• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Signal Processing, Communications and Computing >Reticular shield detection algorithm using superpixel segmentation
【24h】

Reticular shield detection algorithm using superpixel segmentation

机译：基于超像素分割的网状屏蔽检测算法

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

摘要

In this paper, we propose a novel reticular shield detection algorithm to restore the images that are obscured by reticular shield such as barbed wires and fences. The whole framework is composed of three stages: stage-1 for accurate superpixel segmentation, stage-2 for deriving the mask of reticular shield and stage-3 for restoring the image by introducing the algorithm. In this paper, to obtain the accurate mask of the shield, a new joint feature CCTP is used to train support vector machine (SVM) classifier and classify all superpixels. Finally, we make comparison of the effects of the proposed algorithm and several other algorithms put forward by other scientists. We introduce two indexes, PSNR and SSIM to evaluate the results and the proposed algorithm is obviously superior to the other two algorithms, which can also be proved by looking into the restoration images.
机译：在本文中，我们提出了一种新颖的网状屏蔽检测算法，以恢复被网状屏蔽（如铁丝网和栅栏）遮挡的图像。整个框架由三个阶段组成：阶段1用于精确的超像素分割，阶段2用于导出网状屏蔽罩，阶段3通过引入算法来恢复图像。在本文中，为了获得正确的屏蔽罩，使用了新的联合特征CCTP来训练支持向量机（SVM）分类器并对所有超像素进行分类。最后，我们比较了所提算法和其他科学家提出的其他几种算法的效果。我们引入了两个指标PSNR和SSIM来评估结果，并且所提出的算法明显优于其他两个算法，这也可以通过查看恢复图像来证明。

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