Two-layer Clustering Method for Mammogram Segmentation Based on Pixel Blurriness
Yi‐Chong Zeng · 2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · 2021
Segmentation plays a significant role in various applications. The clustering algorithm is a general way to realize image segmentation. However, the parameter setting is a challenge, the improper parameter results in over-segmentation. In this paper, we propose a two-layer clustering method to segment mammograms based on pixel blurriness. In the first layer of operation, the proposed method implements K-means, principal component analysis (PCA), and watershed segmentation. Subsequently, we employ the self-organizing map (SOM) to cluster segmented areas in the second layer. The experiment results demonstrate that our method achieves better performance than the compared approaches in segmentation.