基于超像素快速模糊聚类的印刷品图像分割方法

针对当前彩色印刷品色差检测过程中效率低、复杂性高等问题，提出了一种基于超像素快速模糊聚类的印刷品图像分割方法（SFFCM）。先用简单线性迭代聚类（SLIC）算法将图像分割为紧密相邻的超像素区域。每个超像素区域被视为一个独立的聚类单元。随后，将模糊C均值聚类（FCM）算法应用于超像素的归属关系计算中，即引入隶属度值，允许超像素归属于多个聚类中心，并通过权衡归属度值来实现模糊聚类。实验结果表明，相对于其他算法，本文方法在保持良好实时性的同时，实现了较好的分割效果，有效平衡了算法复杂度与分割效果之间的关系。

Printed Image Segmentation Based on Fast Fuzzy Clustering of Super-Pixels

Aiming at the current problems of low efficiency and high complexity in the color difference detection process of color prints, a print image segmentation method (SFFCM) based on fast fuzzy clustering of super-pixels is proposed. A simple linear iterative clustering (SLIC) algorithm is first used to segment the image into closely neighboring super-pixel regions. Each super-pixel region is considered as an independent clustering unit. Subsequently, the fuzzy C-mean clustering (FCM) algorithm is applied to the computation of the attribution relationship of the super pixels, i.e., the value of affiliation is introduced to allow the super-pixels to belong to more than one clustering centers and fuzzy clustering is achieved by weighing the values of affiliation. The experimental results show that compared with other algorithms, the method achieves better segmentation effect while maintaining good real-time performance, effectively balancing the relationship between algorithm complexity and segmentation effect.