<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Traditional X-ray machine image recognition methods for airport security system have difficulties in recognition and are prone to result in recognition errors due to the impact of placing angle, density and volume of detected objects. This paper accurately describes the image features of X-ray machine visual image, carries out SVM classification after a visual dictionary is formed and enhances the accuracy of image discrimination by means of robust acceleration. The experimental results indicate that both identification efficiency and accuracy are improved to some extent.</p></abstract>

Traditional X-ray machine image recognition methods for airport security system have difficulties in recognition and are prone to result in recognition errors due to the impact of placing angle, density and volume of detected objects. This paper accurately describes the image features of X-ray machine visual image, carries out SVM classification after a visual dictionary is formed and enhances the accuracy of image discrimination by means of robust acceleration. The experimental results indicate that both identification efficiency and accuracy are improved to some extent.

A Study on Optimization Methods of X-Ray Machine Recognition for Aviation Security System

International Journal on Smart Sensing and Intelligent Systems

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Traditional X-ray machine image recognition methods for airport security system have difficulties in recognition and are prone to result in recognition errors...

A Study on Optimization Methods of X-Ray Machine Recognition for Aviation Security System

Publié en ligne: 01 juin 2015

Pages: 1313 - 1332

Reçu: 25 févr. 2015

Accepté: 30 avr. 2015

DOI: https://doi.org/10.21307/ijssis-2017-808

© 2015 Ning Zhang published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.