A synthetic database to assess segmentation algorithms

/in , , /by
A synthetic database to assess segmentation algorithms

Oliveira, Luiz S. and Britto, Alceu S. and Sabourin, Robert

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR 2005

Abstract : In this paper we describe a synthetic database composed of 273,452 handwritten touching digits pairs to assess segmentation algorithms. It contains several different kinds of touching and it was generated by connecting 2,000 images of isolated digits extracted from the NIST SD19. In order to get a better insight on the proposed database and establish some parameters for further comparisons, we carried out experiments using four state-of-the-art segmentation algorithms. © 2005 IEEE.

You might also like
Intensity-based hierarchical clustering in CT-scans : application to interactive segmentation in cardiology
Synthetic parameters for handwriting classification
Mutual information deep regularization for semi-supervised segmentation
Incremental local linear fuzzy classifier in fisher space
Multi-task joint learning of 3D keypoint saliency and correspondence estimation
A new objective function for ensemble selection in random subspaces
Building PC clusters: an object-oriented approach
Pixel level image fusion for medical imaging: an energy minimizing approach