Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
528922 | Image and Vision Computing | 2011 | 13 Pages |
The ultimate opening (UO) is a powerful segmentation operator recently introduced by Beucher [1]. It automatically selects the most contrasted regions of an image. However, in the presence of nested structures (e.g. text in a signboard or windows in a contrasted facade), interesting structures may be masked by the containing region. In this paper we focus on ultimate attribute openings and we propose a method that improves the results by favoring regions with a predefined shape via a similarity function. An efficient implementation using a max-tree representation of the image is proposed. The method is validated in the framework of three applications: facade analysis, scene-text detection and cell segmentation. Experimental results show that the proposed method yields better segmentation results than UO.
Graphical abstractShape ultimate attribute opening provides good segmentation results. The method handles difficult situations: low contrast, multi-scale, perspective effects and different fonts. Text segmentation examples are shown.Figure optionsDownload full-size imageDownload high-quality image (494 K)Download as PowerPoint slideResearch highlights► Ultimate Attribute Opening (UAO) is a powerful multi-scale segmentation operator. ► Our method combines UAO with shape information, favoring regions of a predefined shape. ► Much better results are obtained, at the expense of a marginal increase in the computation time. ► The approach has been validated in three applications (facade, text and cell segmentation).