首页> 外文会议>International Conference on Emerging Trends in Engineering, Technology and Science >Breast and nipple line localization for adult image identification in online social networks
【24h】

Breast and nipple line localization for adult image identification in online social networks

机译:在线社交网络中成人图像识别的乳房和乳头界定定位

获取原文

摘要

The prompt growth in communication and the usage of internet have made it very easy to share personal views and business disputes all over the world through web pages, where most of the sites are fortified with harmful messages and illegal adult contents. To block adult images, content-based image retrieval technique is applied over images to identify adult image in online social networks. In our proposed solution, the background of the images is removed to obtain the skin like region. For each input image color, shape, texture is analyzed and used to retrieve both adult and non-adult images. Our Comparison result shows that, our proposed solution is highly reliable against the non-adult images. The image content features identified as porn will be recommended to the user using recommender system.
机译:迅速的沟通和互联网的使用增长使得通过网页分享世界各地的个人观点和商业纠纷,其中大多数网站都有有害信息和非法成人内容。为了阻止成人图像,基于内容的图像检索技术应用于图像以识别在线社交网络中的成人图像。在我们提出的解决方案中,去除图像的背景以获得像地区的皮肤。对于每个输入图像颜色,形状,纹理被分析并用于检索成人和非成年图像。我们的比较结果表明,我们所提出的解决方案对非成年图像非常可靠。使用推荐系统向用户建议标识为色情的图像内容功能。

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