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/

Zendy Plus

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

Zendy Tools

Zendy Open

This paper focuses on the problem of script identification in scene textimages. Facing this problem with state of the art CNN classifiers is notstraightforward, as they fail to address a key characteristic of scene textinstances: their extremely variable aspect ratio. Instead of resizing inputimages to a fixed aspect ratio as in the typical use of holistic CNNclassifiers, we propose here a patch-based classification framework in order topreserve discriminative parts of the image that are characteristic of itsclass. We describe a novel method based on the use of ensembles of conjoinednetworks to jointly learn discriminative stroke-parts representations and theirrelative importance in a patch-based classification scheme. Our experimentswith this learning procedure demonstrate state-of-the-art results in two publicscript identification datasets. In addition, we propose a new public benchmarkdataset for the evaluation of multi-lingual scene text end-to-end readingsystems. Experiments done in this dataset demonstrate the key role of scriptidentification in a complete end-to-end system that combines our scriptidentification method with a previously published text detector and anoff-the-shelf OCR engine.

Improving patch-based scene text script identification with ensembles of conjoined networks