Automatic ore image segmentation using mean shift and watershed transform

Amankwah, A.; Aldrich, Chris

doi:10.1109/RADIOELEK.2011.5936391

Access Status

Fulltext not available

Authors

Amankwah, A.

Aldrich, Chris

Date

2011

Type

Conference Paper

Metadata

Show full item record

Citation

Amankwah, A. and Aldrich, C. 2011. Automatic ore image segmentation using mean shift and watershed transform, in Proceedings of the 21st International Conference Radioelektronika (RADIOELEKTRONIKA), Apr 19-20 2011, pp. 245-248. Brno, Amankwah, A. and Aldrich, C. 2011. Automatic ore image segmentation using mean shift and watershed transform, in Proceedings of the 21st International Conference Radioelektronika (RADIOELEKTRONIKA), Apr 19-20 2011, pp. 245-248. Brno: Czech Republic: IEEE.

Source Title

Proceedings of 21st International Conference, Radioelektronika 2011

DOI

10.1109/RADIOELEK.2011.5936391

ISBN

9781612843223

School

Dept of Mining Eng & Metallurgical Eng

URI

http://hdl.handle.net/20.500.11937/20170

Collection

Curtin Research Publications

Abstract

In this paper, we present a novel method for segmenting ore images specifically for estimating the size distribution of ore material on conveyer belt. The segmentation system uses the mean shift and watershed algorithm. The mean shift algorithm is used to identify pixel clusters of particular modes of the probability density function of the image data. The pixel clusters are then used to generate markers for the watershed transform and shadow areas in ore image. Experimental results show that the proposed algorithm is not only faster than the standard methods but also more robust.