Wenzhou University of Technology, Wenzhou, 325035, China.
School of Artificial Intelligence, Jilin International Studies University, Changchun, 130000, China.
Comput Biol Med. 2021 Dec;139:104941. doi: 10.1016/j.compbiomed.2021.104941. Epub 2021 Oct 19.
An appropriate threshold is a key to using the multi-threshold segmentation method to solve image segmentation problems, and the swarm intelligence (SI) optimization algorithm is one of the popular methods to obtain the optimal threshold. Moreover, Salp Swarm Algorithm (SSA) is a recently released swarm intelligent optimization algorithm. Compared with other SI optimization algorithms, the optimization solution strategy of the SSA still needs to be improved to enhance further the solution accuracy and optimization efficiency of the algorithm. Accordingly, this paper designs an effective segmentation method based on a non-local mean 2D histogram and 2D Kapur's entropy called SSA with Gaussian Barebone and Stochastic Fractal Search (GBSFSSSA) by combining Gaussian Barebone and Stochastic Fractal Search mechanism. In GBSFSSSA, the Gaussian Barebone and Stochastic Fractal Search mechanism effectively balance the global search ability and local search ability of the basic SSA. The CEC2017 competition data set is used to prove the algorithm's performance, and GBSFSSSA shows an absolute advantage over some typical competitive algorithms. Furthermore, the algorithm is applied in image segmentation of COVID-19 CT images, and the results are analyzed based on three different metrics: peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM), which can lead to the conclusion that the overall performance of GBSFSSSA is better than the comparison algorithm and can effectively improve the segmentation of medical images. Therefore, it is justified that GBSFSSSA is a reliable and effective method in solving the multi-threshold image segmentation problem.
适当的阈值是使用多阈值分割方法解决图像分割问题的关键，而群体智能 (SI) 优化算法是获得最佳阈值的流行方法之一。此外，沙蚕群智能算法 (SSA) 是最近发布的一种群体智能优化算法。与其他 SI 优化算法相比，SSA 的优化求解策略仍需改进，以进一步提高算法的求解精度和优化效率。因此，本文通过结合高斯裸核和随机分形搜索机制，设计了一种基于非局部均值 2D 直方图和 2D Kapur 熵的有效分割方法，称为带有高斯裸核和随机分形搜索的 SSA（GBSFSSSA）。在 GBSFSSSA 中，高斯裸核和随机分形搜索机制有效地平衡了基本 SSA 的全局搜索能力和局部搜索能力。使用 CEC2017 竞赛数据集验证了算法的性能，GBSFSSSA 相对于一些典型的竞争算法具有绝对优势。此外，该算法还应用于 COVID-19 CT 图像的分割，基于三个不同的度量标准（峰值信噪比 (PSNR)、结构相似性 (SSIM) 和特征相似性 (FSIM)）对结果进行分析，这可以得出结论，GBSFSSSA 的整体性能优于对比算法，能够有效提高医学图像的分割效果。因此，GBSFSSSA 是解决多阈值图像分割问题的可靠而有效的方法。
