Cognex VisionPro ViDi – Deep Learning Based Vision Software

Posted on Posted in Cognex ソフトウェア, 製品情報

VisionPro ViDi is the best-in-class deep learning vision software designed specifically for manufacturing. It is a field-tested, optimized, and reliable software solution based on a state-of-the-art set of machine learning algorithms. Combining deep learning technology with VisionPro software, VisionPro ViDi solves complex applications that are too difficult, time-consuming, or expensive for traditional machine vision systems.

VisionPro ViDi combines a comprehensive machine vision tool library with advanced deep learning tools inside a common development and deployment framework. It simplifies the development of highly variable vision applications.

 

Flexible programming interface

Through a graphical programming environment, VisionPro ViDi allows engineers to build flexible, highly customized deep learning solutions tailored to their specific needs. By harnessing the power of a Windows-based PC with GPUs, the software can process hundreds of images per minute. Programmers can build end-to-end solutions to suit their individual requirements.

 

Simplified integration in a common environment

Users can take advantage of the extensive selection of traditional machine vision tools alongside innovative deep learning tools. VisionPro ViDi provides access to both VisionPro and ViDi toolsets through programmatic integration, as well as through the Cognex Designer graphical development interface. From low-level machine integration to deploying an application-specific HMI using Cognex Designer, VisionPro ViDi provides flexibility in how you develop and integrate the vision inspection to your production environment.

 Innovative deep learning toolsVisionPro ViDi provides traditional vision users access to example-based deep learning tools. These tools are optimized for AI inspections in a manufacturing environment and require smaller image sets for quicker training. The user-friendly GUI also provides a simple environment to manage and develop your applications. Choose between Blue-Locate, Red-Analyze, Green-Classify, and Blue-Read tools to solve applications that are too complex for traditional rule-based machine vision approaches.

 

Hardware & OS Requirements CPU Intel Core i5 (minimum), Intel Core i7/Xeon (recommended)
GPU NVIDIA graphics card (CUDA compute capability of 3.0 or higher required. To use Low Precision mode, compute capability of 6.1 or higher required.)
For training purposes, a minimum of 3 GB graphic memory is recommended.
Note: VisionPro ViDi performance — in terms of processing time — will depend on hardware selection.
RAM Memory 4 GB (minimum), 8 GB (recommended)
USB 1 free USB port (for the license dongle)
OS Windows 7 64-bit
Windows 10 64-bit
Windows Server 2016 64-bit
Supported image file formats PNG, BMP, TIFF, JPEG
Supported image properties 1–4 channels, 8 or 16 bits