STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Image Processing & Pattern Recognition Progress

Comparative Analysis of Proposed FCM Clustering Integrated Enhanced Firefly-Optimized Algorithm (En-FAOFCM) for MR Image Segmentation and Performance Evaluation

  1. Partha Ghosh
  2. Sitansu Kumar Das
  3. Kalyani Mali

Abstract

Image segmentation has a significant responsibility in diagnosis and treatment of diseases. To scan patients and determine the severity of certain injuries in hospitals, magnetic resonance imaging (MRI) method is normally used. This paper emphasizes on comparative study of segmentation techniques for segmenting MRI brain images. In this regard, to group the pixels of images in the intensity space, unsupervised clustering techniques are used. Here enhanced firefly algorithm is used as the fundamental optimization technique. The proposed technique is applied on several simulated and real T1-weighted for normal magnetic resonance brain images. Results of these segmentation techniques are analyzed based on four performance metrics; UnS, OvS, InCS and Tanimoto coefficient. Also, the performance of the proposed enhanced firefly algorithm optimized fuzzy image segmentation approach has been evaluated by comparing it with some state-of-the-art segmentation algorithms. The accuracy has been evaluated by comparing the results with the ground truth of each processed image.Cite this ArticlePartha Ghosh, Sitansu Kumar Das, Kalyani Mali. Comparative Analysis of Proposed FCM Clustering Integrated Enhanced Firefly-Optimized Algorithm (En-FAOFCM) for MR Image Segmentation and Performance Evaluation. Journal of Image Processing & Pattern Recognition Progress. 2016; 3(1): 32–44p.

Keywords

Support