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

Segmentation of overlapping convex objects has various applications, forexample, in nanoparticles and cell imaging. Often the segmentation method hasto rely purely on edges between the background and foreground making theanalyzed images essentially silhouette images. Therefore, to segment theobjects, the method needs to be able to resolve the overlaps between multipleobjects by utilizing prior information about the shape of the objects. Thispaper introduces a novel method for segmentation of clustered partiallyoverlapping convex objects in silhouette images. The proposed method involvesthree main steps: pre-processing, contour evidence extraction, and contourestimation. Contour evidence extraction starts by recovering contour segmentsfrom a binarized image by detecting concave points. After this, the contoursegments which belong to the same objects are grouped. The grouping isformulated as a combinatorial optimization problem and solved using the branchand bound algorithm. Finally, the full contours of the objects are estimated bya Gaussian process regression method. The experiments on a challenging datasetconsisting of nanoparticles demonstrate that the proposed method outperformsthree current state-of-art approaches in overlapping convex objectssegmentation. The method relies only on edge information and can be applied toany segmentation problems where the objects are partially overlapping and havea convex shape.

Resolving Overlapping Convex Objects in Silhouette Images by Concavity Analysis and Gaussian Process