华中科技大学学报（自然科学版）2017，Vol.45Issue(8)：32-37,6.DOI:10.13245/j.hust.170807
基于改进CV模型的高原鼠兔图像分割
Ochotona curzoniae image segmentation based on the improved CV model
摘要
Abstract
Chan-Vese (CV) model cannot segment the image of intensity inhomogeneity.An improved CV model was proposed.The new model energy function was added to the restraint object's intensity inhomogeneity information in CV model energy function.The improved CV model can segment the object's intensity inhomogeneity image.In addition,the quaternary tree method and Otsu method were introduced in the image preprocessing stage,which to reduce the image search range,to reduce time consuming and to avoid setting the initial contour manually.The experimental results show that the improved CV model can achieve accurate segmentation,and it takes less time.关键词
高原鼠兔/图像分割/前景灰度不均/CV模型/水平集/前景灰度不均抑制项Key words
ochotona curzoniae/image segmentation/object's intensity inhomogeneity/chan-vese(CV) model/level set分类
信息技术与安全科学引用本文复制引用
张爱华,王帆,陈海燕..基于改进CV模型的高原鼠兔图像分割[J].华中科技大学学报（自然科学版）,2017,45(8):32-37,6.基金项目
国家自然科学基金资助项目(61362034,81360299). （61362034,81360299）
