Multiresolution Adaptive K-means Algorithm for Segmentation of Brain MRI
ICSC '95 Proceedings of the Third International Computer Science Conference on Image Analysis Applications and Computer Graphics
Convergence Analysis of Recurrent Neural Networks (Network Theory and Applications, V. 13)
Convergence Analysis of Recurrent Neural Networks (Network Theory and Applications, V. 13)
A Competitive-Layer Model for Feature Binding and Sensory Segmentation
Neural Computation
Foundations of implementing the competitive layer model by Lotka-Volterra recurrent neural networks
IEEE Transactions on Neural Networks
Color-Based Image Salient Region Segmentation Using Novel Region Merging Strategy
IEEE Transactions on Multimedia
IEEE Transactions on Information Technology in Biomedicine
Hi-index | 0.00 |
The competitive layer model (CLM) of the Lotka-Volterra recurrent neural networks (LV RNNs) is capable of binding similar features into a layer by competing among neurons at different layers In this paper, the CLM of the LV RNNs is used to segment brain MR image Firstly, the CLM of the LV RNNs is applied to segment each subimage into several regions; Secondly, a similar neighboring region merging algorithm is adopted to merge the similar neighboring regions into larger regions, which depends on the intensity and area ratio of two neighboring regions; Finally, the survived regions are further classified into four classes by region-based fuzzy C-means (RFCM) definitely according to four tissues in brain Comparing with other three methods, our proposed method shows better performance.