Every day, textile recycling facilities receive large volumes of used footwear – typically not as pairs but as individual items mixed with thousands of other garments. Identifying matching pairs is challenging, especially when visually similar shoes are made from different materials. In large-scale operations, this directly impacts sorting efficiency and resale value.
To address this challenge, Polish machine vision company AVICON R&D developed an automated solution for VIVE Textile Recycling, one of Europe’s leading textile recycling companies. The system combines artificial intelligence with hyperspectral imaging to identify shoe materials and significantly improve automated shoe pairing.
By integrating Specim hyperspectral cameras, the system adds material information to conventional RGB imaging and 3D measurements. This additional data layer allows the system to distinguish visually similar shoes and improves the reliability of AI-based pairing. As a result, the solution enables more efficient sorting and supports higher-value material recovery. The system processes up to 9,000 shoes per hour across two parallel sorting lines, enabling high-throughput industrial operation.
Automated shoe pairing in large-scale textile recycling
AVICON R&D has nearly 25 years of experience in machine vision and has focused on hyperspectral imaging in recent years. The collaboration with VIVE aimed to improve automation in footwear sorting within VIVE’s high-volume operations.
VIVE processes hundreds of tons of second-hand clothing daily using fully automated sorting lines. Their AI-based system analyzes RGB images and 3D geometry, but cannot always distinguish between shoes made of different materials. Hyperspectral imaging fills this gap by providing reliable material identification for decision-making.
Material identification with hyperspectral imaging
Two Specim FX17 hyperspectral cameras capture hyperspectral data in the NIR/SWIR spectral range, enabling reliable identification of materials such as rubber, plastic, leather, and textiles – even when visual appearance varies.
Post-consumer footwear varies widely in color, wear, and texture. By measuring material-specific spectral signatures, hyperspectral imaging enables consistent identification regardless of visual differences. After normalization, the system processes spectral data using AVICON’s proprietary HSI-CNN classifier.
In testing, material classification accuracy averaged 81.2%, with the highest accuracy for textiles (87.8%) and rubber (85.1%). Parallel hyperspectral stations achieved consistent predictions in over 99.5% of cases. In the pairing process, this consistency is critical, as reliable agreement between stations is more important than individual classification accuracy.
This level of performance enables stable, real-time decision-making in industrial-scale sorting. The system combines material data with RGB and 3D information and passes it to the AI pairing algorithm, which determines whether two shoes form a pair. When a match is identified, pneumatic actuators route the shoes to output buffers.
High-speed processing for industrial environments
The system operates reliably in demanding industrial conditions. The imaging module includes two Specim FX17 cameras with 38° F/1.7 lenses, halogen illumination, and synchronized conveyor-triggered acquisition.
Image processing occurs in three steps: normalization on a Basler microEnable 5 Marathon VCL FPGA frame grabber, classification via HSI-CNN, and post-processing and visualization in Zebra Aurora Vision Studio™. The system achieves an image-to-decision time of around 600 ms, enabling real-time operation.
Two parallel processing lines allow a total throughput of approximately 9,000 shoes per hour, supporting continuous, high-volume processing.
Improving sorting accuracy and economic value
Hyperspectral imaging significantly improves pairing reliability by adding material information to the decision process. This reduces mispairing and increases confidence in automated sorting, even at high throughput.
Beyond accuracy, material identification enables economic optimization. Shoes made from higher-value materials, such as leather, can be prioritized for pairing, increasing resale value and improving the overall efficiency of the sorting process.
Why AVICON chose Specim
According to Jan Jaczewski, CEO of AVICON, the Specim FX17 camera delivers the performance required for industrial hyperspectral applications: high frame rates, excellent spectral and spatial resolution, TEC sensor stabilization, automatic black calibration, and a high signal-to-noise ratio.
The CameraLink interface enables high-speed transfer of raw hyperspectral data for real-time preprocessing, supporting accurate classification on fast conveyor lines.
Enabling the circular textile economy
AVICON sees increasing opportunities for hyperspectral imaging in circular textile processes. As textile and footwear reuse grows, automated sorting becomes essential for efficient processing and material recovery.
Hyperspectral imaging, combined with AI, can also support new business models for secondhand clothing by enabling detailed product information, similar to new retail. In recycling applications, accurate material data supports projects such as VIVE Texcellence, which produces composite materials from used textiles and plastic waste.
Collaboration with Specim
“If you need hyperspectral imaging for your application, give Specim a try. They provide state-of-the-art cameras and outstanding support during both the project realization and technology qualification phases,” says Jan Jaczewski.
The project “Automation of the footwear identification process using modern machine learning methods” (POIR.01.01.01-00-0532/19) was co-financed by the European Union.
More information about the research phase of the project is available in the related scientific publication:
http://dx.doi.org/10.14313/PAR_256/85
