| 基于鲁棒主成分分析和多个色彩通道的显著性检测 | |
| 马小龙 ; 谢旭东 ; 林健文 ; 钟宜生 ; MA Xiaolong ; XIE Xudong ; Lam Kinman ; ZHONG Yisheng | |
| 2016-03-30 ; 2016-03-30 | |
| 关键词 | 显著性检测 鲁棒主成分分析 多个色彩通道 loudness psychoacoustic methods temporal integration mechanism TP391.41 |
| 其他题名 | Saliency detection based on robust principal component analyses and multiple color channels |
| 中文摘要 | 显著性检测在图像分割、物体检测、视觉效果评估等领域有非常广泛的用途。为了增强这种图像预处理技术的实用性,同时对人眼视觉系统的机理进行研究和模拟,该文提出了一种基于鲁棒主成分分析和多个色彩通道的显著性检测方法。将图像的多个色彩空间重构成每一列都线性相关的矩阵,然后将显著性区域看作是矩阵的稀疏成分,将背景信息看作是低秩成分。经过对新矩阵进行鲁棒主成分分析后就可以将显著性区域提取出来。最后加入人眼视觉系统中的显著性先验和中心先验机理,使得提出的模型更加合理。实验结果表明:该方法在量化指标和视觉效果方面超过了当前很多先进的方法,验证了这种假设的合理性。; Saliency detection is widely used in image segmentation,object detection and visual performance evaluations. Image preprocessing is enhanced by imitating the human visual mechanism with a saliency detection method,based on a robust principal component analysis algorithm and multiple color channels.The original image is first transformed into multiple color channels,represented by a matrix with the columns of this matrix linearly correlated.The salient regions are assumed to be the sparse component with the background regions as the low rank component.The robust principal component analysis of this matrix is used to extract the components.Use of a saliency prior and a center prior make the saliency detection model more effective.Tests show that this algorithm outperforms many state-of-the-art methods in terms of aquantitative index and the visual effect. |
| 语种 | 中文 ; 中文 |
| 内容类型 | 期刊论文 |
| 源URL | [http://ir.lib.tsinghua.edu.cn/ir/item.do?handle=123456789/147185]  |
| 专题 | 清华大学 |
| 推荐引用方式 GB/T 7714 | 马小龙,谢旭东,林健文,等. 基于鲁棒主成分分析和多个色彩通道的显著性检测[J],2016, 2016. |
| APA | 马小龙.,谢旭东.,林健文.,钟宜生.,MA Xiaolong.,...&ZHONG Yisheng.(2016).基于鲁棒主成分分析和多个色彩通道的显著性检测.. |
| MLA | 马小龙,et al."基于鲁棒主成分分析和多个色彩通道的显著性检测".(2016). |
| 个性服务 |
| 查看访问统计 |
| 相关权益政策 |
| 暂无数据 |
| 收藏/分享 |
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
修改评论