| 基于尺度不变特征变换的图像自动配准方法 |
| |
| 引用本文： | 罗代建,陈怀新,俞鸿波.基于尺度不变特征变换的图像自动配准方法[J].国际商务研究,2008,48(9). |
| |
| 作者姓名： | 罗代建 陈怀新 俞鸿波 |
| |
| 作者单位： | 电子科技大学电子工程学院，中国西南电子技术研究所 |
| |
| 摘 要： | 运用尺度不变特征变换方法提取图像特征,采用基于圆域的特征主方向计算方法,强化了图像的特征旋转不变性能;利用k-d搜索树与简化的广义Hough变换相结合的方式进行图像特征匹配,提高了特征匹配的效率和精度。实验表明,该方法能够对不同分辨率、不同光照、不同拍摄角度的图像完成精确自动配准。
|
| 关 键 词： | 图像处理 图像自动配准 尺度不变特征变换 广义Hough变换 k-d搜索树 |
Automatic Image Registration Based on Scale-Invariant Feature Transform |
| |
| LUO Dai-jian,CHEN Huai-xin,YU Hong-bo.Automatic Image Registration Based on Scale-Invariant Feature Transform[J].International Business Research,2008,48(9). |
| |
| Authors: | LUO Dai-jian CHEN Huai-xin YU Hong-bo |
| |
| Abstract: | Scale-invariant feature transform is applied to extract image feature,and circle based neighborhood method is adopted to compute feature main orientation,which strengthens the performance of feature rotation invariance,makes use of k-d tree combined with simplified general Hough transform to implement image feature match,which improves the matching efficiency and accuracy.The experiment shows that this method can accomplish image automatic registration accurately in the condition of different resolution,illumination and viewpoint. |
| |
| Keywords: | image processing image automatic registration SIFT general Hough transform k-d tree |
|
| 点击此处可从《国际商务研究》浏览原始摘要信息 |
| 点击此处可从《国际商务研究》下载免费的PDF全文 |
|
