Headlight lens defect inspection using neural networks | Elya

Headlight lens defect inspection using neural networks

December 2, 2021

The aim was to complement the existing inspection cell with cameras and electronics for evaluation using neural networks.

The existing equipment sends an image to a small industrial computer (subject of delivery) where it´s analysed using a neural network based on ResNet-50. All scratches, fingerprints, fibres, etc. are searched for. Subsequently, information is sent back to the inspection equipment to find out the image is OK or NOK.

The actual communication is done using a standard RPC call, so implementation into the control system of an existing cell was easy.

Other Case Studies

světlovodné díly-01

Machine for optical analysis of light guide parts

100% optical analysis of light homogeneity and part manufacturing defects into the existing production line of PMMA (Conductor) light guide parts.

Jednoúčelové zařízení-01

Single-purpose machine for sorting fuel filters based on optical analysis – extension to different shapes of products

Repeat delivery of a single-purpose machine with an extension to different types of the fuel filters. At the same time, the existing requirements for high machine speed (1 pcs/1 sec), loading capacity and reliability requirements for optical inspection had to be met.

automatizovaný systém

Automated system for checking and archiving security features

For a customer in the automotive industry, we have designed and delivered an automated system for the inspection of safety features in the production of dashboards, including a data storage system for each product.

All Case Studies