A novel centroid update approach for clustering-based superpixel methods and superpixel-based edge detection
This work addresses noise robustness in image processing for applications like superpixel generation and edge detection, representing an incremental improvement.
The paper tackles the sensitivity of clustering-based superpixel methods to noise by proposing a novel centroid update approach based on noise features, and introduces a superpixel-based edge detection method, showing significant performance enhancements on the BSD500 dataset.
Superpixel is widely used in image processing. And among the methods for superpixel generation, clustering-based methods have a high speed and a good performance at the same time. However, most clustering-based superpixel methods are sensitive to noise. To solve these problems, in this paper, we first analyze the features of noise. Then according to the statistical features of noise, we propose a novel centroid update approach to enhance the robustness of clustering-based superpixel methods. Besides, we propose a novel superpixel-based edge detection method. The experiments on BSD500 dataset show that our approach can significantly enhance the performance of clustering-based superpixel methods in noisy environment. Moreover, we also show that our proposed edge detection method outperforms other classical methods.