基于栅格元的脉冲耦合神经网络模型
Pulse Couple Neural Network Based on Grat-ing Cells
DOI: 10.12677/CSA.2018.89145, PDF,    科研立项经费支持
作者: 潘 改*, 孔祥勇：江苏师范大学电气工程及自动化学院，江苏 徐州
关键词: 栅格元；脉冲耦合神经网络模型；响应函数；Grating Cells； Pulse Couple Neural Network； Influence Function
摘要: 传统脉冲耦合神经网络模型描述神经元之间的内在联系时，仅仅考虑神经元之间的空间位置信息，忽略了神经元之间的灰度信息，使神经元之间的连接权值不准确，易产生误分割现象。为了解决这一问题，本文采用栅格元的响应函数作为神经元之间的连接权值，得到新的连接输入项。在新的连接权值中，不仅考虑了局部区域的灰度信息，而且考虑了局部区域的方差信息，同时继承了栅格元神经元的优点，即具有较强的方向性、位置相对性和周期性。通过对遥感图像、生活图像、血管图像进行仿真对比实验，实验结果说明本文提出的算法优于传统脉冲耦合神经网络模型。
Abstract: Describing relationship between neurons in the classical pulse couple neural network, it only considers spatial location information between neurons, and neglects gray information, which makes dynamic synapse weight inaccurate and easily produces missegmentation. To overcome this problem, this paper uses influence function of grating cells as dynamic synapse weight between neurons, and gets a new linking item. In the new linking item, it not only considers gray information in a local region, but also considers variance information; at the same time, it has advantages of grating cells, which means appropriate orientation, position and periodicity. Simulation experiments illustrate segmentation of this method is better than the classical pulse coupled neural network model, further verify the effectiveness of this method.
文章引用：潘改, 孔祥勇. 基于栅格元的脉冲耦合神经网络模型[J]. 计算机科学与应用, 2018, 8(9): 1341-1346. https://doi.org/10.12677/CSA.2018.89145

参考文献

[1] Eckhom, R., Reiboeck, H.J., Arndt, M., et al. (1990) Feature Linking via Synchronization among Distributed Assemblies: Simulation of Results from Cat Cortex. Neural Computation, 2, 293-307. [Google Scholar] [CrossRef] 
[2] Johnson, J.L. and Padgett, M.L. (1999) PCNN Models and Applications. IEEE Transactions, 10, 480-498.
[3] Wang, Z.B., Ma, Y.D., Cheng, F.Y., et al. (2010) Review of Pulse-Coupled Neural Networks. Image and Vision Computing, 28, 5-13. [Google Scholar] [CrossRef] 
[4] Monica Subashini, M. and Sahoo, S.K. (2014) Pulse Coupled Neural Networks and Its Applications. Expert Systems with Applications, 41, 3965-3974. [Google Scholar] [CrossRef] 
[5] 邓翔宇, 马义德. PCNN参数自适应设定及其模型的改进[J]. 电子学报, 2012, 40(5): 955-964.
[6] 周东国, 高潮, 郭永彩. 一种参数自适应的简化PCNN图像分割方法[J]. 自动化学报, 2014, 40(6): 1191-1197.
[7] He, F.L., Guo, Y.C. and Gao, C. (2018) A Pa-rameter Estimation Method of the Simple PCNN Model for Infrared Human Segmentation. Optics and Laser Technology.
[8] Gao, C., Zhou, D.G. and Guo, Y.C. (2013) Automatic Iterative Algorithm for Image Segmentation Using a Modified Pulse-Coupled Neural Network. Neurocomputing, 119, 332-338. [Google Scholar] [CrossRef] 
[9] Yang, Z., Lian, J., Li, S.L., et al. (2018) Heterogeneous SPCNN and Its Application in Image Segmentation. Neurocomputing, 285, 196-203. [Google Scholar] [CrossRef] 
[10] Jiang, W., Zhou, H.Y., Shen, Y., et al. (2015) Image Segmentation with Pulse Coupled Neural Network and Canny Operators. Computers and Electrical Engineering, 46, 528-538. [Google Scholar] [CrossRef] 
[11] Wei, W.Y., Li, Y.S. and Ma, Y.D. (2016) CNN-Based Level Set Method of Automatic Mammographic Image Segmentation. Optic, 127, 1644-1650.
[12] Xu, G.Z., Li, X.Y., Lei, B.J., et al. (2018) Unsuper-vised Color Image Segmentation with Color-Alone Feature Using Region Growing Pulse Coupled Neural Network. Neurocomputing, 306, 1-16. [Google Scholar] [CrossRef] 
[13] Guo, Y.N., Yang, Z., Ma, Y.D., et al. (2018) Saliency Motivated Improved Simplified PCNN Model for Object Segmentation. Neurocomputing, 275, 2179-2190. [Google Scholar] [CrossRef] 
[14] Kruizinga, P. and Petkov, N. (1999) Nonlinear Operator for Oriented Texture. IEEE Transactions on Image Processing, 8, 1395-1407. [Google Scholar] [CrossRef] [PubMed]
[15] Daugman, J.G. (1985) Uncer-tainty Relation for Resolution in Space, Spatial Frequency, and Orientation Optimized by Two-Dimensional Visual Cortical Filters. Journal of the Optical Society of America A, 2, 1160-1169. [Google Scholar] [CrossRef] 
[16] Jones, J.P. and Palmer, L.A. (1987) An Evaluation of the Two-Dimensional Ga-bor Filter Model of Simple Receptive Fields in Cat Striate Cortex. Journal of Neurophysiology, 58, 1233-1258. [Google Scholar] [CrossRef] [PubMed]