作者: Salim Ben Chaabane , Mounir Sayadi , Farhat Fnaiech , Eric Brassart
DOI: 10.1155/2010/367297
关键词: Artificial intelligence 、 Mathematics 、 Computer vision 、 Segmentation-based object categorization 、 Fuzzy logic 、 Histogram 、 Image segmentation 、 Segmentation 、 Image processing 、 Homogeneity (statistics) 、 Scale-space segmentation
摘要: A novel method of colour image segmentation based on fuzzy homogeneity and data fusion techniques is presented. The general idea mass function estimation in the Dempster-Shafer evidence theory histogram extended to domain. vector used determine region each primitive colour, whereas, employed merge different sources order increase quality information obtain an optimal segmented image. Segmentation results from proposed are validated classification accuracy for test available evaluated, then a comparative study versus existing experimental demonstrate superiority introducing segmentation.