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

Edge detection, a basic task in the field of computer vision, is an importantpreprocessing operation for the recognition and understanding of a visualscene. In conventional models, the edge image generated is ambiguous, and theedge lines are also very thick, which typically necessitates the use ofnon-maximum suppression (NMS) and morphological thinning operations to generateclear and thin edge images. In this paper, we aim to propose a one-stage neuralnetwork model that can generate high-quality edge images withoutpostprocessing. The proposed model adopts a classic encoder-decoder frameworkin which a pre-trained neural model is used as the encoder and amulti-feature-fusion mechanism that merges the features of each level with eachother functions as a learnable decoder. Further, we propose a new loss functionthat addresses the pixel-level imbalance in the edge image by suppressing thefalse positive (FP) edge information near the true positive (TP) edge and thefalse negative (FN) non-edge. The results of experiments conducted on severalbenchmark datasets indicate that the proposed method achieves state-of-the-artresults without using NMS and morphological thinning operations.

One-Stage Deep Edge Detection Based on Dense-Scale Feature Fusion and Pixel-Level Imbalance Learning