Research of Express Box Defect Detection Based on Machine Vision

The traditional box appearance defect detection adopts manual detection which is low accuracy and time consuming. In order to overcome the drawbacks of manual detection and improve transportation automation, an effective and convenient defect detection algorithm of express boxes is proposed. The central idea of the proposed algorithm is to solve defect identification problems during transportation. This technique only needs to observe defects through the binocular camera system, thus the parameters of shape and size can be obtained subsequently. Finally, experiments are carried out. Results show that the algorithm can accurately identify different shaped defects and the highest reconstruction correct rate is up to 95.83%. The results verify the applicability of the proposed approach.