Traditional Method Inspired Deep Neural Network for Edge Detection

Jan Kristanto Wibisono, Hsueh Ming Hang

研究成果: Conference contribution同行評審

摘要

Recently, Deep-Neural-Network (DNN) based edge prediction is progressing fast. Although the DNN based schemes outperform the traditional edge detectors, they have much higher computational complexity. It could be that the DNN based edge detectors often adopt the neural net structures designed for high-level computer vision tasks, such as image segmentation and object recognition. Edge detection is a rather local and simple job, the over-complicated architecture and massive parameters may be unnecessary. Therefore, we propose a traditional method inspired framework to produce good edges with minimal complexity. We simplify the network architecture to include Feature Extractor, Enrichment, and Summarizer, which roughly correspond to gradient, low pass filter, and pixel connection in the traditional edge detection schemes. The proposed structure can effectively reduce the complexity and retain the edge prediction quality. Our TIN2 (Traditional Inspired Network) model has an accuracy higher than the recent BDCN2 (Bi-Directional Cascade Network) but with a smaller model.

原文English
主出版物標題2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
發行者IEEE Computer Society
頁面678-682
頁數5
ISBN(電子)9781728163956
DOIs
出版狀態Published - 十月 2020
事件2020 IEEE International Conference on Image Processing, ICIP 2020 - Virtual, Abu Dhabi, United Arab Emirates
持續時間: 25 九月 202028 九月 2020

出版系列

名字Proceedings - International Conference on Image Processing, ICIP
2020-October
ISSN(列印)1522-4880

Conference

Conference2020 IEEE International Conference on Image Processing, ICIP 2020
國家United Arab Emirates
城市Virtual, Abu Dhabi
期間25/09/2028/09/20

指紋 深入研究「Traditional Method Inspired Deep Neural Network for Edge Detection」主題。共同形成了獨特的指紋。

引用此