基于多维PCNN的彩色枸杞细胞显微图像的边缘检测  

Edge detection of color images based on the improved multi-dimensional PCNN

作　　者：李志强[1] 程飞燕[2] 安黎哲[1] 马义德[2] 高清祥[1] 

机构地区：[1]兰州大学生命科学学院,兰州730000 [2]兰州大学信息科学与工程学院,兰州730000

出　　处：《兰州大学学报（自然科学版）》2009年第5期130-134,137,共6页Journal of Lanzhou University(Natural Sciences)

基　　金：国家自然科学基金项目(60572011);新世纪人才支持计划项目(NCET)

摘　　要：改进脉冲耦合神经网络模型,结合矢量运算,提出一种基于多维脉冲耦合神经网络的边缘检测模型,直接提取彩色细胞图像边缘,且本模型算法在染色不均匀造成的弱边缘检测和抗噪性能等方面表现优异。仿真和实验结果进一步表明了该算法的有效性。A new multidimensional pulse coupled neural network model was proposed, which integrated with the vector gradient to implement color image edge detection. To test the feasibility and effectiveness of multi- dimensional PCNN on edge detection of microscopic color cell images, the experiments of the microscopic cell images were carried out. Empirical results show that multi-dimensional PCNN outperforms classical methods in terms of noise resistence and accuracy of weak edge detection.

关 键 词：脉冲耦合神经网络 灰度图像 彩色图像 边缘检测 矢量梯度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]