Automatic Extraction Method of Detection Area of ​​Large Sheet Image in Offset Printing

Abstract

The invention relates to a method for automatically extracting a detection area of ​​a large offset printing image, which comprises the following steps: selecting a large offset printing image and preprocessing the offset printing large image; extracting one of the small single image areas in the offset printing large image, And automatically extract the positioning nucleus area in the small single image area; scale the large offset printing image, and obtain other small single image areas in the large offset printing image according to one of the extracted small single image areas, and perform Preliminary positioning: Accurately locate the positions of all small single-sheet image areas according to the automatically extracted positioning core area, and obtain all detection areas of offset printing large-sheet images. The present invention adopts an algorithm for automatically extracting positioning points, combined with image-based cross-correlation matching algorithms, feature point extraction and other methods, and achieves good results in automatic product area extraction in most application scenarios, and satisfies the needs of visual inspection in the offset printing industry. The need to automatically extract the product area of ​​a large image.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an automatic extraction method for quickly finding all product detection areas in a large offset printing image in visual detection. Background technique [0002] Printed matter detection is generally divided into two steps in the specific implementation: the first is the modeling part, that is, the standard printed matter image is obtained through the image collection of qualified products, and the template for detection is established with the standard image, which divides the standard image into different parts. The detection area, and the corresponding detection algorithm is specified for each different detection area. Secondly, it is the process of inspection execution. During this process, the camera collects the images to be inspected in real time, inspects the products to be inspected according to the previously established template, and performs final binning pr...

AI Technical Summary

Problems solved by technology

However, the manual modeling process is cumbersome and requires the modeling operator to have certain professional knowledge

[0004] The closest existing technology is to use operators such as template matching to find the detection area of ​​the same small sheet on a large image; but using operators such as template matching directly will take a huge amount of time due to the large image. For offset printing The requirements for rapid modeling and testing proposed on site cannot be met

Images