| 多特征融合的低景深图像前景提取算法 |
| |
| 引用本文： | 邓小玲,倪江群,李震,代芬.多特征融合的低景深图像前景提取算法[J].自动化学报,2013,39(6):846-851. |
| |
| 作者姓名： | 邓小玲 倪江群 李震 代芬 |
| |
| 作者单位： | 1.华南农业大学工程学院 广州 510642; |
| |
| 基金项目： | 国家自然科学基金(31201129),高等学校博士点基金(20120171110037);广东省自然科学基金重点项目(S2012020011114);广东省科技计划项目(2011B-020308009);公益性行业(农业)科研专项经费项目(200903023-01)资助 |
| |
| 摘 要： | 针对低景深(Low depth-of-field, DOF)图像, 提出了一种融合纹理、颜色和高阶统计量(Higher-order statistics, HOS) 特征的聚焦前景提取方法. 首先, 根据相似性最大化原则, 通过迭代获得纹理和颜色特征的优化权重, 实现低景深图像的区域分割. 然后,根据优化权重值计算颜色空间上的加权HOS 值, 并结合区域归属前景的划分策略, 实现低景深图像的前景提取. 实验结果表明, 该算法可以同时取得较高的主观和客观评价效果.
|
| 关 键 词： | 前景提取 低景深图像 高阶统计量 权重优化 |
| 收稿时间： | 2012-05-17 |
Foreground Extraction from Low Depth-of-field Images Based on Colour-texture and HOS Features |
| |
| DENG Xiao-Ling,NI Jiang-Qun,LI Zhen,DAI Fen.Foreground Extraction from Low Depth-of-field Images Based on Colour-texture and HOS Features[J].Acta Automatica Sinica,2013,39(6):846-851. |
| |
| Authors: | DENG Xiao-Ling NI Jiang-Qun LI Zhen DAI Fen |
| |
| Affiliation: | 1.College of Engineering, South China Agricultural University, Guangzhou 510642;2.School of Information Science and Technology, Sun Yat-sen University, Guangzhou 510275 |
| |
| Abstract: | This paper presents a new algorithm for extracting foreground objects from low depth-of-field (DOF) images using texture, color and high-order statistics (HOS) features. Firstly, an algorithm with automatic weight optimization is designed to segment DOF images according to the principle of maximum similarity. The foreground of DOF images is then extracted based on the weighted HOS and a strategy for foreground region classification. Simulation results demonstrate that the proposed algorithm achieves satisfactory result both subjectively and objectively. |
| |
| Keywords: | Foreground extraction low depth-of-field (DOF) images high-order statistics (HOS) weight optimization |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
