A brief analysis of the dense extreme inception network for edge detection

This work describes DexiNed, a Dense Extreme Inception Network for Edge Detection proposed by Xavier Soria, Edgar Riba and Angel Sappa in [IEEE Winter Conference on Applications of Computer Vision (WACV), 2020]. The network is organized in blocks that extract edges at different resolutions, which ar...

Full description

Bibliographic Details
Authors: Grompone von Gioi, Rafael, Randall, Gregory
Format: article
Status:Published version
Publication Date:2022
Country:Uruguay
Institution:Universidad de la República
Repository:COLIBRI
Language:English
OAI Identifier:oai:colibri.udelar.edu.uy:20.500.12008/34134
Online Access:https://www.ipol.im/pub/art/2022/423/
https://hdl.handle.net/20.500.12008/34134
Access Level:Open access
Keyword:Image edge detection
Neural network
HED
Xception
Description
Summary:This work describes DexiNed, a Dense Extreme Inception Network for Edge Detection proposed by Xavier Soria, Edgar Riba and Angel Sappa in [IEEE Winter Conference on Applications of Computer Vision (WACV), 2020]. The network is organized in blocks that extract edges at different resolutions, which are then merged to produce a multiscale edge map. For training, the authors introduced an annotated dataset (BIPED) specifically designed for edge detection. We perform a brief analysis of the results produced by DexiNed, highlighting its quality but also indicating its limitations. Overall, DexiNed produces state-of-the-art results.