一种用于视觉颜色特征分类的脉冲神经网络

苏亚丽 1; 吴健行 2; 惠维 3; 张国和 2

doi:10.7652/xjtuxb201910016

您当前的位置：

首页 >

文章列表页 >

一种用于视觉颜色特征分类的脉冲神经网络

更新时间：2025-07-09

- 一种用于视觉颜色特征分类的脉冲神经网络
- A Spiking Neural Network for Classification of Visual Color Features
- 西安交通大学学报 2019年53卷第10期页码：115-121
- 作者机构：
  
  西安石油大学机械工程学院,西安,710065
- 作者简介：
- 基金信息：
  
  : 2019-05-07。作者简介: 苏亚丽(1980—),女,博士,讲师;张国和(通信作者),男,副教授。基金项目: 国家自然科学基金资助项目(61772413)
- DOI：10.7652/xjtuxb201910016
  中图分类号： TN402
- 网络首发：2019-10-10，
  
  纸质出版：2019
- 稿件说明：
移动端阅览
苏亚丽 1, 吴健行 2, 惠维 3, 等. 一种用于视觉颜色特征分类的脉冲神经网络[J]. 西安交通大学学报, 2019,53(10):115-121.

A Spiking Neural Network for Classification of Visual Color Features[J]. 2019, 53(10): 115-121.
苏亚丽 1, 吴健行 2, 惠维 3, 等. 一种用于视觉颜色特征分类的脉冲神经网络[J]. 西安交通大学学报, 2019,53(10):115-121. DOI： 10.7652/xjtuxb201910016.

A Spiking Neural Network for Classification of Visual Color Features[J]. 2019, 53(10): 115-121. DOI： 10.7652/xjtuxb201910016.

摘要

针对脉冲神经网络(SNNs)在视觉颜色特征分类领域精度不高的问题

提出了一种基于新型RGB-HSV预处理模型的高精度脉冲神经网络。该脉冲神经网络融合了RGB颜色通道简单和HSV色彩空间直观的特点来提取聚类色彩特征

增强了网络的识别能力。此外

在Tempotron有监督学习基础上提出了一种结合权值动量的训练方式

该方式在计算当前权值更新量的同时保留一定程度的上次权值更新量

加快了网络权值的收敛速度

节省了仿真时间。仿真实验结果表明

所设计的脉冲神经网络的分类精度高达96.21%

且在6次训练迭代后精度仍可达84%左右。

Abstract

A spiking neural network with high precision based on a new RGB-HSV preprocessing model is proposed to solve the problem of low accuracy of spiking neural networks in the field of the classification of visual color features.The proposed network extracts cluster color features by combining the features of the simplicity of RGB color channels and intuitive of HSV color space and enhances the recognition ability.A training method with weight momentum is also proposed based on Tempotron supervised learning rules.The method updates weights with new calculations while some of last weights is retained

so that the convergence of network weights is speeded up and the simulation time is saved.Experimental results show that the classification accuracy of the proposed network is up to 96.21%

and the accuracy reaches about 84% after 6 training iterations.

关键词

Keywords

references

FANG Haowen, SHRESTHA A, DE Ma, et al.Scalable NoC-based neuromorphic hardware learning and inference [C]∥2018 International Joint Conference on Neural Networks.Piscataway, NJ, USA: IEEE, 2018: 1-8.

WANG W, PEDRETTI G, MILO V, et al.Computing of temporal information in spiking neural networks with ReRAM synapses [J].Faraday Discussions, 2018, 213: 453-469.

KIM J, KIM H, HUH S, et al.Deep neural networks with weighted spikes [J].Neurocomputing, 2018, 311(1): 373-386.

LI Xiumin, WANG Wei, XUE Fangzheng, et al.Computational modeling of spiking neural network with learning rules from STDP and intrinsic plasticity [J].Physica: A Statistical Mechanics and Its Applications, 2018, 491: 716-728.

