Foreign object detection classification method, apparatus, and security screening device
By performing atomic number image correction and region segmentation on the detection images of security inspection equipment, and combining attribute information matching, the problem of existing security inspection equipment being unable to identify specific foreign objects has been solved, enabling effective classification and labeling of foreign objects and improving the ease of use of the equipment.
CN119313950BActive Publication Date: 2026-07-03HANGZHOU RAYIN TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HANGZHOU RAYIN TECH CO LTD
- Filing Date
- 2024-09-24
- Publication Date
- 2026-07-03
AI Technical Summary
Technical Problem
Existing security inspection equipment is unable to effectively identify and classify specific foreign objects, leading to inconvenience in certain scenarios.
Method used
By acquiring the detection image and atomic number image of the object being inspected, correction processing is performed to exclude background objects. The target area is determined and the type of foreign object is labeled using the region segmentation and attribute information matching of the atomic number image.
Benefits of technology
It enables the effective identification and classification of specific foreign objects, improving the ease of use of security inspection equipment in specific scenarios.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN119313950B_ABST
Abstract
The embodiment of the application discloses a foreign matter detection classification method, device and security inspection equipment. The foreign matter detection classification method first acquires a detection image of an inspected object and an atomic number image corresponding to the detection image respectively, corrects the atomic number image to exclude background objects in the inspected object, that is, obtains a corrected atomic number image; then, the corrected atomic number image is subjected to region segmentation processing according to the distribution of data to determine one or more target regions in the corrected atomic number image; and finally, the type of target foreign matter corresponding to each target region is determined according to the matching of the attribute information of the target region and the attribute information of different types of target foreign matter preset in advance, so that the type of target foreign matter determined by each target region can be marked at the position corresponding to each target region in the detection image, that is, the classification marking of target foreign matter in the detection image is realized, and the use is convenient.
Need to check novelty before this filing date? Find Prior Art