Semantic segmentation based on iterative contraction and merging

Tzu Hao Yang, Jia Hao Syu, Sheng-Jyh Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The state-of-the-art models for semantic image segmentation usually contain a convolutional neural network (CNN) and a conditional random field (CRF). As a predictor, existing CNN techniques can generate a dense prediction result but may generate obvious boundary errors at the same time. As a refinement model, CRF improves the CNN outcomes by forcing the consistency of local labels. However, the use of CRF may cause fragmentation effect around object boundaries. In this paper, we propose the use of a so-called iterative contraction and merging (ICM) process to facilitate the semantic segmentation process. Guided by the high-level information from CNN, the ICM process is used as a tool to grow image segments in a bottom-up way and to produce more accurate outcomes in an iterative way. The ICM process can faithfully preserve the boundary information and maintain the consistency of local labels. Our experimental results demonstrate that the performance of the proposed approach is comparable to the state-of-the-art models but with more accurate boundaries.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages1282-1286
Number of pages5
ISBN (Electronic)9781509021758
DOIs
StatePublished - 20 Feb 2018
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: 17 Sep 201720 Sep 2017

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2017-September
ISSN (Print)1522-4880

Conference

Conference24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period17/09/1720/09/17

Keywords

  • Convolutional Neural Networks
  • Image Semantic Segmentation

Fingerprint Dive into the research topics of 'Semantic segmentation based on iterative contraction and merging'. Together they form a unique fingerprint.

Cite this