A multiresolution image segmentation technique based on pyramidal segmentation and fuzzy clustering

In this paper, an unsupervised image segmentation technique is presented, w hich combines pyramidal image segmentation with the fuzzy c-means clusterin g algorithm. Each layer of the pyramid is split into a number of regions by a root labeling technique, and then fuzzy c-means is used to merge the reg ions of the layer with the highest image resolution. A cluster validity fun ctional is used to find the optimal number of objects automatically, Segmen tation of a number of synthetic as well as clinical images is illustrated a nd two fully automatic segmentation approaches are evaluated, which determi ne the left ventricular volume (LV) in 140 cardiovascular magnetic resonanc e (MR) images, First fuzzy c-means is applied without pyramids. In the seco nd approach the regions generated by pyramidal segmentation are merged by f uzzy c-means. The correlation coefficients of manually and automatically de fined LV lumen of all 140 and 20 end-diastolic images were equal to 0.86 an d 0.79, respectively, when images were segmented with fuzzy c-means alone. These coefficients increased to 0.90 and 0.94 when the pyramidal segmentati on was combined with fuzzy c-means. This method can be applied to any dimen sional representation and at any resolution level of an image series, The e valuation study shows good performance in detecting LV lumen in MR images.