Enhanced deep learning training, models, and inference engine
MIL X uses deep learning technology
—specifically the convolutional neural network (CNN) and variants—to perform image and pixel classification for identification and defect detection tasks, respectively.
With SP5, users benefit from a simplified workflow for training a deep neural network, corresponding new models producing finer results in the case of segmentation, and a new inference engine enabling higher performance and broader hardware support. MIL X provides the infrastructure and interactive environment for building the training dataset and monitoring and analyzing the training process. SP5 streamlines training by automatically subdividing the training dataset, offering preset augmentations, and proposing a neural network model to start with. Matrox Imaging also continues to make its specialists available for hire to train a deep neural network on a user’s behalf using the same above facilities.
New 3D processing operations, shape finding, and blob analysis
MIL X has a rich set of tools for performing 3D processing and analysis. The enhancements in SP5 include filters for noise removal, while two new tools—for shape-finding and blob analysis, respectively—further expand a user’s ability to locate and measure features and objects in a point cloud.
A product demo video
highlights how two Matrox AltiZ 3D profile sensors and MIL X with SP5 vision software running on a Matrox 4Sight XV6 vision controller perform a variety of 3D analysis tasks.
Hand-eye calibration for robot guidance
Another tool, 3D calibration, now further facilitates the use of a camera or sensor within a robotic cell. Users can opt for eye-to-hand or eye-in-hand calibration, both of which accurately relate what a camera or sensor sees—the object pose established using other MIL X tools—to a robot controller for guidance.
More new tools and functionality
MIL X SP5 boasts improvements to Matrox SureDotOCR tool for reading dot matrix text produced by inkjet printers and dot peen markers. The updated tool now supports text of variable length as well as variation in dot size and overlap.
Finally, SP5 delivers a revamped CPython interface, which features NumPy support, improving the experience and efficiency for those developing using this popular high-level programming language.
“With the release of MIL X SP5, the capabilities of our vision SDK are even more pronounced, especially in the 3D and deep learning spaces,” says Pierantonio Boriero, Director of Product Management. “New neural network models, inference engine, and simplified deep learning training, plus improved 3D tools all combine to present the most capable version of this SDK yet offered.”
SP5 for MIL X is now available.