In material classification, distilling eigenvalue will use the object's true gray levels. The problem is objects in a bag almost always overlap with others. Being able to identify the object of interest and remove the overlap effects becomes the key issue that needs to be solved. First, the paper took an n-object-overlapping problem simplified to a two-object-overlapping problem. So the research focus turned to computing true gray levels for two-object-overlapping problem. It was necessary to develop models that can be used to remove the background object overlapping effects. The author took back scatter images for example, discussed the development of the mathematical model for removing the overlapping effects, solved the model parameter by experiment and analyzed model error. This method has been used in x-ray security inspection equipment of DT Inspection equipment limited company. The results of application show that the algorithm is feasible. This is a unique contribution to the explosive detection community.

Date Published: 11 August 2011
PDF: 8 pages
Proc. SPIE 8195, International Symposium on Photoelectronic Detection and Imaging 2011: Terahertz Wave Technologies and Applications, 81950J (11 August 2011); doi: 10.1117/12.900188

Published in SPIE Proceedings Vol. 8195:
International Symposium on Photoelectronic Detection and Imaging 2011: Terahertz Wave Technologies and Applications
X.-C. Zhang; Jianquan Yao; Cunlin Zhang; Zhenzhan Wang, Editor(s)