Machine vision label proofreading method based on vector object segmentation

Abstract

The invention discloses a machine vision label proofreading method based on vector object segmentation. The method comprises the following steps: 1, obtaining a standard sample grid image group by performing analyzing and storage processing on a standard sample image of a label, wherein the standard sample image comprises a standard sample vector figure, a standard sample vector text and a standard sample grid mage; 2, obtaining a sample image to be detected of a label to be detected for comparing with the standard sample grid image group so as to obtain difference images different from the standard sample image in the sample image to be detected; and 3, by taking a storage unit as a unit, presenting a proofreading result to an operator so as to complete proofreading. The method automatically processes vector figures and vector texts, prevents occurrence of the difference images not needing attention in the proofreading, and enables the proofreading result to present real differences between a sample to be detected and a standard sample.

Description

technical field [0001] The invention relates to a machine vision label proofreading method based on vector object segmentation. Background technique [0002] At present, in the design stage of the label design industry or label printing related industries, or the product quality control stage, people need to find out the mistakes in design revisions, typos or errors in product printing. Whether the items to be compared are patterns or text, most of the content is the same, just look for small mistakes or differences. [0003] In the prior art, human eyes are used to manually compare the actual label, or to display it on a computer screen and use human eyes to perform manual comparison. The new technology is to use scanner and machine vision technology to automatically align the label image of the sample to be tested with the label image of the standard sample, and automatically subtract to obtain the difference image, thus realizing automatic proofreading based on machine v...

AI Technical Summary

Problems solved by technology

And the real fallacious differences are there too, which are hard to spot due to the interference of too many "allowed" differences