| 贺超,陈振学,刘成云.自底向上的图像显著目标检测研究[J].光电子激光,2016,27(8):886~892 |
| 自底向上的图像显著目标检测研究 |
| Bottom-up image saliency target detection via bottom-up |
| 投稿时间：2015-12-06 |
| DOI： |
| 中文关键词: 中心先验 小波变换(WT) 谱残差(SR) 图像显著性 目标检测 |
| 英文关键词:center-prior wavelet transform (WT) spectral residual (SR) images saliency target detection |
| 基金项目:国家自然科学基金(61203261,61273277)、山东省自然科学基金(ZR2012F Q003)、浙江大学CAD&CG国家重点实验室开放课题(A1514)和南京理工大学高维信息智能感知与系统教育部重点实验室创新基金(201501)资助项目 |
|
| 摘要点击次数: 837 |
| 全文下载次数: 0 |
| 中文摘要: |
| 针对传统的图像显著性检测造成显 著目标误检的问题,本文通过采用Harris角点检测算子以及计算机形态学中的凸包理 论,得到改进的中心先验 图像显著性检测系数,进而利用小波变换(WT)在时域和频域上的局部特征信息表征能力 得到局部特征 显著图像,以及采用谱残差(SR)的图像处理方法获取全局特征的显著图像,提出一种基于改 进图像中心先验理 论的自底向上的图像显著目标检测方法。实验结果表明,与现有的图像显著性检测模型相比 ,本文提出的模型检测准确率更好,检测效果也更好。 |
| 英文摘要: |
| Aiming at the problem that the traditional image saliency target detection can c ause false detection for saliency target,in this paper we find the center of tar get by Harris corner detection and convex-hull of computer morphology theory,and bu ilt the advanced center-prior saliency detection model.Then,we get the local feature saliency image by the wavelet transform in the time domain and frequency domain on the local characteristic information representati on ability,and obtain the global features′ saliency image by spectral residual to deal with target images.Final ly,we establish an advanced center-prior saliency detection model which is based on bottom-up image sal iency target detection methods. The experimental results show that the model proposed in this paper is effective in detecting significant object,the target detecti on rate is higher,and the detection of significant target is more complete. |
| 查看全文 下载PDF阅读器 |
| 关闭 |
|
|
|
|
|