Published November 24, 2025 | Version 1.0
Image Open

Image Segmentation Using Fuzzy C-Mean

Authors/Creators

Description

Image segmentation plays a crucial role in image processing and computer vision applications. This paper presents an efficient segmentation approach using the Fuzzy C-Means (FCM) clustering algorithm. Unlike hard clustering methods, FCM allows each pixel to belong to multiple clusters with different membership degrees, leading to smoother and more accurate segmentation. The proposed method is applied on sample images, and the results demonstrate improved region separation and robustness against noise. This study highlights the effectiveness of FCM for medical imaging, pattern recognition, and object detection tasks.

Files

Image_Segmentation (3).pdf

Files (724.5 kB)

Name Size Download all
md5:41ec724c6c2ec969cdfaacd8f12abd5e
724.5 kB Preview Download

Additional details

Software

Programming language
Python

References

  • A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data | Ahmed et al., 2002 | MRI segmentation with intensity inhomogeneity | Bias-corrected FCM with neighborhood term | Corrects bias field | Robust MRI tissue classification | Computationally heavy | Better accuracy than classical FCM in MRI
  • Fuzzy c-means clustering with spatial information for image segmentation | Chuang et al., 2006 | Noise-robust image segmentation | Spatial averaging in FCM | Neighborhood effect included | Good noise tolerance | Blurs edges sometimes | Improves segmentation vs FCM on noisy images
  • A robust fuzzy local information C-means clustering algorithm | Krinidis & Chatzis, 2010 | Segmentation under noise | Adds fuzzy local factor to objective | Noise-resilient clustering | Strong robustness to impulse noise | Higher runtime | Superior to FCM in noisy conditions
  • Fast generalized fuzzy c-means clustering algorithm for image segmentation | Cai et al., 2007 | Efficient segmentation | Generalized objective with local similarity | Faster convergence | Good tradeoff of speed and quality | Less accurate on severe inhomogeneity | Faster than FCM with good accuracy
  • A novel kernelized fuzzy C-means algorithm with application in image segmentation | Zhang & Chen, 2004 | Nonlinear segmentation | Kernel metric in FCM | Handles complex clusters | Separates overlapping classes | Kernel choice needed | Better accuracy than FCM
  • Adaptive fuzzy segmentation of magnetic resonance images | Pham & Prince, 1999 | Adaptive MRI segmentation | Adaptive smoothing in FCM | Adjusts to local variation | Handles noise & bias | Window size sensitive | Improves MRI segmentation quality