Abstract | ||
---|---|---|
Over-segmentation could be relieved by adopting a divisive image segmentation model. This also requires the binary classification of whether a segmented region corresponds to a single semantic object. In this paper, we propose a model to address this classification problem, by detecting if a region contains both "background" and "foreground" regions. When "background" and "foreground" both present, the region is considered to have multiple objects, otherwise it corresponds to a single object. We implement the model based on certain image features of the region that effectively tell the difference between "background" and "foreground". Experiments show that our model can effectively perform the classification tasks. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/ICME.2003.1220902 | ICME |
Keywords | Field | DocType |
single object,image region,classification task,segmented region corresponds,certain image feature,classification problem,binary classification,divisive image segmentation model,single semantic object,multiple object,computer science,image segmentation,computer vision,image features,object recognition,clustering algorithms,support vector machines,image classification | Computer vision,Pattern recognition,Binary classification,Feature (computer vision),Support vector machine classifier,Computer science,Support vector machine,Image segmentation,Artificial intelligence,Cluster analysis,Contextual image classification,Cognitive neuroscience of visual object recognition | Conference |
ISBN | Citations | PageRank |
0-7803-7965-9 | 4 | 0.56 |
References | Authors | |
4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wei Wang | 1 | 51 | 4.27 |
Aidong Zhang | 2 | 2970 | 405.63 |
Yuqing Song | 3 | 181 | 22.44 |