The Segmentation Method for Testing Images of X-Ray Security Inspection Systems
-
摘要: 从X射线安检设备测试图像中分割出各测试项目, 是客观评价X射线安检设备成像图像质量的基础。针对测试图像中测试项目轮廓突出和色彩信息鲜明的特征, 采用基于HSI色彩空间对图像边缘进行多边形逼近简化处理后按照几何特征进行分割的方法。试验结果表明, 基于HSI颜色空间的图像分割算法在图像质量较差, 边缘变形较严重的情况下仍能正确地对图像进行分割, 取得了较好的效果。Abstract: The segmentation for the image of different test items is the foundation of quality assessing for testing image which is generated by X-ray security inspection systems. The segmentation method mentioned is based on HSI color space, using polygon approximation to accomplish image edge extraction, segment image depending on geometric features. The experiment results showed that it could accomplish segmentation for the low quality image with large noise and distortion.
-
-
[1] 林生佑,石教英.基于HVS的彩色图像边缘检测算子[J].中国图象图形学报,2005,10(1): 43-47. [2] Douglas D H, Peucker T K. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature[J]. The Canadian Cartographer,1973,10(2): 112-122. [3] Teh C H, Chin R T. On the detection of dominant points on digital curves[J]. IEEE Tr PAMI,1989,11: 859-872. [4] 刘 敏.基于三维道格拉斯改进算法的地貌自动综合研究[D].西安: 西北大学,2007. [5] 许如初,张智平.确定任意多边形顶点凸凹性的快速算法[J].华中理工大学学报,1997,25(1): 103-104.
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 2