An Improved Image Semantic Segmentation Method Based on Superpixels and Conditional Random Fields

An Improved Image Semantic Segmentation Method Based on Superpixels and Conditional Random Fields

This paper proposed an improved image semantic segmentation method based on superpixels and conditional random fields (CRFs). The proposed method can take full advantage of the superpixel edge information and the constraint relationship among different pixels. First, we employ fully convolutional ne...

Full description

Bibliographic Details
Main Authors: Wei Zhao, Yi Fu, Xiaosong Wei, Hai Wang
Format: Article
Language:English
Published: MDPI AG 2018-05-01
Series:Applied Sciences
Subjects:
image semantic segmentation
superpixels
conditional random fields
fully convolutional network
Online Access:http://www.mdpi.com/2076-3417/8/5/837

Internet

http://www.mdpi.com/2076-3417/8/5/837

Similar Items