Multi-scale print defect detection method based on random forest

Abstract

A random forest-based multi-scale defect detection method for printed matter. A certain number of aligned and qualified printed matter images are input to form a training sample. After setting the detection area, generating defect detection points and multi-scale representation of the training sample image, the Collect its cross-channel binary features for each defect detection point at each scale, and then train the random forest to generate a random forest defect detection model for each defect detection point at multiple scales; after having the model, given the test image , first generate a multi-scale representation, and then apply the trained random forest defect detection model at each scale to judge whether there is a defect at the defect detection point, and perform multi-scale screening and synthesis of the defect detection point, and finally generate the detection effect; The invented method improves the speed and accuracy of detection; under the premise of not significantly increasing the computational complexity, the detection effect is better than other current defect detection algorithms for printed matter.

Description

technical field [0001] The invention belongs to the technical field of image-based industrial product quality detection in computer vision, and in particular relates to a random forest-based multi-scale defect detection method for printed matter. Background technique [0002] Packaging printed matter is the "appearance" of many industrial products, and the quality of its printing is related to the degree of consumer acceptance of the product. In recent years, with the advancement of production technology and the continuous improvement of people's quality of life, new printing technologies have been applied to many printed products. The quality of printed matter is an important part of product quality. Therefore, higher requirements are put forward for the automation level of printed matter quality management in the production process. It is required to use machines to detect printed matter defects instead of manual work, so as to reduce costs and improve efficiency. [0003...

AI Technical Summary

Problems solved by technology

[0014] In order to overcome the problems existing in the above-mentioned prior art, the object of the present invention is to provide a multi-scale printed matter defect detection method based on random forest, which improves the speed and accuracy of detection; under the premise of not significantly increasing the computational complexity, the detection effect is excellent. Compared with other current printing defect detection algorithms

Images