The appearance quality of fresh vegetables directly determines their market value, yet traditional manual picking faces severe challenges. Highly dependent on workers' experience, attention, and physical condition, manual sorting suffers from visual fatigue during long shifts, significantly increasing missed detection rates. This makes it difficult to effectively intercept defects such as rotten leaves, discoloration, and insect damage.
The Legende HDF Series is an intelligent machine-vision-based sorting system tailored for this exact scenario. Utilizing high-resolution RGB (HR-RGB) VIS imaging and proprietary AI deep learning algorithms, it scans and analyzes surface features of fresh vegetables. Coupled with high-performance air ejectors, the system achieves high-precision rejection of color variations, surface defects, and foreign material within milliseconds.
Empowered by AI-driven surface feature recognition algorithms, the system can conduct deep learning training based on real production data, continuously optimizing the visible defect detection accuracy. This means the equipment’s performance is not fixed at the time of factory shipment; instead, it continuously adjusts and improves with the accumulation of production data, delivering stable and reliable sorting performance to help fresh vegetable processing plants significantly reduce labor dependency, fortify quality defense lines, and effectively guarantee product purity and processing profits.
Applications

Technical Features
● Tailored Machine-Vision-Based Sorting System for Fresh Vegetables
✦ Innovative dual-belt structure
✩ Upper Primary Sorting Belt
Applies stringent rejection standards to efficiently remove surface defects, drastically reducing missed detections.
✩ Lower Secondary Sorting Belt
Performs re-inspection on rejected materials, efficiently recovering good products to boost overall yield.
✦ High-Performance Waterproof Vibratory Feeder
Evenly distributes fresh vegetables into a single layer, effectively minimizing overlapping and sticking to provide stable material posture for high-precision detection.
✦ Easy-to-Clean Structural Design
Constructed with food-grade stainless steel, featuring a sealed camera chamber and electrical box, effortlessly handling high-humidity and complex processing environments.
✦ Built-in Humidity Control System
Ensures the stable operation of internal optical components and electrical systems, meeting the stringent environmental requirements of fresh vegetable processing workshops.
✦ Integrated Self-Cleaning
Automatically cleans the glass of the camera chamber to continuously keep the scanning area clear. This reduces manual intervention and downtime for cleaning, ensuring continuous and stable equipment operation.
✦ Multi-Specification Model Portfolio
Available in three belt width models (600mm, 1200mm, and 1800mm) to meet diverse throughput capacity requirements.
● AI Powered High-Precision Defect Inspection System
✦ High-Resolution RGB (HR-RGB) VIS Imaging
Clearly presents material surface features, providing reliable image input for AI algorithms to ensure the accuracy and stability of surface defect recognition.
✦ Proprietary AI Deep Learning Algorithms
Enhances surface feature recognition capabilities and supports model retraining based on real-world production data, achieving continuous optimization of visible defect detection accuracy through deep learning.
✦ High-Intensity LED Illumination
Guarantees a constant imaging environment with clear and stable images, unaffected by external light changes, ensuring consistent detection results across different time periods and batches.
High-precision machine vision detection for various fresh vegetable defects based on surface features:
✩ Color Defects: Discoloration, mold, rot
✩ Shape Defects: Misshapen, deformed, oversized, undersized, broken
✩ Surface Damage: Bruises, cuts, abrasions, crushing, scars, cracks, shriveling
✩ Biological Contaminants: Insect damage, leaf/stem residues, other vegetable debris
✩ Foreign Material: Stones, soil clumps, plastic/rubber fragments, wood chips
● High-Performance Air Ejector System
✦ Optimized Design
The ejector valve structure is optimized to balance durability, response speed, and air consumption efficiency, maintaining stable performance even under long-term, high-frequency operation.
✦ High Efficiency and Stability
Optimized for high-throughput sorting conditions, it maintains stable ejection performance within reasonable parameter ranges, balancing throughput and sorting accuracy.
✦ Cost Reduction
Significantly reduces the false reject rate, minimizing raw material waste from good products being incorrectly ejected, while optimizing air consumption to reduce overall operational costs.
15-Inch Industrial Touchscreen Control System
✦ Intuitive Interaction
User-friendly human-machine interface (HMI) with multi-language support.
✦ One-Click Switching
Quickly recalls sorting parameters for different products.
✦ Comprehensive remote support
✩ Remote access and real-time monitoring
✩ Performance data dashboard
✩ Online expert diagnostics
✩ Interactive troubleshooting
Specifications
Belt Width
(mm)
Air Nozzle
Air Pressure
(MPa)
Air Consumption
(m3/min)
Voltage
Power
(kW)
Dimension
(mm)
Unpacked Weight
(kg)
Legende HDF2
Specifications are approximate and subject to change without notice. Lauffer Vision reserves all rights for modifications.
Model
600
256
0.6~0.8
<2.0
380V~50/60Hz
6.4
4686×1924×2685
1589
Legende HDF4
1200
512
0.6~0.8
<4.1
380V~50/60Hz
8.7
5258×2358×2685
1935
Legende HDF6
1800
768
0.6~0.8
<4.1
380V~50/60Hz
12.9
5015×2994×2685
2658