SUN Qiyan, WU Qingxiang, WANG Xuan, et al.A spiking neural network for extraction of features in colour opponent visual pathways and FPGA implementation [J].Neurocomputing, 2017, 228: 119-132.

张悦, 霍宏, 方涛.基于生物视觉的颜色直方图特征提取 [J].高技术通讯, 2014, 24(4): 407-413.

ZHANG Yue, HUO Hong, FANG Tao.Color histogram feature extraction based on biological vision [J].Chinese High Technology Letters, 2014, 24(4): 407-413.

LEE J H, DELBRUCK T, PFEIFFER M.Training deep spiking neural networks using backpropagation [J].Frontiers in Neuroscience, 2016, 10: 1-10.

BALADRON J, HAMKER F H.A spiking neural network based on the basal ganglia functional anatomy [J].Neural Networks, 2015, 67: 1-13.

贾迪, 孟祥福, 孟琭, 等.RGB空间下结合高斯曼哈顿距离图的彩色图像边缘检测 [J].电子学报, 2014, 42(2): 257-263.

JIA Di, MENG Xiangfu, MENG Lu, et al.Color image edge detection combining with Gauss Manhattan distance map in RGB space [J].Acta Electronica Sinica, 2014, 42(2): 257-263.

DETHIER J, NUYUJUKIAN P, RYU S I, et al.Design and validation of a real-time spiking-neural-network decoder for brain-machine interfaces [J].Journal of Neural Engineering, 2013, 10(3): 036008.

YU Q, TANG H, TAN K C, et al.A brain-inspired spiking neural network model with temporal encoding and learning [J].Neurocomputing, 2014, 22: 3-13.

BAWANE P, GADARIYE S, CHATURVEDI S, et al.Object and character recognition using spiking neural network [J].Materials Today: Proceedings, 2018, 5(1): 360-366.

AMIR S A, STRADMANN Y, MüLLER P, et al.An accelerated LIF neuronal network array for a large-scale mixed-signal neuromorphic architecture [J].IEEE Transactions on Circuits Systems, 2018, 65(12): 4299-4312.

杨静, 徐彦, 赵欣.Spiking神经元输入脉冲扰动敏感性研究 [J].计算机工程与应用, 2017(2): 6-11.

YANG Jing, XU Yan, ZHAO Xin.Research on spiking neuron sensitivity to input perturbation [J].Computer Engineering and Applications, 2017, 53(2): 6-11.

JARVIS S J, CAZE R, CLOPATH C.Extending the Tempotron with hierarchical dendrites allows faster learning [J].BMC Neuroscience, 2015, 16: 37.

XIE X, QU H, LIU G, et al.Efficient training of supervised spiking neural networks via the normalized perceptron based learning rule [J].Neurocomputing, 2017, 241(7): 152-163.

TAHERKHANI A, BELATRECHE A, LI Y, et al.A supervised learning algorithm for learning precise timing of multiple spikes in multilayer spiking neural networks [J].IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(11): 5394-5407.

程龙, 刘洋.脉冲神经网络: 模型、学习算法与应用 [J].控制与决策, 2018, 33(5): 158-172.

CHENG Long, LIU Yang.Spiking neural networks: model, learning algorithms and applications [J].Control and Decision, 2018, 33(5): 923-937.

XIAO R, TANG Huajin, GU Pengjie, et al.Spike-based encoding and learning of spectrum features for robust sound recognition [J].Neurocomputing, 2018, 313(11): 65-73.

ROGGENHOFER E, FIDZINSKI P, SHOR O, et al.A forecast-based biologically-plausible STDP learning rule [C]∥Proceedings of the International Joint Conference on Neural Networks.Piscataway, NJ, USA: IEEE, 2011: 1810-1817.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种离散时间调度的图像自分类脉冲神经网络

不同板叠材料热声热机能量转换过程数值模拟研究

采用试验设计方法的第三代CO2气体箔轴承箔片几何参数敏感性分析

混合电解槽阵列协同的风光耦合制氢系统双层多目标优化

隧道内燃料电池汽车氢气泄漏扩散特性及影响因素