Deep learning industrial vision for woodworking

Deep Capture, an industrial vision software using deep learning, enables the identification of wood plank quality at the output of a planer.

Examples of detected defect classes include

As with other industrial vision applications, defects are subject to interpretation. Our deep learning system differentiates results based on the location of defects on the plank (acceptable defects on the plank edges). The acquisition operates in real-time at a scrolling speed of 30 cm/sec.