The incremental online k-means clustering algorithm and its application to color quantization
作者：
Highlights：
• A novel color quantization (CQ) algorithm, incremental online k-means (IOKM), is introduced.
• IOKM is deterministic and does not require an explicit center initialization.
• IOKM was tested on various test images and compared to classic and state-of-the-art CQ algorithms.
• IOKM is competitive with the best CQ algorithm tested while being 1–2 orders of magnitude faster.
• IOKM can be used to cluster other types of higher-dimensional numerical data.
摘要
•A novel color quantization (CQ) algorithm, incremental online k-means (IOKM), is introduced.•IOKM is deterministic and does not require an explicit center initialization.•IOKM was tested on various test images and compared to classic and state-of-the-art CQ algorithms.•IOKM is competitive with the best CQ algorithm tested while being 1–2 orders of magnitude faster.•IOKM can be used to cluster other types of higher-dimensional numerical data.
论文关键词：Color quantization,Clustering,Batch k-means,Online k-means,Binary splitting,Quasirandom sampling
论文评审过程：Received 6 November 2021, Revised 24 May 2022, Accepted 18 June 2022, Available online 5 July 2022, Version of Record 11 July 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117927
