• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Computer Technology and Media Convergence Design >Research on the Algorithm of Intelligent Review of Image Content
【24h】

Research on the Algorithm of Intelligent Review of Image Content

机译：图像内容智能审查算法研究

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

With the development and popularization of mobile products, people's demand for content information continues to increase. In order to provide users with a better and cleaner reading environment as much as possible, the content of the published image messages is reviewed and the images containing low-quality information are eliminated. However, for the huge amount of audit data, using traditional manual auditing methods can no longer achieve ideal results while ensuring the timeliness of information. Therefore, intelligent review of image messages by means of machine review is the key method to solve the above problems. The image message content intelligent review system designed in this paper uses deep learning related algorithms to review information. And it mainly includes two parts. They are vulgar porn review module and politically sensitive review module. The image message intelligent review system reduces the number of various types of illegal images, improves the reading environment and achieves the design purpose of this paper.
机译：随着移动产品的开发和普及，人们对内容信息的需求仍在继续增加。为了尽可能多地为用户提供更好和更清晰的读取环境，审查发布的图像消息的内容并消除了包含低质量信息的图像。但是，对于大量的审计数据，使用传统的手动审计方法无法再获得理想的结果，同时确保信息的时间性。因此，通过机器审查智能回顾图像消息是解决上述问题的关键方法。本文中设计的图像消息内容智能评论系统使用深度学习相关算法来审查信息。它主要包括两部分。它们是粗俗的色情审查模块和政治敏感评论模块。图像消息智能评论系统减少了各种类型的非法图像的数量，提高了阅读环境，并实现了本文的设计目的。

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