Home           Contact us           FAQs           
 
   Journal Page   |   Aims & Scope   |   Author Guideline   |   Editorial Board   |   Search
    Abstract
2013 (Vol. 5, Issue: 06)
Article Information:

Multiclass Image Segmentation Based on Pixel and Segment Level

Ling Mao and Mei Xie
Corresponding Author:  Ling Mao 

Key words:  Constrained parametric min cuts, CRF, higher order potential, non-linear support vector model , , ,
Vol. 5 , (06): 2238-2244
Submitted Accepted Published
September 03, 2012 September 24, 2012 February 21, 2013
Abstract:

Multi-class image segmentation (or pixel labeling) is one of the most important and challenging tasks in computer vision. Currently, many different methods for this task can be broadly categorized into two types according to their choice of the partitioning of the image space, i.e., pixels or segments. However, each choice of the two types of methods comes with its share of advantages and disadvantages. In this study, we construct a novel CRF model to integrate features extracted from pixel and segment levels. We exploit segments generated by Constrained Parametric Min Cuts (CPMC) algorithm in the proposed framework, instead of commonly used unsupervised segmentation method (e.g., mean-shift approach). Additionally, the recognition based on these segments is also integrated into the model, which possible corrects classification mistakes caused by the unary term based on information derived from pixel level. We experimentally demonstrate our modelís quantitative and qualitative improvements over the baseline methods.
Abstract PDF HTML
  Cite this Reference:
Ling Mao and Mei Xie, 2013. Multiclass Image Segmentation Based on Pixel and Segment Level.  Research Journal of Applied Sciences, Engineering and Technology, 5(06): 2238-2244.
    Advertise with us
 
ISSN (Online):  2040-7467
ISSN (Print):   2040-7459
Submit Manuscript
   Current Information
   Sales & Services
   Contact Information
  Executive Managing Editor
  Email: admin@maxwellsci.com
  Publishing Editor
  Email: support@maxwellsci.com
  Account Manager
  Email: faisalm@maxwellsci.com
  Journal Editor
  Email: admin@maxwellsci.com
  Press Department
  Email: press@maxwellsci.com
Home  |  Contact us  |  About us  |  Privacy Policy
Copyright © 2009. MAXWELL Science Publication, a division of MAXWELLl Scientific Organization. All rights reserved