Skip to main content

AI visual inspection tool simplifies learning and image labelling


The Unsupervised Learning feature can identify normal and abnormal by learning only from normal images (image: Neurocle)

Neurocle has launched version 4.0 of its Neuro-T AI deep learning vision trainer, which creates AI models for vision inspection, along with its Neuro-R runtime API that applies the inspection model created by Neuro-T to the manufacturing process line in real time. 

In certain industries, it is difficult to collect defect data. The new Gan Model Generation Center is designed to solve these cases, so users can create virtual defects similar to the real ones based on a small number of defect images. 

The update also includes 'Unsupervised Learning', which can identify normal and abnormal by learning only from normal images. This function is also good news for users who lack defect data. Users can choose between Anomaly Classification and Anomaly Segmentation depending on the judgment criteria and the method of result confirmation.

Other features were also added to help users significantly reduce labeling resources. Auto-Selector automatically labels areas with similar characteristics based on objects, while  the Keyword Labeler labels keywords when part of the image corresponds to a keyword.


Read more about:

Artificial intelligence (AI)

Media Partners