| 摘要 |
The method includes obtaining slice data of inspected luggage in a CT system and generating 3D volume data of objects in the luggage from the slice data. Three depth projection images are calculated based on the data. The symmetry, duty ratio and aspect ratio for each image and the similarity between the images is calculated. A shape feature parameter based on these is generated. The parameter is then classified with a classifier to obtain a quantifier description expressing the shape of the object. For each object, a semantic description is outputted including at least a quantifier description of the object based on the 3D volume data. The above solutions can create a 3D model for objects in the inspected luggage in a relatively accurate manner, and thus provide better basis for subsequent shape feature extraction and security inspection, and reduce omission factor. Another aspect relates to displaying objects in a CT system comprising determining a semantic description of an object based on 3D volume data and, upon user selection of an object, presenting the semantic description. |
