欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
准确分割是图像处理与分析的关键。然而显微细胞图像的目标轮廓模糊、存在弱边界等问题，使得分割结果往往不尽人意。针对这一问题，提出基于混合主动轮廓模型和区域间差别最大化的细胞弱边界分割方法。该模型根据区域最大化的原则，并采用局部和全局灰度信息作模型的驱动力，在确保检测出全局差异的同时，捕捉到局部差异性。模型的能量泛函是由局部和全局拟合项组成的，并引入策略权重参数，这个参数利用梯度信息来解释局部拟合项和全局拟合项是如何组成混合拟合项的。实验结果表明，这种基于混合主动轮廓模型和区域间差别最大化的细胞分割方法能有效地捕获弱边界并分割出细胞核。
英文摘要：
Accurate segmentation is the key to image processing and analysis. However there are problems with microscopic cell images like target contour obscure or existing weak borders etc. which usually produces unsatisfactory segmenting results. To tackle the problem, the paper proposes a hybrid active contour model and inter-regional difference maximization based cell weak border segmentation method. The method conforms to region maximization principle, taking local and global gray information as model＇s driving force, on the one hand ensures the detection of global dissimilarities,and on the other hand captures local differences. The models energy functional are composed of local and global fitting items by introducing a strategy weight parameter which makes use of graded information to explain how do local fitting items and global fitting items combine together to form hybrid fitting items. Experimental results indicate that the hybrid active contour model and inter-regional difference maximization based cell segmentation method can effectively capture weak borders and separate cell nucleus apart.
同期刊论文项目
同项目期刊论文
A Hierarchical Model Incorporating Segmented Regions and Pixel Descriptors for Video Background Subt
Discover Novel Visual Categories from Dynamic Hierarchies Using Multimodal Attributes [长文：动态继承方法以从未知
A Hybrid Neuro-Fuzzy Network Based on Differential Biogeography-Based Optimization for Online Popula
Distributed Leader-Following Finite-Time Consensus Control for Linear Multiagent Systems under Switc
Finding Optimal Focusing Distance and Edge Blur Distribution for Weakly Calibrated 3D Vision [长文：最佳聚
A double-loop structure in the adaptive generalized predictive control algorithm for control of robo
期刊信息
位置：