首页> 外文会议>International conference on electronic engineering, communication and management;EECM 2011 >Scale Invariant Target Recognition in Non-uniform Illuminated and Noisy Scene
【24h】

Scale Invariant Target Recognition in Non-uniform Illuminated and Noisy Scene

机译:非均匀光照嘈杂场景下的尺度不变目标识别

获取原文

摘要

A new method is presented for scale invariant target recognition under non-uniform illumination and noisy conditions. Both overlapping additive noise and nonoverlapping background noise are considered. The method includes two steps. First, the input scene is preprocessed with estimated illumination function. Then an optimum correlation filter is designed based on modified Wiener filter(WF) model, which the reference term of WF's transfer function is synthesized using the mean of training images . Simulation results verify the effectiveness of the proposed idea in terms of tolerance to scale distortion in presence of non-uniform illumination and noise.
机译:提出了一种在光照和噪声不均匀条件下尺度不变目标识别的新方法。重叠的加性噪声​​和非重叠的背景噪声均被考虑。该方法包括两个步骤。首先,使用估计的照明功能对输入场景进行预处理。然后基于改进的维纳滤波器(WF)模型设计了一个最佳相关滤波器,利用训练图像的均值合成了WF传递函数的参考项。仿真结果在存在不均匀照明和噪声的情况下对比例失真的容忍度方面验证了所提出思想的有效性。

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