Home           Contact us           FAQs           
     Journal Home     |     Aim & Scope    |    Author(s) Information      |     Editorial Board     |     MSP Download Statistics
2013 (Vol. 5, Issue: 06)
Article Information:

Semantic Segmentation with Same Topic Constraints

Ling Mao and Mei Xie
Corresponding Author:  Ling Mao 

Key words:  CRF, higher-order potential, pLSA, topic, , ,
Vol. 5 , (06): 2232-2237
Submitted Accepted Published
August 17, 2012 September 08, 2012 February 21, 2013

A popular approach to semantic segmentation problems is to construct a pair wise Conditional Markov Random Field (CRF) over image pixels where the pair wise term encodes a preference for smoothness within pixel neighborhoods. Recently, researchers have considered higher-order models that encode local region or soft non-local constraints (e.g., label consistency or co-occurrence statistics). These new models with higher-order terms have significantly pushed the state-of-the-art for semantic segmentation problems. In this study, we consider a novel non-local constraint that enforces consistent pixel labels among those image regions having the same topic. These topics are discovered by Probabilistic Latent Semantic Analysis model (PLSA). We encode this constraint as a robust Pn higher-order potential among all the image regions of the same topic in a unified CRF model. We experimentally demonstrate quantitative and qualitative improvements over a refined baseline unary and pair wise CRF models.
Abstract PDF HTML
  Cite this Reference:
Ling Mao and Mei Xie, 2013. Semantic Segmentation with Same Topic Constraints.  Research Journal of Applied Sciences, Engineering and Technology, 5(06): 2232-2237.
    Advertise with us
ISSN (Online):  2040-7467
ISSN (Print):   2040-7459
Submit Manuscript
   Current Information
   Sales & Services
Home  |  Contact us  |  About us  |  Privacy Policy
Copyright © 2015. MAXWELL Scientific Publication Corp., All rights reserved