Scene text detection based on pruning strategy of MSER-trees and Linkage-trees

Jin Ma, Weiqiang Wang, Ke Lu, Jianshe ZhouICME 2017 · OpenReview

Abstract

The extraction and recognition of scene text in images is an important way to understand the semantic information in image. By now, scene text detection is still a challenging problem. In this paper, we present a scene text localization method based on the pruning of Maximally Stable Extremal Region (MSER) tree and Linkage-tree. Concretely, the MSER-tree is first constructed and overlap MSERs are removed by the nonmaximum suppression strategy. Further, the linkage-trees are constructed and pruned based on the features considering the nodes themselves and their siblings. Finally, the non-text lines are eliminated based on to the CNN-based features and intensity contrast. Experimental results on two challenging datasets demonstrate the effectiveness of the proposed method.
BibTeX
@inproceedings{ma2017scene,
  author = {Jin Ma and Weiqiang Wang and Ke Lu and Jianshe Zhou},
  title = {{Scene text detection based on pruning strategy of MSER-trees and Linkage-trees}},
  booktitle = {ICME},
  year = {2017},
  url = {https://openreview.net/forum?id=QnNcBrbh_aP},
}

Loading related content...

Figure