| 自动识别并分割太赫兹图像中的可疑物 |
| |
| 引用本文： | 严志讯,林晓,童慧鑫,蒋林华. 自动识别并分割太赫兹图像中的可疑物[J]. 上海理工大学学报, 2018, 40(5): 435-443 |
| |
| 作者姓名： | 严志讯 林晓 童慧鑫 蒋林华 |
| |
| 作者单位： | 上海理工大学 光电信息与计算机工程学院, 上海 200093,上海理工大学 光电信息与计算机工程学院, 上海 200093,上海理工大学 光电信息与计算机工程学院, 上海 200093,上海理工大学 光电信息与计算机工程学院, 上海 200093 |
| |
| 基金项目： | 国家自然科学基金资助项目（61775139） |
| |
| 摘 要： | 分析了太赫兹图像的特征,基于图像处理技术提出了一种新颖并且快速检测人体太赫兹图像的算法。使用改进的非局部均值滤波器来减少太赫兹图像中的噪声;应用主动形状模型(ASM)检测人体轮廓;采用基于TSED(total square euclidean distance)的k-means算法分割可疑物。实验结果表明,提出的算法能够很好地检测和分割太赫兹图像中的可疑物体。
|
| 关 键 词： | 公众安全 太赫兹安检仪 模糊太赫兹图像 可疑物体检测 |
| 收稿时间： | 2017-11-21 |
Automatic Identification and Segmentation of Suspicious Objects in Terahertz Images |
| |
| YAN Zhixun,LIN Xiao,TONG Huixin and JIANG Linhua. Automatic Identification and Segmentation of Suspicious Objects in Terahertz Images[J]. Journal of University of Shanghai For Science and Technology, 2018, 40(5): 435-443 |
| |
| Authors: | YAN Zhixun LIN Xiao TONG Huixin JIANG Linhua |
| |
| Affiliation: | School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China,School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China,School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China and School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China |
| |
| Abstract: | The features of terahertz images were analyzed, relying on the digital image processing technique and an efficient and real-time algorithm was proposed for a terahertz security system for human bodies. The noise in terahertz images was removed by using an improved nonlocal mean filter. The human body outline was detected by applying active shape model (ASM) algorithm. And a TSED(total square euclidean distance) based k-means algorithm was used to label objects in terahertz images. The experimental results demonstrate that the proposed method can well detect and segment suspicious objects from terahertz images. |
| |
| Keywords: | public security terahertz security system blurred terahertz image suspicious objects detection |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《上海理工大学学报》浏览原始摘要信息 |
|
点击此处可从《上海理工大学学报》下载全文 |
|
