Printing quality detection and analysis system based on deep learning

Abstract

The invention relates to a printing quality detection and analysis system based on deep learning. The printing quality detection and analysis system comprises a Client end independent defect image data acquisition and transmission module, a Client end and Server end communication module, a Server end defect image data receiving and storage module, a Server end defect image deep learning classification module, a Server end deep learning training module and a Server end report display module. Defects are positioned to a process link, a high-quality statistical analysis report is formed, the optimization and improvement work of production, quality, equipment and other departments is guided from the perspective of a production process, the purposes of optimizing the yield, reducing resource waste, reducing cost and reducing cost and efficiency are achieved, and finally the purposes that the quality report is more accurate, the process improvement direction is accurate, and the comprehensive quality is continuously improved are achieved.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a printing quality detection and analysis system based on deep learning. Background technique [0002] Printed cigarette packs will go through different processes in the production process, and various uncertain factors in the production process can easily lead to surface defects and blemishes. In the defect detection of cigarette package printed matter, different layers are usually established with different processes, and the types of defects can be counted according to the layered defect information. [0003] However, the existing detection technology can only define the defect category according to the location of the defect and the algorithm used in the detection. It can only distinguish the abnormality of defective products and good products, but it cannot describe the defect information, let alone accurately locate the process of defect generation. There is no way t...

AI Technical Summary

Problems solved by technology

[0003] However, the existing detection technology can only define the defect category according to the location of the defect and the algorithm used in the detection. It can only distinguish the abnormality of defective products and good products, but it cannot describe the defect information, let alone accurately locate the process of defect generation. cannot find the direction to improve the process or equipment, and the improvement measures cannot be formulated and implemented, so that the defect rate cannot be reduced from the production process

Therefore, the above-mentioned problems are likely to cause a great waste of manpower and material resources of the enterprise, but there is still nothing to do

Images