Wizer DP

Wizer DP has AI 3 modules to meet to the market needs, and this includes Trainer, Detect & Classify. The Trainer module is needed to build up the recipe by training selected good images & different group of NG images. The Detect module is used to detect the defects on the production parts, and the Classify module is used to classify the defects type. It has been proven that deep learning will be able to recognize a defect even if the production parts have some different variation on the threshold or machining marks.

WIZER DP Training Process in 3 Steps

The WIZER DP is to be able to train sufficient sample size of good parts, and “marking” the defects area on the NG parts. During the production, new group of NG parts can be marked & added to the existing database to improve the inspection capability.

Step 1. Image Acquisition

Minimum 30 images for each class
Every error class needs separate images

Step 2. Learning

ImageGen™ generates 10 or 100 times images using realistic models

Step 3. Inference

WIZER DP uses trained data
If inspection condition is changed, retrain using pre-trained data

The WIZER DP Trainer Module, selection of good images and NG images for the software to learn. Robust result for target shape, size, colour.

The WIZER DP Detect Module, to detect the defects on the production parts like cracks, stains or scratches. Abnormal position detection and segmentation.