Edge Detection Using Fuzzy C-Means: A Comparative Study

Edge detection is a fundamental image processing technique that identifies boundaries within images by detecting abrupt intensity changes. This paper investigates the application of the Fuzzy C-Means (FCM) clustering algorithm in edge detection and compares its performance with traditional methods such as Sobel, Prewitt, and Canny. By leveraging MATLAB for implementation, the study highlights the advantages of FCM in handling overlapping data and its applicability in fields like medical imaging and computer vision. A specific focus is given to the edge detection of brain tumors in MRI images, which is a critical step in medical image analysis. The proposed methodology employs noise removal techniques to enhance image quality, followed by image segmentation using FCM, and concludes with fine edge detection using the Canny method. Experimental results on MRI images with varying tumor characteristics, such as location, size, shape, and density, demonstrate that the FCM-based approach improves segmentation accuracy by 10-15% in certain cases compared to expert assessments. This study provides valuable insights into the strengths and limitations of each technique, offering a pathway for future research in medical image processing and other computer vision applications.