Solutions
V²
Vision × Validation — automatic detection of fine defects with deep learning
Questions this page answers
- Can AI catch defects that rule-based vision cameras miss?
- How are hard-to-detect defects in injection molding identified?
- Can AI vision inspection be introduced without stopping the line?
The defects rules cannot catch
The hardest cases in vision inspection are the defects that are difficult to define as defects at all. A small change in lighting or angle and a rule-based camera either misses them or rejects good parts.
V² collects and analyzes imagery and process data from the shop floor in real time, detecting fine defects such as scratches and contamination automatically through deep learning.
The AI behind it
Quality prediction and process optimization — XGBoost and genetic algorithms predict quality and derive optimal process conditions automatically.
Anomaly detection — Models trained on images of normal parts detect subtle anomalies, which is particularly useful where defect samples are scarce.
No line stoppage
Multimodal sensor data is fused to predict quality quantitatively, and lightweight models on edge devices allow high-speed inspection and optimal condition derivation without interrupting the process.
Components and key capabilities
- Fine defect detection
- Deep learning catches scratches, contamination and other defects that rule-based cameras miss.
- Multimodal fusion
- Combines imagery with sensor data to predict quality quantitatively.
- Lightweight edge models
- Runs on edge devices for high-speed inspection without interrupting the process.
- Quality prediction and process optimization
- Derives optimal process conditions automatically using XGBoost and genetic algorithms.
- Anomaly detection
- Models trained on images of good parts alone pick up subtle anomalies — suited to sites with few defect samples.