Product packaging surface defect detection and classification method based on machine vision

Abstract

The invention discloses a product packaging surface defect detection and classification method based on machine vision. The method comprises the steps of 1, acquiring a high-definition color image of defect-free product packaging, making the high-definition color image into a standard image, conducting real-time shooting with a camera, conducting online acquisition of a high-definition color image of product packaging to be detected, and making the high-definition color image as an image to be detected; 2, conducting image matching on the image to be detected and the standard image based on SURF algorithm; 3, conducting difference image operation on the two images matched in step 2 to obtain a defective image; 4, conducting feature extraction on the defective image to obtain the geometrical features and color features of the defective image; 5, classifying product packaging surface defects by means of RBF neural network algorithm. Automatic defect detection and classification are conducted by means of a machine vision system, human factor interference can be avoided, labor cost is reduced greatly, and then huge hidden cost caused by training and management when artificial detection is adopted is avoided.

Description

technical field [0001] The invention belongs to the field of packaging inspection, and in particular relates to a method for detecting and classifying surface defects of product packaging based on machine vision. Background technique [0002] With the development of modern printing industry, people have higher and higher requirements for printing technology. Under the background of this era, fast and high-precision image detection and recognition algorithms are needed to meet the current high-speed and high-precision requirements of surface defect detection. Development in the direction of low cost. [0003] Common surface defects mainly include: missing printing, stains, scratches, pasting, flying ink, chromatic aberration, inaccurate registration, etc. Due to the above situation, the reject rate is too high, which will seriously affect the production quality. In order to strictly control the unqualified rate, it is necessary to inspect the printing surface during printi...

AI Technical Summary

Problems solved by technology

The system is a sampling inspection, which has a certain effect on the inspection of process defects, such as inaccurate registration, large-area missing printing, etc. Defect detection is not ideal

[0006] In addition, most of the existing online inspections are based on grayscale images, and there are few inspections on colors, but the problem of color cast is a defect that cannot be ignored

When inspecting color images, the traditional method is to convert color images to grayscale images, but this will lose a lot of color information, making it difficult to detect color-related defects

[0007] Therefore, the existing surface defect detection system can only detect a certain type of defect within a certain range, which has certain limitations, such as slow detection speed, high detection cost, and single detection type.

Images