计算机工程与应用2018，Vol.54Issue(10)：19-25,7.DOI:10.3778/j.issn.1002-8331.1801-0269
基于改进深度孪生网络的分类器及其应用
Deep siamese network-based classifier and its application
摘要
Abstract
Siamese neural network consists of twin networks which share the same parameters,and can map nonlinear data with high dimension onto a low dimension and easy separable feature space. By taking use of its excellent perfor-mance on similarity computing,an efficient classifier based on Siamese network is proposed.Convolutional Neural Net-works(CNNs)are used as building blocks,combined with max-pooling and dropout techniques,to construct a multi-scale CNNs for feature extraction.A spatial transformer network is used as a supplementary to promote the accuracy of the clas-sifier.Through experiments on traffic sign data GTSRB, the classifier obtains 99.40% accuracy rate for this recognition benchmark.The proposed method for classification has virtues of simple structure,high accuracy,short training and fast recognition.关键词
孪生神经网络/分类器/空间变换器网络/交通标志识别Key words
Siamese network/classifier/spatial transformer networks/traffic sign recognition分类
信息技术与安全科学引用本文复制引用
沈雁,王环,戴瑜兴..基于改进深度孪生网络的分类器及其应用[J].计算机工程与应用,2018,54(10):19-25,7.基金项目
浙江省自然科学基金重点项目(No.LZ16E050002). （No.LZ16E050002）
