Information processing method and information processing equipment

Abstract

The invention provides an information processing method and an information processing equipment. The information processing equipment can be used to detect an abnormality in an image file including arepetition pattern, and includes a processor configured to: encode a current region of the image file as a detection target with a pre-trained auto-encoder to obtain a hidden variable of the current region; obtain similar regions of the current region from the image file, and encode each similar region by using an auto-encoder to obtain a hidden variable of each similar region; modify the hidden variable of the current area based on the obtained hidden variable of the similar area; decode the modified hidden variable by using an auto-encoder to obtain a reconstructed region of the current region; and compare the current region with the reconstructed region, and judge whether the current region is abnormal or not based on a comparison result.

Description

technical field [0001] The present disclosure generally relates to the field of information processing, and in particular, relates to an information processing method for detecting anomalies in image files including repeated patterns and an information processing device capable of implementing the above information processing method. Background technique [0002] In different technical fields or production industries, the detection and processing of images comprising repetitive patterns is often involved. As examples, fabrics with repeating textures or patterns (such as carpets, curtains, clothing, etc.), printed matter with repeating patterns (such as wallpaper, decorative paintings, etc.), even photographs obtained by taking items that include repeating patterns, etc. Treated as images that include repeating patterns. [0003] In processing related to images that include repeating patterns, it is often desirable to detect anomalies or defects in the images. For example, ...

AI Technical Summary

Problems solved by technology

However, manual-based operations are time consuming and unreliable as many of the flaws on the fabric surface are small and difficult to identify

In addition, although in recent years, with the development of computer vision, automatic fabric defect detection has been paid attention to and applied, but at the same time, the texture of fabrics has become more and more complex and diverse, thus making fabric quality inspection more difficult. task becomes more and more difficult

Images