Package Printing Defect Detection Method Based on Image Processing

ZHOU Ji-yan, YU Zheng-hong

Packaging Engineering ›› 2017 ›› Issue (9) : 240-244.

Packaging Engineering ›› 2017 ›› Issue (9) : 240-244.

Package Printing Defect Detection Method Based on Image Processing

  • ZHOU Ji-yan, YU Zheng-hong
Author information +
History +

Abstract

The work aims to improve the accuracy and applicability of package printing defect detection, and design a detection method based on image processing. Several key steps, including image registration, automatic selection of registration areas, and defect detection were adopted. The registration area was selected according to the image features of package printing matter. At the same time, a fast image registration algorithm was presented. Then, the defect detection was achieved on the basis of the improved subtraction matching algorithm. The hardware platform of control system was designed based on DSP and FPGA, mainly including control unit, image acquisition and processing unit, imaging unit and so on. Finally, the experimental study was carried out. Experimental results showed that the described method could accurately identify the subtle defect, such as knife filament and brace. The method has higher reliability and universality, which can realize the rapid detection of package printing defects.

Cite this article

Download Citations
ZHOU Ji-yan, YU Zheng-hong. Package Printing Defect Detection Method Based on Image Processing[J]. Packaging Engineering. 2017(9): 240-244

Accesses

Citation

Detail

Sections
Recommended

/