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

Word spotting in natural scene images has many applications in sceneunderstanding and visual assistance. In this paper we propose a technique tocreate and exploit an intermediate representation of images based on textattributes which are character probability maps. Our representation extends theconcept of the Pyramidal Histogram Of Characters (PHOC) by exploiting FullyConvolutional Networks to derive a pixel-wise mapping of the characterdistribution within candidate word regions. We call this representation theSoft-PHOC. Furthermore, we show how to use Soft-PHOC descriptors for wordspotting tasks in egocentric camera streams through an efficient text lineproposal algorithm. This is based on the Hough Transform over characterattribute maps followed by scoring using Dynamic Time Warping (DTW). Weevaluate our results on ICDAR 2015 Challenge 4 dataset of incidental scene textcaptured by an egocentric camera.

Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images