计算机应用 ›› 2020, Vol. 40 ›› Issue (9): 2743-2747.DOI: 10.11772/j.issn.1001-9081.2020010106

• 虚拟现实与多媒体计算 • 上一篇    下一篇

距离保持水平集演化模型的快速实现算法

原泉1, 王艳1, 李玉先2   

  1. 1. 重庆师范大学 数学科学学院, 重庆 401331;
    2. 重庆市中医院 药剂科, 重庆 400011
  • 收稿日期:2020-02-07 修回日期:2020-04-03 出版日期:2020-09-10 发布日期:2020-04-09
  • 通讯作者: 王艳
  • 作者简介:原泉(1994-),女,河南郑州人,硕士研究生,主要研究方向:图像处理的偏微分方程方法;王艳(1984-),女,山东青岛人,教授,博士,主要研究方向:图像处理的偏微分方程方法;李玉先(1979-),女,湖北宜昌人,副主任药师,硕士,主要研究方向:医院药学和药事管理、医学影像药物。
  • 基金资助:
    国家自然科学基金青年基金资助项目(11901071);重庆市自然科学基金面上项目(cstc2019jcyj-msxmX0219);重庆市教委科学技术研究项目青年项目(KJQN201800506);重庆师范大学博士启动基金资助项目(17XLB001);浙江省博士后科研项目(514000-X81902)。

Fast algorithm for distance regularized level set evolution model

YUAN Quan1, WANG Yan1, LI Yuxian2   

  1. 1. School of Mathematical Sciences, Chongqing Normal University, Chongqing 401331, China;
    2. Pharmacy Department, Chongqing Traditional Chinese Medicine Hospital, Chongqing 400011, China
  • Received:2020-02-07 Revised:2020-04-03 Online:2020-09-10 Published:2020-04-09
  • Supported by:
    This work is partially supported by the Youth Program of the National Natural Science Foundation of China (11901071), the Surface Program of the Natural Science Foundation of Chongqing (cstc2019jcyj-msxmX0219), the Youth Science and Technology Research Program of the Educational Commission of Chongqing (KJQN201800506), the Doctor Start Fund of Chongqing Normal University (17XLB001), the Zhejiang Postdoctoral Scientific Research Program (514000-X81902).

摘要: 针对梯度下降法收敛性较差、对局部极小值比较敏感的问题,提出一种改进NAG算法,并以此替换距离保持水平集演化(DRLSE)模型中的梯度下降算法,进而得到一个基于NAG的图像快速分割算法。首先,给出初始水平集演化方程;其次,用改进NAG算法计算梯度;最后,对水平集函数进行不断更新,从而避免水平集函数陷入局部极小值。实验结果表明,与DRLSE模型中的原算法相比,所提算法迭代次数减少了约30%,CPU运行时间减少了30%以上。该算法实现简单,能够对实时性要求较高的红外图像、医学图像进行快速、有效的分割。

关键词: 图像分割, 水平集方法, 活动轮廓模型, 距离保持水平集演化模型, NAG算法

Abstract: The gradient descent method has poor convergence and is sensitive to local minimum. Therefore, an improved NAG (Nesterov’s Accelerated Gradient) algorithm was proposed to replace the gradient descent algorithm in the Distance Regularized Level Set Evolution (DRLSE) model, so as to obtain a fast image segmentation algorithm based on NAG algorithm. First, the initial level set evolution equation was given. Second, the gradient was calculated by using the NAG algorithm. Finally, the level set function was updated continuously, avoiding the level set function falling into local minimum. Experimental results show that compared with the original algorithm in the DRLSE model, the proposed algorithm has the number of iterations reduced by about 30%, and the CPU running time reduced by more than 30%. The algorithm is simple to implement, and can be applied to segment the images with high real-time requirement such as infrared images and medical images .

Key words: image segmentation, level set method, active contour model, Distance Regularized Level Set Evolution (DRLSE) model, NAG (Nesterov's Accelerated Gradient) algorithm

中图分类号: