Deep learning machine vision software for gobs
Dynamic glass "gob" position detection system

Deep learning industrial vision for glass bottles

Deep capture, machine vision software in deep learning allows the detection of glass gobs position (X, Y) on a conveyor dynamically.

The difficulty of detection lies in the reflection of the product making the gobs shapes variable as a function of their advance on the conveyor. In addition, the low opacity of the glass on the metal scale conveyor does not make it possible to sufficiently contrast the product on its support.

Consumer PC

INTEL CORE I9 7940X
32GB RAM
2x GEFORCE RTX 2080TI-11G
WINDOWS 10

SVS VISTEK camera

Configuration of the deep learning model compatible with Google’s open source platform: TensorFlow.

Results detection and communication on Deep Capture software.

Taking photos and labeling on deep vision software