首页> 外文会议>2012 International workshop on image processing and optical engineering >Target Recognition Research Based on Combined Invariant Moments
【24h】

Target Recognition Research Based on Combined Invariant Moments

机译:基于组合不变矩的目标识别研究

获取原文
获取原文并翻译 | 示例

摘要

Target recognition is more difficult for the distortion space target images coming from view, camera, climate et al. It is a effective method to recognize target with moment feature for its translation invariance, rotation invariance and scale invariance. This paper studied the features and application conditions on Hu's moments, affine invariant moments, and wavelet invariant moments, made combined moments for target recognition. It combines partial Hu's moments, affine invariant moments with wavelet invariant moments. To take ship target recognition for an example, the combined moments is proved suitable for improving recognition efficiency by Matlab simulation.
机译:对于来自视图,相机,气候等的失真空间目标图像,目标识别更加困难。这是一种有效的识别具有矩特征的目标的平移不变性,旋转不变性和尺度不变性的方法。研究了胡氏矩,仿射不变矩和小波不变矩的特征和应用条件,并结合了组合矩进行目标识别。它结合了部分Hu矩,仿射不变矩和小波不变矩。以舰船目标识别为例,通过Matlab仿真证明了组合矩适合提高识别效率。

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