[1]王新美,丁爱玲,雷梦宁,等.基于 CNN 和 SVM 融合的交通标志识别[J].计算机技术与发展,2020,30(06):7-12.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 002]
　WANG Xin-mei,DING Ai-ling,LEI Meng-ning,et al.Traffic Sign Recognition Based on Combination of CNN and SVM[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2020,30(06):7-12.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 002]
点击复制

基于 CNN 和 SVM 融合的交通标志识别()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年06期
页码:
7-12
栏目:
智能、算法、系统工程
出版日期:
2020-06-10

文章信息/Info

Title:
Traffic Sign Recognition Based on Combination of CNN and SVM
文章编号:
1673-629X(2020)06-0007-06
作者:
王新美; 丁爱玲; 雷梦宁; 康 盟
长安大学 信息工程学院,陕西 西安 710000
Author(s):
WANG Xin-mei; DING Ai-ling; LEI Meng-ning; KANG Meng
School of Information Engineering,Chang’an University,Xi’an 710000,China
关键词:
CNN; SVM; 迁移学习; 归一化; 交通标志识别
Keywords:
CNN; SVM; transfer learning; normalization; traffic sign recognition
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 06. 002
摘要:
针对传统的卷积神经网络对小样本分类易产生过拟合等问题,在卷积神经网络(CNN) 和支持向量机( SVM) 融合模型的基础上,提出对 CNN 网络结构提取的特征进行归一化处理,提高泛化能力,并将其应用到交通标志识别。 该方法构建了一种 CNN-SVM 模型,将卷积神经网络和支持向量机结合起来,使用从 ImageNet 数据集初始化的网络进行特定域的微调,截取网络内层来提取交通标志图像特征,并对特征进行归一化处理,最后采用 SVM 进行识别,从而有效解决交通标志分类过拟合问题。 仿真结果表明,通过 CNN 内层建立的特征映射模型,所传递的特征经过归一化处理后,在交通标志分类任务中具有良好的特征表示能力,较好地提升了 SVM 分类性能,表现出更好的分类精度以及泛化性能。
Abstract:
Aiming at the problem that the traditional convolutional neural network tends to over-fit the classification of small samples,we propose a new method to normalize the features extracted from CNN network structure based on the model of CNN and SVM combination,so as to improve its generaliza-tion ability and apply it to traffic sign recognition. The method builds a CNN-SVM model which combines convolutional neural network and support vector machine,and fine-tunes the network initialized from ImageNet dataset on specific domain and intercepts its inner layer to extract the image features from traffic signs. The features are normalized and finally identified by SVM,which effectively solves the over-fitting problem toward traffic signs’ classification. The simulation results show that the feature mapping model established through the inner layer of CNN, after the transmitted features being normalized,have a superb feature presentation ability in traffic sign classification tasks,improve the SVM classification performance,and show better classification accuracy and generalization performance.

相似文献/References:

[1]钱秋银 张正兰.一种基于多分类SVM的相关反馈图像检索方法[J].计算机技术与发展,2009,(08):65.
　QIAN Qiu-yin,ZHANG Zheng-lan.One Method of Relevance Feedback Image Retrieval Based on Multi - Classification SVM[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2009,(06):65.
[2]袁芬萍 季桂树.基于SVM的三阶段人脸检测方法的研究与应用[J].计算机技术与发展,2007,(09):133.
　YUAN Fen-ping,JI Gui-shu.Research and Application about Three- Stage Face Detection Method Based on SVM[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2007,(06):133.
[3]戴林 姜梅.基于半监督学习的入侵检测系统[J].计算机技术与发展,2011,(01):162.
　DAI Lin JIANG Mei.Semi-Supervised Learning-Based Network Intrusion Detection System[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2011,(06):162.
[4]陈自洁,陆小兵[],杨晓伟[].面向分组类别概率问题的模糊SVM分类算法[J].计算机技术与发展,2013,(11):46.
　CHEN Zi-jie[],LU Xiao-bing[],YANG Xiao-wei[].A Fuzzy SVM Classification Algorithm from Group Probabilities Problem[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2013,(06):46.
[5]赵胜,赵学健,张欣慧,等.基于Sobel 算子和 CNN 的车辆轨迹识别系统[J].计算机技术与发展,2018,28(07):169.[doi:10.3969/ j. issn.1673-629X.2018.07.036]
　ZHAO Sheng,ZHAO Xue-jian,ZHANG Xin-hui,et al.Vehicle Trajectory Recognition System Based on Sobel Operator and CNN[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2018,28(06):169.[doi:10.3969/ j. issn.1673-629X.2018.07.036]
[6]段国仑,谢钧,郭蕾蕾,等.Web文档分类中TFIDF特征选择算法的改进[J].计算机技术与发展,2019,29(05):49.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 010]
　DUAN Guo-lun,XIE Jun,GUO Lei-lei,et al.Improvement of TFIDF Feature Selection Algorithm in Web Document Classification[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2019,29(06):49.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 010]
[7]袁鹏泰,刘宁钟.基于关节点提取的老年人跌倒检测算法[J].计算机技术与发展,2019,29(09):200.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 038]
　YUAN Peng-tai,LIU Ning-zhong.Elderly Fall Detection Algorithm Based on Joint Point Extraction[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2019,29(06):200.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 038]
[8]高 强,潘 俊,洪锐锋.基于 CNN 的机场安检危险品自动识别研究[J].计算机技术与发展,2019,29(10):95.[doi:10. 3969 / j. issn. 1673-629X. 2019. 10. 020]
　GAO Qiang,PAN Jun,HONG Rui-feng.Research on Automatic Recognition of Dangerous Goods in Airport Security Inspection Based on CNN[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2019,29(06):95.[doi:10. 3969 / j. issn. 1673-629X. 2019. 10. 020]
[9]任飞凯,邱晓晖.基于 LBP 和数据扩充的 CNN 人脸识别研究[J].计算机技术与发展,2020,30(03):62.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 012]
　REN Fei-kai,QIU Xiao-hui.Research on Face Recognition of CNN Based on LBP and Data Expansion[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2020,30(06):62.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 012]
[10]张明军,俞文静,李伟滨,等.一种基于机器学习的车牌识别系统的设计[J].计算机技术与发展,2020,30(05):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 05. 041]
　ZHANG Ming-jun,YU Wen-jing,LI Wei-bin,et al.Design of License Plate Recognition System Based on Machine Learning[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2020,30(06):216.[doi:10. 3969 / j. issn. 1673-629X. 2020. 05. 041]

更新日期/Last Update: 2020-06-10