Cookie Consent by PrivacyPolicies.com
Quality Automation with AI and Relimetrics

Knowledge Hub

What, How, why?
User Guide
Installation
Learning center

Version 3.0.0

Learning Center

ReliVision is the AI Solution [Development & Maintenance] Life Cycle Management platform for developing AI-based computer vision solutions. ReliVision brings you:

  • Flexible, distributed, hardware agnostic deployment capability,
  • Scalability by design across lines/plants,
  • End-to-end pre-implemented AI life cycle,
  • Maintained state-of-the-art AI model library.

In this center, you will have the chance to get first-hand experience with ReliUI in building your own detection, segmentation, classification applications, and even combining them to build more complex solutions, all without writing a single line of code. 

We will walk you through sample use cases with instructive documents and share the data with you to try it yourself. Such AI solutions are easily deployable via the platform’s edge module, ReliAudit, virtually in any topology you need.

Quality Automation with AI and Relimetrics

Detection of Solar Panels from Aerial Photographs

The task is to detect solar panels on aerial photographs.

Quality Automation with AI and Relimetrics

Defect and Classify Defects on Metal Nuts

The task is to defect and classify defects on Metal Nuts

Quality Automation with AI and Relimetrics

Detect Threat Objects from X-Ray Images

The task is to detect various threat objects, if there is any, from X-Ray images with discriminating the type. This is a multi-class Object Detection task where classes are hammer, scissors, gun and knife.

Quality Automation with AI and Relimetrics

Detect and Classify Defected Characters on Metal Plates

The task is to detect imprinted alphanumeric characters on metal plates and classify them. This is a Detection followed by a Classification task and can be realized as a pipeline composed of a detector followed by a classifier.

Quality Automation with AI and Relimetrics

Detect and Classify Defects on Metal Nuts

The task is to detect defects on metal nuts and classify them. This is a defect detection followed by a 3-class classification task and can be realized as a pipeline.

1. The main tab displays the number of audits conducted over specific periods, such as by date and hour. This temporal analysis helps in identifying peak times, trends, and patterns in audit activities.

2. The user can filter audit results based on their needs, selecting options to view audits performed on a monthly, weekly, daily, or hourly basis using the filter (1). After choosing the desired filter, click the “Update” button (2) to refresh the results.

3.  The table view displays the audit outcomes, including the count, type, and percentage in relation to the total number of audits conducted over a specified period.

4. The 'Other' audit section highlights the primary reasons for unsuccessful audits, providing details on the number and type of these audits.

5. In the graph view, audit results are presented in a user-friendly format, allowing users to easily review audit outcomes filtered by hour, day, week, or month.

1. The Audit History displays the Audit outcomes conducted by the AI solutions, allowing the user to see the quality check and inspection results in real time.

2. The user can type the “Search Audit” area to view the results and use the “Select Option” filter to customize the audit results display based on specific preferences.

3. Once completed, click “Run Audit” to generate and display the audit results in detail. The Audit Results tab will show a “Processing” status until the audit is fully completed and the results are ready for review. To view these results, click on any button in the “Audit Result” column.

4. The user can check a comprehensive breakdown of the audit results, highlighting areas of interest such as detected defects (1), showing/hiding annotations (2), and zooming (3) on the detected components.

5. The user can accept or dispute the audit results. This feedback loop is vital for refining the AI models and adapting to changing production conditions.

6. The user can review previous audit results by navigating to the "Audit History" tab on the main page.

Download