airport X-ray contraband image detection method based on an attention mechanism

Abstract

The invention discloses an airport X-ray contraband image detection method based on an attention mechanism. The method comprises the steps of forming a security check image database; obtaining a CNN model; constructing an attention mechanism model, and obtaining a contraband target attention map; suppressing noise and background information interference in the contraband target attention map, andacquiring a suppressed contraband target attention map; and generating a position window, and obtaining a contraband target detection map by using the inhibited contraband target attention map. According to the airport X-ray contraband image detection method based on the attention mechanism provided by the invention, the advantages of high image feature extraction capability, high recognition precision, high robustness and the like of the attention mechanism model are utilized, and automatic detection of various contrabands in an X-ray security inspection image is realized. Meanwhile, the training mechanism of the attention mechanism model is weak supervised training, so that extra manual annotation is not needed in the training process.

Description

technical field [0001] The invention belongs to the technical field of X-ray security inspection image detection and deep learning, and in particular relates to an airport X-ray contraband image detection method based on an attention mechanism. Background technique [0002] In airport security inspection, X-ray security inspection machines are widely used in the inspection of cargo and luggage. At present, the detection of contraband in X-ray security images is done by security inspectors. The single manual security inspection mode has the following disadvantages: 1) The labor cost is high, each X-ray security inspection machine needs to be operated by at least one security inspector and the processing speed is limited. 2) The detection accuracy is unstable, and the detection accuracy is affected by many uncontrollable factors, such as the mental state, professional ability and freight flow of security inspectors. With the increase in traffic and cargo transportation, ordi...

AI Technical Summary

Problems solved by technology

The single manual security inspection mode has the following disadvantages: 1) The labor cost is high, each X-ray security inspection machine needs to be operated by at least one security inspector and the processing speed is limited

2) The detection accuracy is unstable, and the detection accuracy is affected by many uncontrollable factors, such as the mental state, professional ability and freight flow of security inspectors, etc.

But so far, no report has been found on the detection method of airport X-ray contraband images based on the attention mechanism.

Images