Traditional Method Inspired Deep Neural Network for Edge Detection

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 hi...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-05
Main Authors: Wibisono, Jan Kristanto, Hsueh-Ming Hang
Format: Article
Language:English
Subjects:
Artificial neural networks
Complexity
Computer architecture
Computer vision
Detectors
Edge detection
Feature extraction
Image detection
Image segmentation
Low pass filters
Model accuracy
Object recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422