HxGN Visual Detection: Aprendizaje automático

Inspección de superficies impulsada por IA

Ingeniero frente a un escritorio utiizando HxGN Visual Detection
HxGN Visual Detection utiliza modelos de aprendizaje profundo CNN (red neuronal convolucional) para entrenar, identificar y categorizar los defectos de las superficies. Requiere de una cantidad relativamente pequeña de ejemplos de defectos (del orden de cientos) para comenzar. Conforme descubre defectos no detectados, el modelo se puede entrenar para aumentar su capacidad de identificar positivos verdaderos.

Los algoritmos en HxGN Visual Detection utilizan el reconocimiento de patrones, estadísticas, aprendizaje profundo y otras técnicas de procesamiento de imágenes para aprender rápidamente acerca de las desviaciones de la superficie. 

El proceso de aprendizaje automático de HxGN Visual Detection
 

Deep learning drives greater accuracy

Successful deep learning relies on the depth and sensitivity of the learning model and its environment. HxGN Visual Detection includes a set of models (X-CNN, X-CNN-Tiny, X-CNN-Plus and Segmentation) which are optimised for performance and accuracy. 

The construction of an advanced neural network increases HxGN Visual Detection’s ability to quickly and correctly identify defects, also known as true positives. Powerful algorithms including synthetic image data augmentation, image morphing, normalisation and dimensionality reduction all contribute to this process.

The foundations of these models are based on accepted industry frameworks such as GAN, YOLO, and RCNN.  

HxGN Visual Detection provides an open architecture design that can be easily integrated with custom CNN models. The application is extendable through an API and can be integrated into third party automated manufacturing cells.
 
Advanced-neural-networks-icon
Advanced neural networks 
Synthetic image data augmentation, image morphing, and normalisation algorithms.

 
 
 
Easy-to-use-hyperparameters
Easy to use hyperparameters
Fine-tuned image analysis without coding.
 
 
 
 
You-only-look-once
Built on YOLO (you only look once) CNN principles
Leading neural network for fast object detection.




CNN-models
Choose from a range of CNN models
Select the most useful machine learning model for your application.




Automate-with-third-party-systemsAutomate with third-party systems
Add to vision and metrology workflows via Bridge application
Información personal
Información de su empresa