• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Recent patents on computer science >An Improved Model for Face Recognition Verification
【24h】

An Improved Model for Face Recognition Verification

机译：面部识别验证的改进模型

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Background: Biometric testing concerning face recognition makes it hard to solve dueto the inaccuracy problem. Alongside the present progress in many technological fields, there arestill different critical issues that affect the performance of real-time face recognition systems.Methods: Recent publications and patent databases related to face recognition are reviewed to findthe best classifier of face recognition. In addition, these publications and patents are concerned toimprove the face recognition system especially its real-time performance. In this paper, we introducea new multi-agent system that will improve the face recognition system especially its real-time performance.Results: Face recognition done using multi-classifier (K-NN, NN, and CART) and multi-agents incorporatedagent with a multi-feature approach. Five types of agents are used in our experimentsnamely; information agent, preprocessing agent, classifier agent, headquarters agent, and communicationagent. The experimental results showed that the recognition rate improved. Face recognitionaccuracy up to 99.5% interpreted as 1.5 seconds in threading mode, and 1 second in distributedmode.Conclusion: By using multiple agents, the recognition processing time was improved. The use ofmulti-feature extraction turned out to be more efficient in the recognition accuracy. The proposedmodel proved to be robust in time using distributed mode execution for the classifier agents group.In addition, tapping the issue of distributed vs. threading mode distribution of agents makes a greatlink to the upcoming challenges of nowadays-modern sciences.
机译：背景：关于面部识别的生物识别测试使得难以解决Dueto不准确的问题。除了许多技术领域的目前的进展之外，还有不同的关键问题，这些问题影响了实时面部识别系统的性能。方法：综述了与面部识别相关的专利数据库，以查找面部识别的最佳分类器。此外，这些出版物和专利尤为涉及面部识别系统，尤其是其实时性能。在本文中，我们介绍了新的多代理系统，可以提高面部识别系统，尤其是其实时性能。结果：使用多分类器（K-NN，NN和购物车）和多种代理的面部识别多特征方法。我们的实验中使用了五种类型的药剂;信息代理，预处理代理，分类代理，总部代理和CommunicAgent。实验结果表明，识别率改善。面部识别可达99.5％的线程模式下的1.5秒，分布式频道中的1秒钟。结论：通过使用多个代理，识别处理时间得到改善。使用Multi-Feature Extraction旨在更有效地识别精度。 ProposedModel以分类器代理组的分布式模式执行在时间上被证明是稳健的。此外，点击分布式VS的问题，代理的线程模式分布使其成为当今 - 现代科学的即将到来的挑战。

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