Name
Abstract | ||
|---|---|---|
Constructing a discriminative affinity graph plays an essential role in graph-based image segmentation, and feature directly influences the discriminative power of the affinity graph. In this paper, we propose a new method based on the weighted color patch to compute the weight of edges in an affinity graph. The proposed method intends to incorporate both color and neighborhood information by representing pixels with color patches. Furthermore, we assign both local and global weights adaptively for each pixel in a patch in order to alleviate the over-smooth effect of using patches. The normalized cut (NCut) algorithm is then applied on the resulting affinity graph to find partitions. We evaluate the proposed method on the Prague color texture image benchmark and the Berkeley image segmentation database. The extensive experiments show that our method is competitive compared to the other standard methods with multiple evaluation metrics. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICIP.2013.6738837 | ICIP |
Keywords | Field | DocType |
multiple evaluation metrics,image representation,weighted color patch,ncut algorithm,pixel representation,image segmentation,graph-based image segmentation,berkeley image segmentation database,affinity graph,discriminative affinity graph,normalized cut algorithm,graph theory,normalized cuts,image texture,prague color texture image benchmark,image colour analysis,normalized | Computer vision,Scale-space segmentation,Pattern recognition,Color histogram,Image texture,Computer science,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Region growing,Connected-component labeling,Color image | Conference |
ISSN | Citations | PageRank |
1522-4880 | 1 | 0.36 |
References | Authors | |
18 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaofang Wang | 1 | 65 | 7.63 |
| Chao Zhu | 2 | 126 | 23.97 |
| Charles-Edmond Bichot | 3 | 174 | 11.97 |
| Simon Masnou | 4 | 124 | 9.26 |