seeing what matters

Deep Learning-based industrial image analysis

Automated detection, inspection and classification

Human-like, Self-learning, Powerful

ViDi offers the first ready-to-use Deep Learning-based software dedicated to industrial image analysis. ViDi Suite is a field-tested, optimized and reliable software solution based on a state-of-the-art set of algorithms in Machine Learning. It allows tackling otherwise impossible to program inspection & classification challenges. This results in a powerful, flexible and straightforward solution for countless challenging machine vision applications. The Suite consists of 3 different tools:

Feature localization & identification

ViDi blue is used to find and localize single or multiple features within an
image. Be it strongly deformed characters on very noisy backgrounds (OCR) or complex objects in bulk; the blue tool can localize and identify complex features and objects by learning from annotated images.

To train the blue tool, all you need to provide are images where the targeted features are marked.

Segmentation & defect detection

ViDi red is used to detect anomalies and aesthetic defects. Be it scratches on a decorated surface, incomplete or improper assemblies or even weaving problems in textiles; the red tool can identify all of these and many more problems simply by learning the normal appearance of an
object including its significant but tolerable variations. ViDi red is also used to segment specific regions such as defects or other areas of interest. Be it a specific foreign material on a medical fabric or the cutting zone on lace; the red tool can identify all of these regions of interest simply by learning the varying appearance of the targeted zone.

Object & scene classification

ViDi green is used to classify an object or a complete scene. Be it the
identification of products based on their packaging, the classification of welding seams or the separation of acceptable or inacceptable defects; the green tool learns to separate different classes based on a collection of labelled images.

To train the green tool, all you need to provide are images assigned to and
labelled in accordance with the different classes.

Graphical & application programming interfaces

Windows graphical user interface (GUI) with plugin support

HTML based GUI (required browser: Mozilla Firefox ESR (extended support release))

C library (Windows DLL / Linux shared object) for runtime and/or training

Microsoft .NET library (Wrapper for C library and WPF GUI components)

Hardware & OS Requirements

CPU: Intel Core i5 (minimum), Intel Core i7/Xeon (recommended)

Optional GPU: NVidia Graphic Card (CUDA compute capability ≥ 3.0)

Recommended: GeForce GTX970-980, GTX1070-1080, GTX TITAN, Quadro K2200-M4000-M6000, Tesla

K40-K80

Memory: 4GB (minimum), 8GB (recommended)

1 free USB port (for the license dongle)

OS: Windows 7 – 64 / Linux - Ubuntu 14.04 64bit LTS

Runtime license support & Maintenance

Licenses are permanent and do not require maintenance or renewable fees

Miscellaneous

Supported image file formats: PNG, BMP, TIFF, JPEG

Supported image properties: 1 - 4 channels, 8 or 16 bits

ViDi Suite GUI & documentation language: EN