计算机科学 ›› 2018, Vol. 45 ›› Issue (11A): 238-243.

• 模式识别与图像处理 • 上一篇    下一篇

多层前向人工神经网络图像分类算法

顾哲彬, 曹飞龙   

  1. 中国计量大学理学院 杭州310018
  • 出版日期:2019-02-26 发布日期:2019-02-26
  • 通讯作者: 曹飞龙(1965-),男,博士,教授,博士生导师,主要研究方向为智能计算、图像处理等,E-mail:feilongcao@gmail.com
  • 作者简介:顾哲彬(1992-),男,硕士,主要研究方向为机器学习、图像处理,E-mail:gzbin@foxmail.com
  • 基金资助:
    本文受国家自然科学基金(61672477)资助。

Algorithm of Multi-layer Forward Artificial Neural Network for Image Classification

GU Zhe-bin, CAO Fei-long   

  1. College of Sciences,China Jiliang University,Hangzhou 310018,China
  • Online:2019-02-26 Published:2019-02-26

摘要: 传统人工神经网络的输入均为向量形式,而图像由矩阵形式表示,因此,在用人工神经网络进行图像处理时,图像将以向量形式输入至神经网络,这破坏了图像的结构信息,从而影响了图像处理的效果。为了提高网络对图像的处理能力,文中借鉴了深度学习的思想与方法,引进了具有矩阵输入的多层前向神经网络。同时,采用传统的反向传播训练算法(BP)训练该网络,给出了训练过程与训练算法,并在USPS手写数字数据集上进行了数值实验。实验结果表明,相对于单隐层矩阵输入前向神经网络(2D-BP),所提多层网络具有较好的分类效果。此外,对于彩色图片分类问题,利用所提出的2D-BP网络,给出了一个有效的可行方法。

关键词: 多层前向神经网络, 学习算法, 图像分类, 梯度优化

Abstract: The input of traditional artificial neural network is in vector form,but the image is represented by matrix.Therefore,in the process of image processing,the image will be inputted into the neural network in vector form,which will destroy the structure information of image,and thus affect the effect of image processing.In order to improve the ability of network on image processing,the multilayer feedforward neural networks with matrix inputs are introducedbased on the idea and method of deep learning.At the same time,the traditional back-propagation algorithm (BP) is used to train the network,and the training process and training algorithm are given.After a lot of experiments,the network structure with good performance were determined,and the numerical experiments were carried out on the USPS handwritten digital data set.The experimental results show that the proposed multilayer network has better classification results than the single hidden layer feed forward neural network with matrix input (2D-BP).In addition,to deal with the problem of color image classification,this paper provided an effective and feasible method,the new 2D-BP network,to deal with it

Key words: Multilayer feedforward neural networks, Learning algorithm, Image classification, Gradient optimization

中图分类号: 

