Bio-Cell Image Segmentation Using Bayes Graph-Cut Model
MetadataShow full item record
The accurate segmentation of biomedical images has become increasingly important for recognizing cells that have the phenotype of interest in biomedical applications. In order to improve the conventional deterministic segmentation models, this paper proposes a novel graph-cut cell image segmentation algorithm based on Bayes theorem. There are two segmentation phases in this method. The first phase is an interactive process to specify a preliminary set of regional pixels and the background based on the interactive graph-cut model. In the second phase, final segmentation is calculated based on the idea of Bayes theorem, combining prior information with data. Our idea can be considered an integration of graph-cut methods and Bayes theorem for cell image segmentation. Experimental results show that the proposed model performs better in comparison with several existing methods.
2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Pattern Recognition and Data Mining