首页 | 官方网站   微博 | 高级检索  
     

基于联合卷积和递归神经网络的交通标志识别
引用本文:宣森炎,龚小谨,刘济林.基于联合卷积和递归神经网络的交通标志识别[J].传感器与微系统,2014(8):30-33.
作者姓名:宣森炎  龚小谨  刘济林
作者单位:浙江大学信息科学与电子工程学系,浙江杭州310027
摘    要:提出了一种联合卷积和递归神经网络的深层网络结构,在卷积神经网络中引入了递归神经网络能学到的组合特征:原始图片先通过一级由k均值聚类学得滤波器的卷积神经网络,得到的结果再同时通过一级卷积和一级递归神经网络,最后得到的特征向量由Softmax分类器进行分类。实验结果表明:在第二级卷积和递归神经网络权重随机的情况下,该网络的识别率已经能够达到98.28%,跟其他网络结构相比,大大减少了训练时间,而且无需复杂的工程技巧。

关 键 词:卷积神经网络  递归神经网络  k均值聚类

Traffic sign recognition based on joint convolutional and recursive neural networks
XUAN Sen-yah,GONG Xiao-jin,LIU Ji-lin.Traffic sign recognition based on joint convolutional and recursive neural networks[J].Transducer and Microsystem Technology,2014(8):30-33.
Authors:XUAN Sen-yah  GONG Xiao-jin  LIU Ji-lin
Affiliation:(Department of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China)
Abstract:Propose a joint convolutional and recursive neural network structure, bring the combinational feature that recursive neural networks can learn into convolutional neural networks, that is, the raw image is first passed through a convolutional neural network stage with filters trained by k-means clustering, the result is then passed through a convolutional and a recursive neural network stage simultaneously, at last ,the obtained feature vector is classified by softmax classifier. Experimental result shows that even with weights randomly set for the second convolutional and recursive neural network, the network reaches a recognition rate of 98.28 % , compared to other network structures, it greatly reduces training time and requires no complex engineering tricks.
Keywords:convolutional neural networks  recursive neural networks  k-means clustering
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号