【24h】

Ramanujan sums based image kernels for computer vision

机译:Ramanujan基于求和的图像核用于计算机视觉

获取原文
获取原文并翻译 | 示例

摘要

In the recent history, kernel methods had established themselves as powerful tools for computer vision. In this paper we introduce an integer image kernel function based on Ramanujan Sums which finds its place in image vision. The paper proves the validity of kernel function theoretically and also shows the application of the kernel in image vision. Ramanujan Sums are based on number theory and hence the new kernel matrix will contain only the integer values. Since the image processing involves complex matrix manipulations, the processing based on the new kernel will be computationally effective. The paper shows the applicability of the kernel in various context of image processing. By applying the theory of Ramanujan Sums for image kernel, we will show the intervention of numerical mathematics in machine learning which gives new directions for future research.
机译:在最近的历史中,内核方法已将自己确立为计算机视觉的强大工具。在本文中,我们介绍了一个基于Ramanujan Sums的整数图像核函数,该函数可在图像视觉中找到其位置。本文从理论上证明了核函数的有效性,并说明了核在图像视觉中的应用。 Ramanujan Sums基于数论,因此新的内核矩阵将仅包含整数值。由于图像处理涉及复杂的矩阵操作,因此基于新内核的处理将在计算上有效。本文展示了内核在各种图像处理环境中的适用性。通过将Ramanujan Sums理论应用于图像核,我们将展示数值数学在机器学习中的介入,这为未来的研究提供了新的方向。

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