinformation in a single shot. Moreover, the polygonal representation ofarbitrarily-shaped text can be extracted with the proposed geometric propertiesmuch more effectively. Experiments on several benchmarks, including ICDAR2015,ICDAR2017-MLT, SCUT-CTW1500, and Total-Text, demonstrate that SAST achievesbetter or comparable performance in terms of accuracy. Furthermore, theproposed algorithm runs at 27.63 FPS on SCUT-CTW1500 with a Hmean of 81.0% on asingle NVIDIA Titan Xp graphics card, surpassing most of the existingsegmentation-based methods.

A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning