Deep learning machine vision for glass bottles

Deep Capture, an industrial vision software using deep learning, enables the detection of the position (X, Y) of glass gobs dynamically on a conveyor. The challenge in detection comes from the product’s reflectiveness, which causes the shapes of the gobs to vary as they move along the conveyor. Additionally, the low opacity of the glass on the metal-scaled conveyor makes it difficult to create sufficient contrast between the product and its support.