Curvelet Transform-based Image De-noising for Electrical Fire Cause Investigation

摘要：

Electrical fire cause investigation involves much work to be done with human experiences. In order to improve accuracy and clearness,curvelet transform based thresholding for image de-noising was employed in this paper. Through detailed experiments suitable parameters for image de-noising were achieved,and also it was proved that hard thresholding could result better performance than hard thresholding for curvelet transform based de-noising. Then curvelet transform based thresholding de-noising method was used for metallo-graphic structure image de-noising with optimized parameters and algorithm. Further experiments showed that curvelet trans-form based image de-noising can be a promising method aimed for electrical fire cause investigation.

关键词： electrical fire cause investigation metallographic image curvelet transform hard threshold

作者: Chunhua Li Shu Yang Zunze Hou

作者单位: Research Institute,Chinese Peoples Armed Police Forces Academy,HeBei Province,China Fire Engineering Department,Chinese Peoples Armed Police Forces Academy,HeBei Province,China

会议类型: 国际会议

会议名称: 2011 International Conference on Opto-Electronics Engineering and Information Science(2011光电电子工程与信息科学国际会议 ICOEIS 2011)

会议地点: 西安

会议语种:英文

页码: 1889-1892

在线出版日期: 2011-12-23（万方平台首次上网日期，不代表论文的发表时间）