  • TN911.71
[1]高隽,谢昭.图像理解理论与方法 [M].北京:科学出版社,2009.
[2]RICHARDS L E.Principal Component Analysis [J].Journal of Marketing Research,1988,38(22):41-64.
[3]STONE J.Principal Component Analysis and Factor Analysis[M].MIT Press,2004:129-135.
[4]LU J,PLATANIOTIS K N,VENETSANOPOULOS A N.Face recognition using LDA-based algorithms [J].IEEE Transactions on Neural Networks,2003,14(1):195-200.
[5]ZHENG W S,LAI J H,YUEN P C.GA-fisher:A new LDA-based face recognition algorithm with selection of principal components[J].IEEE Transactions on Systems Man & Cybernetics Part B,2005,35(5):1065-1078.
[6]VAPNIK V N.The nature of statistical learning theory[M].New York:Springer,2000.
[7]SHAKHNAROVICH G,DARRELL T,INDYK P.Nearest- neighbor methods in learning and vision[J].Pattern Analysis and Applications,2008,11(2):221-222.
[8]HORNIK K,STINCHCOMBE M,WHITE H.Multilayer feedforward networks are universal approximators[J].Neural Networks,1989,2(5):359-366.
[9]DAI K,ZHAO J,CAO F.A novel algorithm of extended neural networks for image recognition [J].Engineering Applications of Artificial Intelligence,2015,42(1):57-66.
[10]YAN X,YAN X,ZHANG L,et al.Feature extraction based on fuzzy 2DLDA[J].Neurocomputing,2010,73(10-12):1556-1561.
[11]SANGUANSAT P,ASDORNWISED W,JITAPUNKUL S,et al.Two-Dimensional Linear Discriminant Analysis of Principle Component Vectors for Face Recognition[J].IEICE-Transactions on Information and Systems,2006,E89-D(7):2164-2170.
[12]LU J,ZHAO J,CAO F.Extended feed forward neural networks with random weights for face recognition[J].Neurocomputing,2014,136(1):96-102.
[13]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[14]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[C]∥International Conference on Neural Information Processing Systems.Curran Associates Inc.2012:1097-1105.
[15]ZEILER M D,FERGUS R.Visualizing and Understanding Convolutional Networks[C]∥European Conference on Computer Vision.2013:818-833.
[16]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J/OL].[2015-04-10].https://arxiv.org/pdf/1409.1556v6.pdf.
[17]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]∥IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2015:1-9.
[18]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Ima-ge Recognition[C]∥Computer Vision and Pattern Recognition.IEEE,2016:770-778.
[19]HULL J J.A database for handwritten text recognition research[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(5):550-554.
[20]KRIZHEVSKY,ALEX.Learning Multiple Layers of Features from Tiny Images[M].Toronto:University of Toronto,2009.
[1] 吴昊昊, 王方石. 多尺度膨胀卷积在图像分类中的应用[J]. 计算机科学, 2020, 47(6A): 166-171.
[2] 张华丽, 康晓东, 冉华, 王亚鸽, 李博, 白放. 用于肺结节影像分类识别的DBN与CNN的比较研究[J]. 计算机科学, 2020, 47(6A): 254-259.
[3] 王俊茜, 郑文先, 徐勇. 基于测试样本误差重构的协同表示分类方法[J]. 计算机科学, 2020, 47(6): 104-113.
[4] 王燕, 王丽. 面向高光谱图像分类的局部Gabor卷积神经网络[J]. 计算机科学, 2020, 47(6): 151-156.
[5] 孔芳, 李奇之, 李帅. 在线影响力最大化研究综述[J]. 计算机科学, 2020, 47(5): 7-13.
[6] 王立华,杜明辉,梁亚玲. 基于角度特征的分类网络[J]. 计算机科学, 2020, 47(2): 83-87.
[7] 满芮, 杨萍, 季程雨, 许博文. 乳腺癌组织病理学图像分类方法研究综述[J]. 计算机科学, 2020, 47(11A): 145-150.
[8] 江泽涛, 秦嘉奇, 胡硕. 基于多路卷积神经网络的多光谱场景识别方法[J]. 计算机科学, 2019, 46(9): 265-270.
[9] 徐书艳, 韩立新, 徐国夏. 基于张量分解的域适应算法[J]. 计算机科学, 2019, 46(12): 89-94.
[10] 张天柱, 邹承明. 使用模糊聚类的胶囊网络在图像分类上的研究[J]. 计算机科学, 2019, 46(12): 279-285.
[11] 王岩, 吴晓富. 深度神经网络训练中适用于小批次的归一化算法[J]. 计算机科学, 2019, 46(11A): 273-276.
[12] 王丽苹, 高瑞贞, 张京军, 王二成. 基于卷积神经网络的混凝土路面裂缝检测[J]. 计算机科学, 2019, 46(11A): 584-589.
[13] 崔璐,张鹏,车进. 基于深度神经网络的遥感图像分类算法综述[J]. 计算机科学, 2018, 45(6A): 50-53.
[14] 李思瑶, 周海芳, 方民权. 基于GPU的图像监督分类算法的研究[J]. 计算机科学, 2018, 45(6A): 143-145.
[15] 李昌利, 张琳, 樊棠怀. 基于自适应主动学习与联合双边滤波的高光谱图像分类[J]. 计算机科学, 2018, 45(12): 223-228.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 编辑部. 新网站开通,欢迎大家订阅![J]. 计算机科学, 2018, 1(1): 1 .
[2] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75 .
[3] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[4] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[5] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[6] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99 .
[7] 周燕萍,业巧林. 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100 -105 .
[8] 刘博艺,唐湘滟,程杰仁. 基于多生长时期模板匹配的玉米螟识别方法[J]. 计算机科学, 2018, 45(4): 106 -111 .
[9] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[10] 崔琼,李建华,王宏,南明莉. 基于节点修复的网络化指挥信息系统弹性分析模型[J]. 计算机科学, 2018, 45(4): 117 -121 .