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

Mask R-CNN has recently achieved great success in the field of instancesegmentation. However, weaknesses of the algorithm have been repeatedly pointedout as well, especially in the segmentation of long, sparse objects whoseorientation is not exclusively horizontal or vertical. We present here anapproach that significantly improves the performance of the algorithm by firstpre-segmenting the images with a PSPNet algorithm. To further improve itsprediction, we have developed our own cost functions and heuristics in the formof training strategies, which can prevent so-called (early) overfitting andachieve a more targeted convergence. Furthermore, due to the high variance ofthe images, especially for PSPNet, we aimed to develop strategies for a highrobustness and generalization, which are also presented here.

Boosting Mask R-CNN Performance for Long, Thin Forensic Traces with Pre-Segmentation and IoU Region Merging