交通标志分类神经网络委员会

The 2011 International Joint Conference on Neural Networks Pub Date : 2011-10-03 DOI:10.1109/IJCNN.2011.6033458

D. Ciresan, U. Meier, Jonathan Masci, J. Schmidhuber

{"title":"交通标志分类神经网络委员会","authors":"D. Ciresan, U. Meier, Jonathan Masci, J. Schmidhuber","doi":"10.1109/IJCNN.2011.6033458","DOIUrl":null,"url":null,"abstract":"We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. Our fast, fully parameterizable GPU implementation of a Convolutional Neural Network does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. A CNN/MLP committee further boosts recognition performance.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"29 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"385","resultStr":"{\"title\":\"A committee of neural networks for traffic sign classification\",\"authors\":\"D. Ciresan, U. Meier, Jonathan Masci, J. Schmidhuber\",\"doi\":\"10.1109/IJCNN.2011.6033458\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. Our fast, fully parameterizable GPU implementation of a Convolutional Neural Network does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. A CNN/MLP committee further boosts recognition performance.\",\"PeriodicalId\":415833,\"journal\":{\"name\":\"The 2011 International Joint Conference on Neural Networks\",\"volume\":\"29 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2011-10-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"385\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"The 2011 International Joint Conference on Neural Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IJCNN.2011.6033458\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"The 2011 International Joint Conference on Neural Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IJCNN.2011.6033458","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 385

摘要

我们描述的方法赢得了德国交通标志识别基准的初步阶段，优于人类的识别率为98.98%。通过进一步训练，我们获得了99.15%的识别率。我们对卷积神经网络的快速、完全可参数化的GPU实现不需要仔细设计预先连接的特征提取器，而是以监督的方式学习。CNN/MLP委员会进一步提高了识别性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A committee of neural networks for traffic sign classification

We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. Our fast, fully parameterizable GPU implementation of a Convolutional Neural Network does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. A CNN/MLP committee further boosts recognition performance.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

The 2011 International Joint Conference on Neural Networks

自引率

0.00%

发文量