A5078870647- Industrial Vision Systems and Defect Detection
- 3D Surveying and Cultural Heritage
- Image and Object Detection Techniques
- Manufacturing Process and Optimization
- Non-Destructive Testing Techniques
- COVID-19 diagnosis using AI
- Advanced Neural Network Applications
- Surface Roughness and Optical Measurements
- Tactile and Sensory Interactions
- Radiomics and Machine Learning in Medical Imaging
- Augmented Reality Applications
- Optical measurement and interference techniques
- AI in cancer detection
- Recycling and Waste Management Techniques
- Infrastructure Maintenance and Monitoring
- Anatomy and Medical Technology
Vicomtech
2018-2025
University of the Basque Country
2021-2022
The Corona Virus Disease (COVID-19) is an infectious disease caused by a new virus that has not been detected in humans before.The causes respiratory illness like the flu with various symptoms such as cough or fever that, severe cases, may cause pneumonia.The COVID-19 spreads so quickly between people, affecting to 1,200,000 people worldwide at time of writing this paper (April 2020).Due number contagious and deaths are continually growing day day, aim study develop quick method detect chest...
Personalized production is moving the progress of industrial automation forward, and demanding new tools for improving decision-making operators. This paper presents a new, projection-based augmented reality system assisting operators during electronic component assembly processes. The describes both hardware software solutions, depicts results obtained usability test with system.
This paper explores the use of state-of-the-art latent diffusion models, specifically stable diffusion, to generate synthetic images for improving robustness visual defect segmentation in manufacturing components. Given scarcity and imbalance real-world data, data generation offers a promising solution training deep learning models. We fine-tuned using LoRA technique on NEU-seg dataset evaluated impact different ratios real set DeepLabV3+ FPN Our results demonstrated significant improvement...
This paper presents an automatic system for the quality control of metallic components using a photometric stereo-based sensor and customized semantic segmentation network. is designed based on interoperable modules, allows capturing knowledge operators to apply it later in defect detection. A salient contribution compact representation surface information achieved by combining stereo images into RGB image that fed convolutional network trained We demonstrate advantage this imaging over use...
This paper describes the application of Semantic Networks for detection defects in images metallic manufactured components a situation where number available samples is small, which rather common real practical environments. In order to overcome this shortage data, approach use conventional data augmentation techniques. We resort Generative Adversarial (GANs) that have shown capability generate highly convincing specific class as result game between discriminator and generator module. Here,...
This paper presents an automated inspection and classification system for automotive component remanufacturing industry, based on ensemble learning. The is different stages allowing to classify the components as good, rectifiable or rejection according manufacturer criteria. A study of two deep learning-based models’ performance when used individually using them carried out, obtaining improvement 7% in accuracy ensemble. results test set demonstrate successful terms classification.
The final product quality control is critical for any manufacturing process. In the case of steel products, there are different inspection methods that able to classify defects, but they usually require human intervention. this context, a deep learning-based automatic defect classifier method surfaces proposed. combines some traditional Machine Learning techniques with Convolutional Neural Network (CNN). Different experiments were carried out in order obtain best parameter setup. To verily...
Anomaly detection is an important method in industrial manufacturing environments for defect detection, and consequently, the quality requirements attainment. There a strong trend to automate inspection systems using Artificial Intelligence techniques, especially through use of 2D information. However, dimensional inspection, it necessary have 3D data that provide detailed geometric information object. In this paper, we present novel Deep Learning based approach fast anomaly applicable...