Smart X-Ray Inspection System

AI solution for manufacturing that we have commercially deployed in Milarex, a large salmon processing company, that has already exceeded EUR 200 million in annual turnover. FIRECRUX is already installed on 14 production lines. Ultimately, 60 production lines are to be built.

0 %
increase in contamination detection efficiency
0 %
increase in production line speed
250 M+
total trays of salmon scanned
factory deployment

Project info

Milarex banner
Go‑Live Date
System development
2019 - 2022
Maintenance contract
Nov 2022 - ...

FIRECRUX has provided 61,1% increase of X-Ray contaminants detection efficiency.

Client struggled with low efficiency of X-ray contaminants detection (such as metal, glass, ceramics) in food production. The detection method at the outset was at 62% total efficiency.

We analysed clients data and developed a new X-ray detection method based on machine learning algorithms that increased detection efficiency to 99.9%.

In addition, the new detection method accelerated the manufacturer’s production lines from 1,2 m/s to 2 m/s repositioning the bottleneck of the whole system to a different area.

Guiding principles

Enhanced detection

Milarex was determined to build a system characterized by high flexibility, enabling the expansion of its product range. However, this capability had to meet rigorous requirements regarding detection effectiveness.

Downtime Reduction

The previous system caused almost 2 hours of daily downtime due to false positives. Reduction in of FP was crucial for enhancing production profitability. It was imperative to bring false positives down from 20% to a maximum of 5%.

Operating in real-time

The new contamination detection method must operate at a speed no slower than the current system, as it is crucial to maintain synchronization between various stages of production. Faster operation was highly desired.

Energy efficient

Effective energy management aimed not only at achieving cost savings but also at extending the operational lifespan of X-ray lamps, which is crucial due to their high replacement costs.

Results and customer benefits

The project began with the analysis of a vast image database, a process that took nearly 6 months to appropriately classify. The acquired training material served as the foundation for developing multiple classification models using Machine Learning, particularly Deep Learning techniques.

Two Overlapping Neural Networks

We simultaneously employed two neural networks because deep learning has its limitations. FIRECRUX models for AI was trained using two datasets: one comprising images of pristine, uncontaminated products, and the other containing images of products mixed with contaminants. This dual dataset strategy allows us to address three key scenarios:

  1. Verification of a clean production line – in this case, the classification model trained on clean product images exhibits the highest score.
  2. Detection of contamination within the scanned area – the scoring is reversed to identify the presence of contaminants.
  3. Ensuring manufacturer safety in unusual situations involving impurities outside the tested spectrum or intentional sabotage – in such instances, the models produce similar scores, signaling a suspicious situation. For safety reasons, these situations are flagged and rejected for investment by our staff.

Hardware Requirements

System that has been developed is based on the FIRECRUX engine and can be operated on GPU, CPU, or VPU processors. In the current version at Milarex, it runs on a GPU processor using the nVidia Jetson TX2 Developer Kit (945-82771-0005-000). The CPU version is embedded on Intel i7 and i9 processors, while the VPU version utilizes Intel Movidius.

Furthermore, the software has been seamlessly integrated with X-ray lamps, including the SAXG monobloc x-ray generators from Spellman and a line scan detector from Detection Technology.

FP Reduction and Effectiveness Testing

The previous solution utilized by Milarex, developed by a Canadian company, led to significant downtime due to the occurrence of false positives (FP), averaging nearly 2 hours per day. During the initial phase of our solution’s development, around 2017, we placed considerable emphasis on addressing this FP issue. Through rigorous testing, both on quality control testers and in real-world contamination scenarios (such as detecting broken knives from portioning machines, identifiable medical plasters, or glass fragments), we successfully reduced the FP rate from approximately 20% to less than 1%.

Subsequently, we resolved this problem and integrated the option to mark FP (False Positives), NP (Non-Presence), and TP (True Positives) within the X-ray scanner management system.

We rely on machine-generated data, specifically the number of scans, detections, and saved confirmation photos, to monitor the system’s performance.

Real-time Contamination Detection

The completed system also enables on-the-fly scanning. Our software has been designed to accommodate two types of machines: cyclic and continuous scanning.

The cyclic scanning method proved sufficient for machines handling 9/12/16 pieces of salmon, as the production line’s manual worker efficiency was the bottleneck in these scenarios.

In 2021, a continuous scanning solution was developed. Instead of having 9/12/16 trays go into the bin upon contamination detection in the cyclic machine, the fish are now seamlessly redirected to the real-time scanning machine without the need for a ‘stop-start’ action.

Production Deployment and Licensing

The solution for a first machine was implemented in 2019 and an additional 13 machines were gradually added between 2019 and 2022. Subsequently, development efforts continued until November 2022 and a local data cloud was established.

The final version of the system achieved two significant milestones:

  • A 61% increase in contamination detection efficiency,
  • A 66% increase in production line speed.

In Nov 2022 licensing and maintenance agreements were signed and currently Greenlogic is solely dedicated to optimizing classification models to maintain a high level of contamination detection accuracy.

Benefits Beyond the Project Scope

New Production Detection Capabilities

Visual detection based on machine learning algorithms can play many roles in the production process. It will both find the right objects (desirable or not), but is also able to count, measure, weigh or compare them with a given pattern.


The classification model is trained based on the perfect product pattern, so even if the AI does not find a known contamination on the product, it will be able to react due to the lack of confirmation of a "clean scan".

Object Type

Recognition of the type of objects in order to complete the set (e.g. in the furniture industry).


An example of detection with the determination of the size of the object as a parameter of the threat.

Technical stack

Next use cases banner

Recommendation Engine & Personalization Platform

Learn how we developed and implemented a website personalization system for one of the largest travel agents in Poland.

Eye Measurements & Cylinder Alignment App

Explore the history of pioneering a unique method across Europe to provide superior eyewear for hundreds of thousands of brand customers.


Over 400 projects for 140 clients