HomeDocumentation
Log In
Documentation

Getting Started with VIA

Overview

Neurala VIA is a suite of software tools that use vision AI technology to perform production-line inspections that manufacturers can use to ensure quality and consistency in their manufacturing process.

The Neurala VIA software includes capabilities that address many types of inspection applications and use cases, such as defect identification, product sorting, packaging completion, and others.

This Knowledge Base is organized to make it simple and straightforward to learn how to successfully install, deploy, and run the VIA software in a production environment. It includes the following sections:

  • Quick Start - an overview of Neurala's VIA tools with tips and best practices
  • Brain Builder - detailed instructions on how to use the Brain Builder application to train a variety of AI models.
  • Inspector - detailed instructions on how to use Neurala's suite of Inspector applications to run the trained AI models to perform inspections in a variety of environments.
  • Partner Integrations - additional documentation that details how to use Neurala's VIA applications with partner products, such as Sony's AITRIOS platform.

The VIA Software Suite

The Neurala VIA product line includes the following applications:

Brain Builder Icon

Brain Builder

Brain Builder is used to quickly and easily train and manage "Brains" (vision AI models) for a wide range of use cases.

Brain Builder can be used locally or in the cloud.

Inspector Icon

Inspector

Inspector is the tool that quickly integrates the trained Brains into the automation workflow.

Brain Builder and Inspector work together to easily train and deploy vision AI technology that can be integrated into factory automation equipment, including PLCs, cameras, and industrial PCs.

There are multiple versions of Inspector for different types of deployments, integrations, and platforms, including Inspector, InspectorWeb, and InspectorLib.

Types of AI Models

Neurala VIA supports training and deployment of multiple types of vision AI models

Model TypeDetails
ClassifierClassification models (or "Classifiers") analyze the full image (or a region of the image) and classify the image into one of many "classes" on which they have been trained. These types of models can be used to sort products that are mixed together on a conveyor belt. Integrate vision AI with an automation system to customize product handling based on type.

Classifier model types include Learning Classifier and Static Classifier.
Anomaly RecognizerLike Classifiers, Anomaly Recognition models (or "Anomaly Recognizers") analyze the full image or a specific region. They are trained on what normal product images should look like. The models can then recognize when there is an anomaly or defect in the product and alert the operator.

Anomaly model types include Anomaly Recognizer and Anomaly Hi-Fi.
DetectorDetection models (or "Detectors") can locate one or more instances of defined objects within an image. These models use bounding boxes to show where trained object classes are located and can find multiple instances of an item in a single image.