Algorithm Study On Automatically Discerning Suspicious Region In Luggage DR Image

Luggage Inspection System with DR-CT represents a most advancednondestructive inspection technology in aviation system nowadays, which iscapable of automatically discerning interesting regions in the luggage withDR subsystem and is competitive to differentiate exactly types of luggageobjects with CT subsystem, and which makes it possible to implement thewhole process of luggage checking automatically and intelligently, greatlyimproving exactness rate and efficiency of luggage checking.Whether or not the system is able to inspect concealed contrabandexactly in the luggage, is mainly determined by whether DR subsystem is ableto discern interesting regions in DR image of the luggage. Because of thediversity of things in luggage and without any orderliness of things placement,DR image of luggage is rather complex, with terrible region conglutinationamong things and with no rule of gray and profile of contraband, which hasmake it the most difficult problem to design an algorithm of automaticallydiscerning interesting region.The article focuses on a main study, how to discern interesting regionautomatically and effectively, firstly, to analyze the impact on backgroundand gray of DR image of luggage imposed by whole system design, and then,to analyze noise trait, object conglutination trait and histogram trait in DRimage, from which method of discerning interesting region can begeneralized.In the studying of image segmentation, six crucial technologies havebeen developed successfully. 1) In one dimension histogram of original DRimage of luggage, there remain maximum-value wave crest havingapproximately stationary position, and the first minimum to the left of thewave crest performs excellently to be used to get rid of background of DRimage. 2) Open operation, one type of math morphology, is the right idea toerase luggage disturbance in DR image and at the same time, can be retaininteresting region appropriately. 3) After open operation, there are only a fewminimums on image histogram, one of which can be to segment image furtherand achieves satisfying result. 4) Method of histogram analyzing and that oferosion performs well in the re-segmentation of conglutinative region in DRimage. 5) Method of image distance switch can ensure Luggage CT sectionautomatically obtained to have rich suspicious region information. 6) Todecompose structure element of math morphology is a way to save a great dealrunning time for automatically discerning interesting regions algorithm,apparently improving implementation efficiency.The algorithm to automatically discerning interesting regions in DRimage of luggage designed in this article, is capable to discern and to obtaincontraband region in luggage with a good performance, and can also illustrateedges of interesting regions and transmit suspect point to CT subsystem withno error, which pave a solid way to inspect luggage automatically andintelligently for Luggage Inspection System with DR-CT.