Deep Capture

Deep Capture is a deep learning vision software allowing objects detection, analysis and classification. This software is the most efficient on the market in terms of image analysis in an industrial environment, and is used on complex inspection issues to which traditional vision systems cannot respond (great diversity of references, objects with strong light reflection ). The software works in guided learning, from labeled images on the areas sought. Working on the best GPUs on the market, we are able to detect and process images in real time at framerates above 60 fps per camera. Deep learning makes it possible, from a set of image data to be detected, to generalize the detection of unrecognized elements. In other words, the system is capable of detecting objects with a large variation in shapes, textures, dimensions, etc. From a "hypermodel" created by our teams, the software allows the detection of defects over a large area. variety of references without changing particular formats (no change in camera or lighting position) and freeing you from variations in exterior lighting.