Abstract | ||
---|---|---|
This paper presents a novel region merging segmentation method for color image based on color and texture distribution features. The segmentation strategy includes two phases. In the first phase, we select initial seed points for superpixels extraction in the texture energy image at average intervals. Then we implement pixels clustering to extract over segmentation regions at local areas using color and texture information. In the second phase, a hybird texture histograms is introduced to represent the local color distribution information of internal pixels in over segmentation regions. The region merging employs computing corresponding histograms, which are normalized into fixed bins. Experiment results on Berkeley Segmentation Dataset (BSD) demonstrated that the proposed segmented algorithm can achieve good applications on the nature images with complex textures. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/CIS.2013.54 | CIS |
Keywords | Field | DocType |
complex texture,super pixels extraction,color information,texture distribution feature,pattern clustering,over-segmentation,color image segmentation,pixels clustering,segmentation method,image segmentation,hybird texture histograms,texture distribution features,bsd,color image,segmentation strategy,segmentation region,region merging,berkeley segmentation dataset,hybird histograms,texture information,local color distribution information,texture energy image,histogram feature,feature extraction,texture region merging,color features,region merging segmentation method,image texture,hybird texture histogram,image colour analysis,initial seed point selection | Computer vision,Scale-space segmentation,Color histogram,Pattern recognition,Image texture,Computer science,Segmentation-based object categorization,Image segmentation,Region growing,Artificial intelligence,Minimum spanning tree-based segmentation,Color image | Conference |
ISBN | Citations | PageRank |
978-1-4799-2548-3 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haifeng Sima | 1 | 5 | 2.88 |
Ping Guo | 2 | 601 | 85.05 |