Positive and negative data set bidirectional joint intelligent image judgment method based on X-ray machine image

Abstract

The invention discloses a positive and negative data set bidirectional joint intelligent image judgment method based on an X-ray machine image. The method comprises the following steps: respectively acquiring a plurality of X-ray machine pictures with dangerous goods and / or safety goods to form a sample data set, dividing samples in all sample data sets into dangerous goods and safety goods according to attributes of goods in the pictures, extracting feature information of various dangerous goods and safety goods in the pictures, and correspondingly establishing a positive data set and a negative data set; performing neural network training on the negative data set and the positive data set to form a negative sample network training model and a positive sample network training model; acquiring data of an article in the to-be-judged picture; and respectively inputting into the negative sample network training model and the positive sample network training model to carry out target detection, identifying the safety goods and the dangerous goods in the picture, and displaying in the picture. Effective measures can be provided for improving the detection rate and the like.

Description

technical field [0001] The invention relates to the field of X-ray machine image recognition, in particular to a two-way joint intelligent image judgment method based on positive and negative data sets of X-ray machine images. Background technique [0002] In recent years, international and domestic aviation incidents have occurred frequently, and the security situation has become increasingly severe. The market demand for airport security inspection systems has also increased year by year. In order to ensure the safety of passengers, it is necessary to be able to accurately identify prohibited items in luggage packages during security checks to reduce the probability of danger. For the inspection of passengers' luggage and air cargo, the current main method is to use the X-ray machine to identify images generated after fluoroscopy to prevent prohibited items from being carried on the plane. Therefore, the identification and detection method of X-ray machine images is the ai...

AI Technical Summary

Problems solved by technology

Airport security checks have high requirements on the accuracy and efficiency of X-ray machine image recognition. For X-ray machine security inspectors, manual recognition with the naked eye is not only low in automation, heavy workload and easy to fatigue, but also due to dangerous goods There are many kinds of baggage, as well as different luggage placement angles, different object densities and volumes, and other reasons. It is also very easy to make misjudgments during the identification process, which increases the difficulty of security checks and poses hidden dangers to civil aviation safety.

Images