摘要
针对Chan-Vese（CV）模型无法完整分割目标包含多色彩及色彩具有突变性图像的问题,通过K-means聚类对图像演化曲线内部像素进行处理,得出聚类中心点,用聚类中心点值与均值滤波后图像的灰度信息构造CV模型内部拟合值,从而提高模型对复杂目标图像分割的适应性.此外,用矩形脉冲函数代替CV模型能量泛函中的正则化脉冲函数,可将水平集演化方程的计算限定在零水平集附近,从而避免图像背景干扰物对分割结果的影响.实验结果表明：改进模型可准确、快速地分割目标包含多色彩及色彩具有突变性的图像.
As Chan-Vese（CV） model could not fully segment the image of object color are diversity and mutability,thus an improved CV model was proposed.The internal pixels of image evolution contours were processed by K-means clustering,and the clustering center point values were obtained.The internal fitting values of CV model was constructed by the clustering center point values and the image mean filtered intensity information,thereby improving the adaptability of CV model for complex object image segmentation.In addition,rectangular Dirac function was used to replace regularized Dirac function in the energy function of CV model,and the calculation of level set evolution equation could be limited to the zero level set so as to avoid the influence of the image background disturbance on the segmentation result.The experimental result shows that the improved CV model can accurately and quickly segment the multi-color and color-mutation object image.
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2018年第1期63-66,86,共5页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
基金
国家自然科学基金资助项目(61362034,81360229)
甘肃省高等学校科研资助项目(2016B-025)
甘肃省基础研究创新群体项目(1506RJIA031)
