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

The research focus of scene text detection and recognition has shifted toarbitrary shape text in recent years, where the text shape representation is afundamental problem. An ideal representation should be compact, complete,efficient, and reusable for subsequent recognition in our opinion. However,previous representations have flaws in one or more aspects. Thin-Plate-Spline(TPS) transformation has achieved great success in scene text recognition.Inspired by this, we reversely think of its usage and sophisticatedly take TPSas an exquisite representation for arbitrary shape text representation. The TPSrepresentation is compact, complete, and efficient. With the predicted TPSparameters, the detected text region can be directly rectified to anear-horizontal one to assist the subsequent recognition. To further exploitthe potential of the TPS representation, the Border Alignment Loss is proposed.Based on these designs, we implement the text detector TPSNet, which can beextended to a text spotter conveniently. Extensive evaluation and ablation ofseveral public benchmarks demonstrate the effectiveness and superiority of theproposed method for text representation and spotting. Particularly, TPSNetachieves the detection F-Measure improvement of 4.4\% (78.4\% vs. 74.0\%) onArt dataset and the end-to-end spotting F-Measure improvement of 5.0\% (78.5\%vs. 73.5\%) on Total-Text, which are large margins with no bells and whistles.

TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation