Method and system for extracting bonded sample set based on target

Abstract

The invention discloses a method and a system for extracting a bonded sample set based on a target. The method specifically comprises the following steps: S1, acquiring an original picture sent by an X-ray machine; s2, generating a plurality of different object sample set libraries according to the original picture; s3, acquiring a request containing a target object parameter information list; and S4, according to a request containing a target object parameter information list, extracting an object picture from the object sample set library, carrying out image data enhancement and synthesis processing corresponding to the target object parameter information, obtaining a sample picture corresponding to the target object parameter information, and determining all the sample pictures as an output sample set. According to the method, the object sample set library is generated for the object types with a small number in the training samples, so that the problem that the object types with a small number of training sets are dangerous and cannot be identified and judged is solved, and computer operation and storage resources are not excessively occupied.

Description

technical field [0001] The invention relates to the field of intelligent security inspection, in particular to a method and a system for extracting a bonded sample set based on a target. Background technique [0002] With the development of the security inspection field, X-ray security inspection machines and other equipment can be used to photograph and identify targets, so as to quickly and accurately identify and detect different types of targets, and to discover and determine dangerous goods in a timely manner. In the process of target recognition, deep learning can replace manual work to detect the category of the target, the position of each component of the target, and the topographic features. At present, the target is generally photographed by X-rays, etc., and multiple target images captured are input to a processing device such as a server, and a processing device embedded with a detection model performs deep learning detection on the target. However, the detecti...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method and system for extracting a cohesive sample set based on a target. By collecting the original picture of the X-ray machine, extracting the object picture and generating the corresponding object sample set library, and according to the target object parameter information list, a The sample set corresponding to the object parameter information list is used to solve the problem of missed detection and false detection caused by the unbalanced number of training samples in each category

Images