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

Automatic extraction methods typically assume that line segments arepronounced, thin, few and far between, do not cross each other, and are noiseand clutter-free. Since these assumptions often fail in realistic scenarios,many line segments are not detected or are fragmented. In more severe cases,i.e., many who use the Hough Transform, extraction can fail entirely. In thispaper, we propose a method that tackles these issues. Its key aspect is thecombination of thresholded image derivatives obtained with filters of large andsmall footprints, which we denote as contextual and local edges, respectively.Contextual edges are robust to noise and we use them to select valid localedges, i.e., local edges that are of the same type as contextual ones:dark-to-bright transition of vice-versa. If the distance between valid localedges does not exceed a maximum distance threshold, we enforce connectivity bymarking them and the pixels in between as edge points. This originatesconnected edge maps that are robust and well localized. We use a powerfultwo-sample statistical test to compute contextual edges, which we introducebriefly, as they are unfamiliar to the image processing community. Finally, wepresent experiments that illustrate, with synthetic and real images, how ourmethod is efficient in extracting complete segments of all lengths and widthsin several situations where current methods fail.

Combining contextual and local edges for line segment extraction in cluttered images