Image labeling by multiple segmentation

Quan Zhou, Canxiang Yan, Yingying Zhu, Xiang Bai, Wenyu Liu

Abstract

In this paper, we provide a method for image labeling by combining the local features and contextual cues in a multiple segmentation framework. Our main insight is to weight the classification results of each image region in different levels, which are obtained by a series of learned discriminative models based on bag of features. The contextual cues are implicitly embedded as feature selection in learning process. Multiple segmentation framework provides robust representation, allowing a wide variety of cues to contribute to the confidence in each semantic label. Our algorithm has been applied on the lotus hill institute(LHI) 15-class dataset and outperforms other state-of-the-art methods.
BibTeX
@inproceedings{zhou2011image,
  author = {Quan Zhou and Canxiang Yan and Yingying Zhu and Xiang Bai and Wenyu Liu},
  title = {{Image labeling by multiple segmentation}},
  booktitle = {ICIP},
  year = {2011},
  doi = {10.1109/icip.2011.6116329},
}

Loading related content...

Figure