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

Leveraging the advances of natural language processing, most recent scenetext recognizers adopt an encoder-decoder architecture where text images arefirst converted to representative features and then a sequence of charactersvia `sequential decoding'. However, scene text images suffer from rich noisesof different sources such as complex background and geometric distortions whichoften confuse the decoder and lead to incorrect alignment of visual features atnoisy decoding time steps. This paper presents I2C2W, a novel scene textrecognition technique that is tolerant to geometric and photometric degradationby decomposing scene text recognition into two inter-connected tasks. The firsttask focuses on image-to-character (I2C) mapping which detects a set ofcharacter candidates from images based on different alignments of visualfeatures in an non-sequential way. The second task tackles character-to-word(C2W) mapping which recognizes scene text by decoding words from the detectedcharacter candidates. The direct learning from character semantics (instead ofnoisy image features) corrects falsely detected character candidateseffectively which improves the final text recognition accuracy greatly.Extensive experiments over nine public datasets show that the proposed I2C2Woutperforms the state-of-the-art by large margins for challenging scene textdatasets with various curvature and perspective distortions. It also achievesvery competitive recognition performance over multiple normal scene textdatasets.

I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition