We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
CRF-Based Figure/Ground Segmentation with Pixel-Level Sparse Coding and Neighborhood Interactions.
- Authors
Lihe Zhang; Yongri Piao
- Abstract
In this paper, we propose a new approach to learning a discriminative model for figure/ground segmentation by incorporating the bag-of-features and conditional random field (CRF) techniques. We advocate the use of image patches instead of superpixels as the basic processing unit. The latter has a homogeneous appearance and adheres to object boundaries, while an image patch often contains more discriminative information (e.g., local image structure) to distinguish its categories. We use pixel-level sparse coding to represent an image patch. With the proposed feature representation, the unary classifier achieves a considerable binary segmentation performance. Further, we integrate unary and pairwise potentials into the CRF model to refine the segmentation results. The pairwise potentials include color and texture potentials with neighborhood interactions, and an edge potential. High segmentation accuracy is demonstrated on three benchmark datasets: the Weizmann horse dataset, the VOC2006 cow dataset, and the MSRC multiclass dataset. Extensive experiments show that the proposed approach performs favorably against the state-of-the-art approaches.
- Subjects
CONDITIONAL random fields; PIXELS; ACCURACY; DIMENSIONAL preference; PERFORMANCE
- Publication
Journal of Information & Communication Convergence Engineering, 2015, Vol 13, Issue 3, p205
- ISSN
2234-8255
- Publication type
Article
- DOI
10.6109/jicce.2015.13.3.205