首页> 外文会议>5th European symposium on artificial neural networks >Neural network cooperation for handwritten digit recognition: a comparison of four methods
【24h】

Neural network cooperation for handwritten digit recognition: a comparison of four methods

机译:神经网络合作手写数字识别:四种方法的比较

获取原文
获取原文并翻译 | 示例

摘要

In this paper we focus on "off-line digit recognition" with unknown scriptor. After presenting two neural recognisers, we evaluate four solutions to combine results obtained from the two systems.rnThe tests were performed by the French postal services (SRTP) on their secret data base containing more than 7000 digits taken from everyday mail. This allows us to evaluate our four cooperation methods and also to compare them to other methods developed by other research teams.
机译:在本文中,我们着重研究未知脚本的“离线数字识别”。在介绍了两个神经识别器之后,我们评估了四种解决方案,以结合从这两个系统获得的结果。测试由法国邮政服务(SRTP)在其秘密数据库上进行,该数据库包含从日常邮件中提取的7000多个数字。这使我们能够评估我们的四种合作方法,并将它们与其他研究团队开发的其他方法进行比较。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号