Recognizing method of flaky or blocky prohibited articles, explosives or drugs
The present invention discloses recognizing methods of flaky or blocky prohibited articles, explosives or drugs. Specifically, the method for recognizing flaky prohibited articles, explosives or drugs comprises steps of: (1) reading in tomogram data of an object to be inspected for one tomogram; (2) pre-processing the tomogram data; (3) splitting the pre-processed tomogram data into a plurality of regions that have similar physical properties; (4) analyzing whether each of the split regions is a flaky region; (5) determining whether the flaky region recognized in the current tomogram can be merged with the flaky region detected from the previous tomogram, so as to form a flaky target; (6) determining whether each detected flaky target is complete or finished; (7) repeating steps (1)-(6) and processing each tomogram data layer by layer, until all of the tomogram data have been processed.
1. A method for recognizing flaky prohibited articles, explosives or drugs, characterized in that, comprising steps of:
(1) reading in tomogram data of an object to be inspected for one tomogram;
(2) pre-processing the tomogram data;
(3) splitting the pre-processed tomogram data into a plurality of regions that have similar physical properties;
(4) analyzing whether each of the split regions is a flaky region;
(5) determining whether the flaky region recognized in the current tomogram can be merged with the flaky region detected from the previous tomogram, so as to form a flaky target;
(6) determining whether each detected flaky target is complete or finished;
(7) repeating steps (1)-(6) and processing each tomogram data layer by layer, until all of the tomogram data have been processed.
2. The method of claim 1 , characterized in that,
after the step (4), the method further comprises post-processing the flaky regions detected out in the current tomogram, so as to merge short and split flaky regions into a long flaky region.
3. The method of claim 2 , characterized in that,
the merging step in the step (5) and the process to merge the short flaky regions are performed based on positional proximity and similarity of physical properties.
4. The method of claim 3 , characterized in that,
the physical properties comprise density or atomic numbers.
5. The method of claim 1 , characterized in that,
the process whether each split region is the flaky region, is performed based on the following regulations:
a length of the split region cannot be less than a predetermined first threshold;
a thickness of the split region cannot be larger than a predetermined second threshold;
uniformity of the thickness of the split region cannot be larger than a predetermined third threshold;
when the above three conditions are satisfied at the same time, the split region is recognized as the flaky region.
6. The method of claim 5 , characterized in that,
the length is a half of a number of profile pixels of the split region; the thickness is an area of the split region divided by the length; the uniformity of the thickness is measured by “ standard deviation of the thickness of the split region divided by an average of thickness thereof”.
7. The method of claim 1 , characterized in that,
in the step (5), if it is determined that the flaky regions detected in the current tomogram can be merged with the previous flaky targets, then the step (6) is performed;
otherwise, a new flaky target is established.
8. The method of claim 1 , characterized in that,
during the step (6), if it is determined that each detected flaky target is finished or complete, then the flaky target with a mass within a predetermined range is outputted.
9. The method of claim 1 , characterized in that,
the pre-processing step comprises: threshold limit, smoothing and quantifying of the tomogram data.
10. The method of claim 1 , characterized in that,
this method is applicable to a CT system or a nuclear magnetic resonance system.