摘要
图像分割被认为是图像处理中的一个重要步骤。模糊c-均值聚类(FCM)是图像分割的常用方法之一。为了克服模糊c-均值聚类算法容易陷入局部最优的不足,该算法在中智学理论的基础上将模糊c-均值聚类和量子粒子群算法相结合。首先,根据中智学模糊理论将图像转换成中智图像,然后通过α均值、图像增强算法对中智图像进行预处理,最后用QPSO-FCM算法进行分割。在实验中,自然图像以及医学图像都被用来验证这些方法,无论图像是否加入噪声,相比于其他算法,其分割边界都较为清晰。
Image segmentation is considered an important step in image processing.Fuzzy C-means clustering(FCM)is one of the commonly used methods in image segmentation.In order to overcome the shortcomings of fuzzy c-means clustering algorithm,which is prone to falling into local optima,this algorithm combines fuzzy c-means clustering with quantum particle swarm optimization algorithm based on the theory of neutrosophy.Firstly,according to the fuzzy theory of neutrosophy,convert the image into neutrosophic image,and then use α The mean and image enhancement algorithms preprocess the neutrosophic image,and finally use the QPSO-FCM algorithm for segmentation.In the experiment,both natural images and medical images were used to validate these methods.Regardless of whether noise was added to the images,their segmentation boundaries were clearer compared to other algorithms.
作者
王晓莉
白二净
Wang Xiaoli;Bai Erjing(Qingdao Huanghai University,Qingdao,China)
出处
《科学技术创新》
2024年第17期98-101,共4页
Scientific and Technological Innovation
关键词
图像分割
FCM
QPSO
中智学
医学图像分割
image segmentation
FCM
QPSO
neutrosophic theory
medical image segmentation