Handwritten digit segmentation: A comparative study

/in , , /by
Handwritten digit segmentation: A comparative study

Ribas, F. C. and Oliveira, L. S. and Britto, A. S. and Sabourin, R.

International Journal on Document Analysis and Recognition 2013

Abstract : In this work, algorithms for segmenting handwritten digits based on different concepts are compared by evaluating them under the same conditions of implementation. A robust experimental protocol based on a large synthetic database is used to assess each algorithm in terms of correct segmentation and computational time. Results on a real database are also presented. In addition to the overall performance of each algorithm, we show the performance for different types of connections, which provides an interesting categorization of each algorithm. Another contribution of this work concerns the complementarity of the algorithms. We have observed that each method is able to segment samples that cannot be segmented by any other method, and do so independently of their individual performance. Based on this observation, we conclude that combining different segmentation algorithms may be an appropriate strategy for improving the correct segmentation rate. © 2012 Springer-Verlag.

You might also like
A pattern reordering approach based on ambiguity detection for online category learning
Improving the reliability of music genre classification using rejection and verification
TTTFlow: Unsupervised Test-Time Training with Normalizing Flow
Gaussian mixture modeling for dynamic particle swarm optimization of recurrent problems
Merging active contours
End-to-end environmental sound classification using a 1D convolutional neural network
Weakly supervised segmentation with cross-modality equivariant constraints
MRI fuzzy segmentation of brain tissue using IFCM algorithm with genetic algorithm optimization